From d8de6aca505cd69df548bfc98208ed74203d8c2b Mon Sep 17 00:00:00 2001 From: Taylor Paisie Date: Thu, 22 Feb 2024 15:15:41 -0500 Subject: [PATCH 01/92] Create main.yml --- .github/workflows/main.yml | 137 +++++++++++++++++++++++++++++++++++++ 1 file changed, 137 insertions(+) create mode 100644 .github/workflows/main.yml diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml new file mode 100644 index 000000000..09a300dee --- /dev/null +++ b/.github/workflows/main.yml @@ -0,0 +1,137 @@ + +##### ------------------------------------------------------------------------------------------------ ##### +##### This caller workflow tests, builds, and pushes the image to Docker Hub and Quay using the most ##### +##### recent version of Freyja and downloading the most recent variant information. ##### +##### It takes no manual input. ##### +##### ------------------------------------------------------------------------------------------------ ##### + +name: Update Freyja + +on: + workflow_dispatch: + schedule: + - cron: '30 7 * * *' + +run-name: Updating Freyja + +jobs: + update: + runs-on: ubuntu-latest + steps: + +# Keeping here in case we want to use it to keep Freyja's version up-to-date as well +# - name: Get latest release +# uses: rez0n/actions-github-release@main +# id: latest_release +# with: +# token: ${{ secrets.GITHUB_TOKEN }} +# repository: andersen-lab/Freyja +# type: "stable" +# - name: Remove V +# id: strip +# run: | +# version=$(echo "${{ steps.latest_release.outputs.release }}" | sed 's/V//g' | sed 's/v//g' ) +# echo "The version is $version" +# echo "version=$version" >> $GITHUB_OUTPUT + + - name: pull repo + uses: actions/checkout@v3 + +# Keeping here in case we want to figure out why this doesn't work +# - name: get latest version of freyja in docker-builds repo +# id: latest_version +# run: | +# file=$(git log -1 --name-only --format=%cd --date=iso freyja/*/Dockerfile | grep Dockerfile | head -n 1 ) +# echo "the latest file is $file" +# echo "file=$file" >> $GITHUB_OUTPUT +# +# version=$(echo $file | cut -f 2 -d "/" | cut -f 1 -d "_") +# echo "the latest version is $version" +# echo "version=$version" >> $GITHUB_OUTPUT + + - name: set freyja version + id: latest_version + run: | + version=1.4.8 + echo "version=$version" >> $GITHUB_OUTPUT + + file=freyja/$version/Dockerfile + ls $file + echo "file=$file" >> $GITHUB_OUTPUT + - name: set up docker buildx + id: buildx + uses: docker/setup-buildx-action@v2 + + - name: cache docker layers + uses: actions/cache@v3 + with: + path: /tmp/.buildx-cache-freyja + key: ${{ runner.os }}-buildx-freyja-${{ github.sha }} + restore-keys: ${{ runner.os }}-buildx-freyja + + - name: build to test + id: docker_build_to_test + uses: docker/build-push-action@v3 + with: + file: ${{ steps.latest_version.outputs.file }} + target: test + load: true + push: false + cache-from: type=local,src=/tmp/.buildx-cache-freyja + cache-to: type=local,mode=max,dest=/tmp/.buildx-cache-freyja-new + tags: freyja:update + + - name: get freyja database version + id: db_version + run: | + docker run freyja:update freyja demix --version + version=$(docker run freyja:update freyja demix --version | grep . | grep -v Barcode | head -n 1) + echo "the latest version is $version" + echo "version=$version" >> $GITHUB_OUTPUT + - name: Get current date + id: date + run: | + date=$(date '+%Y-%m-%d') + echo "the date is $date" + echo "date=$date" >> $GITHUB_OUTPUT + + # - name: Login to DockerHub + # uses: docker/login-action@v2 + # with: + # username: ${{ secrets.DOCKER_HUB_USERNAME }} + # password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }} + + - name: Login to Quay + uses: docker/login-action@v2 + with: + registry: quay.io + username: ${{ secrets.QUAY_USERNAME }} + password: ${{ secrets.QUAY_ROBOT_TOKEN }} + + - name: Build and push user-defined tag to DockerHub + id: docker_build_user_defined_tag + uses: docker/build-push-action@v3 + with: + file: ${{ steps.latest_version.outputs.file }} + target: app + push: true + cache-from: type=local,src=/tmp/.buildx-cache-freyja + cache-to: type=local,mode=max,dest=/tmp/.buildx-cache-freyja-new # mode=max means export layers from all stage to cache + tags: staphb/freyja:${{ steps.latest_version.outputs.version }}-${{ steps.db_version.outputs.version }}-${{ steps.date.outputs.date }} + + - name: Build and push to Quay + id: build + uses: docker/build-push-action@v3 + with: + file: ${{ steps.latest_version.outputs.file }} + target: app + push: true + cache-from: type=local,src=/tmp/.buildx-cache-freyja + cache-to: type=local,mode=max,dest=/tmp/.buildx-cache-freyja-new # mode=max means export + tags: quay.io/staphb/freyja:${{ steps.latest_version.outputs.version }}-${{ steps.db_version.outputs.version }}-${{ steps.date.outputs.date }} + + - name: Move cache # apparently prevents the cache from growing in size forever + run: | + rm -rf /tmp/.buildx-cache-freyja + mv /tmp/.buildx-cache-freyja-new /tmp/.buildx-cache-freyja + - name: Image digest From d345f7ae69913430af0d55b13467f1851760fefb Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 11 Sep 2024 13:32:24 -0400 Subject: [PATCH 02/92] adding my seqfu docker container to branch --- seqfu/1.20.3/Dockerfile | 87 +++++++++++++++++++++++++++++++++++++++++ seqfu/1.20.3/README.md | 46 ++++++++++++++++++++++ 2 files changed, 133 insertions(+) create mode 100644 seqfu/1.20.3/Dockerfile create mode 100644 seqfu/1.20.3/README.md diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile new file mode 100644 index 000000000..a22a46dec --- /dev/null +++ b/seqfu/1.20.3/Dockerfile @@ -0,0 +1,87 @@ +# Set global variables +ARG SEQFU_VER="1.20.3" + +# Build Dockerfile +FROM ubuntu:focal AS builder +ARG SEQFU_VER + +LABEL base.image="ubuntu:focal" +LABEL dockerfile.version="1" +LABEL software="SeqFu" +LABEL software.version=${SEQFU_VER} +LABEL description="A general-purpose program to manipulate and parse information from FASTA/FASTQ files, supporting gzipped input files." +LABEL website="https://github.com/telatin/seqfu2" +LABEL license.url="https://github.com/telatin/seqfu2?tab=GPL-3.0-1-ov-file#readme" +LABEL maintainer="Taylor K. Paisie" +LABEL maintainer.email='ltj8@cdc.gov' + +# Set non-interactive frontend +ENV DEBIAN_FRONTEND=noninteractive + +# Set PATH globally to include Nimble binaries +ENV PATH="/root/.nimble/bin:${PATH}" + +# Install required dependencies +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + unzip \ + build-essential \ + zlib1g-dev \ + curl \ + python3 \ + python3-pip \ + git \ + ca-certificates \ + && rm -rf /var/lib/apt/lists/* + +# Set the working directory to /root +WORKDIR /root + +# Run commands in non-interactive mode +RUN curl https://nim-lang.org/choosenim/init.sh -sSf | sh -s -- -y && \ + wget https://github.com/telatin/seqfu2/archive/refs/tags/v${SEQFU_VER}.tar.gz && \ + tar -xzf v${SEQFU_VER}.tar.gz && \ + rm -r v${SEQFU_VER}.tar.gz && \ + cd seqfu2-${SEQFU_VER} && \ + # make 2>&1 | tee /tmp/make_output.log && \ + make && \ + # Run tests and allow build to continue even if some tests fail + make test VERBOSE=1 || (echo "Tests failed, but continuing build"; exit 0) + + +# Copy the built binary to a location in the PATH +RUN cp /root/seqfu2-${SEQFU_VER}/bin/seqfu /usr/local/bin/seqfu + +# Final image +FROM ubuntu:focal AS app +ARG SEQFU_VER + +# Copy the necessary files from the builder +COPY --from=builder /usr/local/bin/seqfu /usr/local/bin/seqfu +COPY --from=builder /root/seqfu2-${SEQFU_VER}/data/tests /root/seqfu2-${SEQFU_VER}/data/tests + +RUN apt-get update && apt-get install -y --no-install-recommends \ + curl \ + wget \ + && rm -rf /var/lib/apt/lists/* + +# Setting working directory +RUN mkdir /data +WORKDIR /data + +RUN seqfu --version &&\ + seqfu --help + + +# ## Test ## +# FROM app as test + +# RUN apt-get update && apt-get install -y \ +# python3 \ +# wget + +# RUN mkdir ../tests/ +# COPY tests/ ../tests/ + + +# RUN python3 -m unittest discover -v -s ../tests \ No newline at end of file diff --git a/seqfu/1.20.3/README.md b/seqfu/1.20.3/README.md new file mode 100644 index 000000000..024720839 --- /dev/null +++ b/seqfu/1.20.3/README.md @@ -0,0 +1,46 @@ +# SeqFu + +Main tool: [SeqFu](https://sourceforge.net/projects/rdp-classifier/) + +Code repository: https://github.com/telatin/seqfu2 + +Basic information on how to use this tool: +- executable: | +``` + · count [cnt] : count FASTA/FASTQ reads, pair-end aware + · deinterleave [dei] : deinterleave FASTQ + · derep [der] : feature-rich dereplication of FASTA/FASTQ files + · interleave [ilv] : interleave FASTQ pair ends + · lanes [mrl] : merge Illumina lanes + · list [lst] : print sequences from a list of names + · metadata [met] : print a table of FASTQ reads (mapping files) + · sort [srt] : sort sequences by size (uniques) + · stats [st] : statistics on sequence lengths + + · cat : concatenate FASTA/FASTQ files + · grep : select sequences with patterns + · head : print first sequences + · rc : reverse complement strings or files + · tab : tabulate reads to TSV (and viceversa) + · tail : view last sequences + · view : view sequences with colored quality and oligo matches +``` + +- help: seqfu --help +- version: seqfu --version +- description: | +> A general-purpose program to manipulate and parse information from FASTA/FASTQ files, supporting gzipped input files. + + +Full documentation: https://telatin.github.io/seqfu2/ + + +# Testing SeqFU analysis +``` +seqfu check \ + --deep \ + --verbose \ + /root/seqfu2-1.20.3/data/tests/sample1_R1.fq \ + /root/seqfu2-1.20.3/data/tests/sample1_R2.fq +``` + From 91f036648a49a5d4b8ded7e029cf73fd4d6b13e2 Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 11 Sep 2024 13:34:10 -0400 Subject: [PATCH 03/92] editing seqfu readme --- seqfu/1.20.3/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/seqfu/1.20.3/README.md b/seqfu/1.20.3/README.md index 024720839..d399605da 100644 --- a/seqfu/1.20.3/README.md +++ b/seqfu/1.20.3/README.md @@ -26,8 +26,8 @@ Basic information on how to use this tool: · view : view sequences with colored quality and oligo matches ``` -- help: seqfu --help -- version: seqfu --version +- help: `seqfu --help` +- version: `seqfu --version` - description: | > A general-purpose program to manipulate and parse information from FASTA/FASTQ files, supporting gzipped input files. From fdf1a331be8aab6fdb22bc4270dc80358b7bcc39 Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 11 Sep 2024 14:09:25 -0400 Subject: [PATCH 04/92] updated seqfu readme --- seqfu/1.20.3/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/seqfu/1.20.3/README.md b/seqfu/1.20.3/README.md index d399605da..98d5794f9 100644 --- a/seqfu/1.20.3/README.md +++ b/seqfu/1.20.3/README.md @@ -1,6 +1,6 @@ # SeqFu -Main tool: [SeqFu](https://sourceforge.net/projects/rdp-classifier/) +Main tool: [SeqFu](https://github.com/telatin/seqfu2) Code repository: https://github.com/telatin/seqfu2 From d0f59ae99d87b49efb8545a1238a9c8cbcd07e52 Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 11 Sep 2024 14:19:10 -0400 Subject: [PATCH 05/92] removed extra 1.20.3 seqfu dir in wrong spot --- seqfu/1.20.3/Dockerfile | 78 ++++++++++++++++------------------------- 1 file changed, 31 insertions(+), 47 deletions(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index a22a46dec..c1f025a45 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -1,25 +1,24 @@ # Set global variables ARG SEQFU_VER="1.20.3" -# Build Dockerfile +# Stage 1: Build Dockerfile FROM ubuntu:focal AS builder ARG SEQFU_VER -LABEL base.image="ubuntu:focal" -LABEL dockerfile.version="1" -LABEL software="SeqFu" -LABEL software.version=${SEQFU_VER} -LABEL description="A general-purpose program to manipulate and parse information from FASTA/FASTQ files, supporting gzipped input files." -LABEL website="https://github.com/telatin/seqfu2" -LABEL license.url="https://github.com/telatin/seqfu2?tab=GPL-3.0-1-ov-file#readme" -LABEL maintainer="Taylor K. Paisie" -LABEL maintainer.email='ltj8@cdc.gov' - -# Set non-interactive frontend -ENV DEBIAN_FRONTEND=noninteractive - -# Set PATH globally to include Nimble binaries -ENV PATH="/root/.nimble/bin:${PATH}" +# Metadata +LABEL base.image="ubuntu:focal" \ + dockerfile.version="1" \ + software="SeqFu" \ + software.version="${SEQFU_VER}" \ + description="A general-purpose program to manipulate and parse information from FASTA/FASTQ files, supporting gzipped input files." \ + website="https://github.com/telatin/seqfu2" \ + license.url="https://github.com/telatin/seqfu2?tab=GPL-3.0-1-ov-file#readme" \ + maintainer="Taylor K. Paisie" \ + maintainer.email="ltj8@cdc.gov" + +# Set non-interactive frontend and update PATH +ENV DEBIAN_FRONTEND=noninteractive \ + PATH="/root/.nimble/bin:${PATH}" # Install required dependencies RUN apt-get update && apt-get install -y --no-install-recommends \ @@ -31,57 +30,42 @@ RUN apt-get update && apt-get install -y --no-install-recommends \ python3 \ python3-pip \ git \ - ca-certificates \ - && rm -rf /var/lib/apt/lists/* + ca-certificates && \ + rm -rf /var/lib/apt/lists/* -# Set the working directory to /root +# Set the working directory WORKDIR /root -# Run commands in non-interactive mode +# Install Nim and SeqFu RUN curl https://nim-lang.org/choosenim/init.sh -sSf | sh -s -- -y && \ wget https://github.com/telatin/seqfu2/archive/refs/tags/v${SEQFU_VER}.tar.gz && \ tar -xzf v${SEQFU_VER}.tar.gz && \ - rm -r v${SEQFU_VER}.tar.gz && \ + rm v${SEQFU_VER}.tar.gz && \ cd seqfu2-${SEQFU_VER} && \ - # make 2>&1 | tee /tmp/make_output.log && \ make && \ - # Run tests and allow build to continue even if some tests fail make test VERBOSE=1 || (echo "Tests failed, but continuing build"; exit 0) - # Copy the built binary to a location in the PATH -RUN cp /root/seqfu2-${SEQFU_VER}/bin/seqfu /usr/local/bin/seqfu +RUN ls -l /root/seqfu2-${SEQFU_VER}/bin && \ + cp -R /root/seqfu2-${SEQFU_VER}/bin/* /usr/local/bin/ && \ + chmod +x /usr/local/bin/seqfu -# Final image +# Stage 2: Create the final image FROM ubuntu:focal AS app ARG SEQFU_VER # Copy the necessary files from the builder -COPY --from=builder /usr/local/bin/seqfu /usr/local/bin/seqfu +COPY --from=builder /usr/local/bin /usr/local/bin COPY --from=builder /root/seqfu2-${SEQFU_VER}/data/tests /root/seqfu2-${SEQFU_VER}/data/tests +# Install minimal runtime dependencies RUN apt-get update && apt-get install -y --no-install-recommends \ curl \ - wget \ - && rm -rf /var/lib/apt/lists/* + wget && \ + rm -rf /var/lib/apt/lists/* -# Setting working directory -RUN mkdir /data +# Set working directory WORKDIR /data -RUN seqfu --version &&\ - seqfu --help - - -# ## Test ## -# FROM app as test - -# RUN apt-get update && apt-get install -y \ -# python3 \ -# wget - -# RUN mkdir ../tests/ -# COPY tests/ ../tests/ - - -# RUN python3 -m unittest discover -v -s ../tests \ No newline at end of file +# Verify installation +RUN ls -l /usr/local/bin && seqfu --version && seqfu --help \ No newline at end of file From 1f8ce15b3788e859f1fcb7b2b244dc242a3a3900 Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 11 Sep 2024 14:26:20 -0400 Subject: [PATCH 06/92] restored files for seqfu --- seqfu/1.20.3/Dockerfile | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index c1f025a45..43e93efb0 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -68,4 +68,13 @@ RUN apt-get update && apt-get install -y --no-install-recommends \ WORKDIR /data # Verify installation -RUN ls -l /usr/local/bin && seqfu --version && seqfu --help \ No newline at end of file +RUN ls -l /usr/local/bin && seqfu --version && seqfu --help + +# Uncomment for testing +# FROM app as test +# RUN apt-get update && apt-get install -y python3 wget +# RUN mkdir ../tests/ +# COPY tests/ ../tests/ +# RUN python3 -m unittest discover -v -s ../tests + +# tpaisie/seqfu@sha256:e2d3e2f7229cf64c20634701dca5206619191551b91f2f306bdd326e623864c8 From 9ea00af9ef58e4e3943efd3a35d1fd48b061acbc Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 11 Sep 2024 14:29:16 -0400 Subject: [PATCH 07/92] cleaning up dockerfile --- seqfu/1.20.3/Dockerfile | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index 43e93efb0..2dc175901 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -68,13 +68,4 @@ RUN apt-get update && apt-get install -y --no-install-recommends \ WORKDIR /data # Verify installation -RUN ls -l /usr/local/bin && seqfu --version && seqfu --help - -# Uncomment for testing -# FROM app as test -# RUN apt-get update && apt-get install -y python3 wget -# RUN mkdir ../tests/ -# COPY tests/ ../tests/ -# RUN python3 -m unittest discover -v -s ../tests - -# tpaisie/seqfu@sha256:e2d3e2f7229cf64c20634701dca5206619191551b91f2f306bdd326e623864c8 +RUN seqfu --version && seqfu --help From d06fe74a6e4c876fb32f6196cbbd4563c0b6d300 Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 11 Sep 2024 14:40:54 -0400 Subject: [PATCH 08/92] updated readme and program licenses with seqfu --- Program_Licenses.md | 1 + README.md | 2 ++ 2 files changed, 3 insertions(+) diff --git a/Program_Licenses.md b/Program_Licenses.md index fd5fbcec7..559ffbbc4 100644 --- a/Program_Licenses.md +++ b/Program_Licenses.md @@ -133,6 +133,7 @@ The licenses of the open-source software that is contained in these Docker image | Roary | GNU GPLv3 | https://github.com/sanger-pathogens/Roary/blob/master/GPL-LICENSE | | SalmID| MIT | https://github.com/hcdenbakker/SalmID/blob/master/LICENSE | | Samtools | GNU GPLv3 | https://github.com/samtools/samtools/blob/develop/LICENSE | +| SeqFu | GNU GPLv3 | https://github.com/telatin/seqfu2 | | SeqKit | MIT | https://github.com/shenwei356/seqkit/blob/master/LICENSE | SeqSero | GNU GPLv2 | https://github.com/denglab/SeqSero/blob/master/LICENSE | | SeqSero2 | GNU GPLv2 | https://github.com/denglab/SeqSero2/blob/master/LICENSE | diff --git a/README.md b/README.md index 01e1407e8..bb22190e0 100644 --- a/README.md +++ b/README.md @@ -238,6 +238,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Roary](https://hub.docker.com/r/staphb/roary/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/roary)](https://hub.docker.com/r/staphb/roary) |
  • 3.12.0
  • 3.13.0
| https://github.com/sanger-pathogens/Roary | | [SalmID](https://hub.docker.com/r/staphb/salmid)
[![docker pulls](https://badgen.net/docker/pulls/staphb/salmid)](https://hub.docker.com/r/staphb/salmid) |
  • 0.1.23
| https://github.com/hcdenbakker/SalmID | | [Samtools](https://hub.docker.com/r/staphb/samtools)
[![docker pulls](https://badgen.net/docker/pulls/staphb/samtools)](https://hub.docker.com/r/staphb/samtools) |
  • [1.9](./samtools/1.9/)
  • [1.10](./samtools/1.10/)
  • [1.11](./samtools/1.11/)
  • [1.12](./samtools/1.12/)
  • [1.13](./samtools/1.13/)
  • [1.14](./samtools/1.14/)
  • [1.15](./samtools/1.15/)
  • [1.16](./samtools/1.16/)
  • [1.16.1](./samtools/1.16.1/)
  • [1.17](./samtools/1.17/)
  • [1.17-2023-06](./samtools/1.17-2023-06/)
  • [1.18](./samtools/1.18/)
  • [1.19](./samtools/1.19/)
| https://github.com/samtools/samtools | +| [SeqFu](https://hub.docker.com/r/staphb/SeqFu)
[![docker pulls](https://badgen.net/docker/pulls/staphb/seqfu)](https://hub.docker.com/r/staphb/seqfu) | | [SeqKit](https://hub.docker.com/r/staphb/SeqKit)
[![docker pulls](https://badgen.net/docker/pulls/staphb/seqkit)](https://hub.docker.com/r/staphb/seqkit) |
  • [2.3.1](./seqkit/2.3.1/)
  • [2.6.1](./seqkit/2.6.1/)
  • [2.7.0](./seqkit/2.7.0/)
| https://github.com/shenwei356/seqkit | | [SeqSero](https://hub.docker.com/r/staphb/seqsero/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/seqsero)](https://hub.docker.com/r/staphb/seqsero) |
  • 1.0.1
| https://github.com/denglab/SeqSero | | [SeqSero2](https://hub.docker.com/r/staphb/seqsero2/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/seqsero2)](https://hub.docker.com/r/staphb/seqsero2) |
  • 0.1.0
  • 1.0.0
  • 1.0.2
  • 1.1.0
  • 1.1.1
  • 1.2.1
| https://github.com/denglab/SeqSero2/ | @@ -344,3 +345,4 @@ Each Dockerfile lists the author(s)/maintainer(s) as a metadata `LABEL`, but the * [@evagunawan](https://github.com/evagunawan) * [@nawrockie](https://github.com/nawrockie) * [@stephenturner](https://github.com/stephenturner) + * [@taylorpaisie](https://github.com/taylorpaisie) From ecbc8b82acda4ca6b5c978ef2efa78772233b5a4 Mon Sep 17 00:00:00 2001 From: Young Date: Thu, 12 Sep 2024 12:54:46 -0600 Subject: [PATCH 09/92] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 57b11813b..75b9cf911 100644 --- a/README.md +++ b/README.md @@ -257,7 +257,7 @@ To learn more about the docker pull rate limits and the open source software pro | [SalmID](https://hub.docker.com/r/staphb/salmid)
[![docker pulls](https://badgen.net/docker/pulls/staphb/salmid)](https://hub.docker.com/r/staphb/salmid) |
  • 0.1.23
| https://github.com/hcdenbakker/SalmID | | [samclip](https://hub.docker.com/r/staphb/samclip)
[![docker pulls](https://badgen.net/docker/pulls/staphb/samclip)](https://hub.docker.com/r/staphb/samclip) |
  • [0.4.0](./samclip/0.4.0/)
| https://github.com/tseemann/samclip | | [Samtools](https://hub.docker.com/r/staphb/samtools)
[![docker pulls](https://badgen.net/docker/pulls/staphb/samtools)](https://hub.docker.com/r/staphb/samtools) |
  • [1.9](./samtools/1.9/)
  • [1.10](./samtools/1.10/)
  • [1.11](./samtools/1.11/)
  • [1.12](./samtools/1.12/)
  • [1.13](./samtools/1.13/)
  • [1.14](./samtools/1.14/)
  • [1.15](./samtools/1.15/)
  • [1.16](./samtools/1.16/)
  • [1.16.1](./samtools/1.16.1/)
  • [1.17](./samtools/1.17/)
  • [1.17-2023-06](./samtools/1.17-2023-06/)
  • [1.18](./samtools/1.18/)
  • [1.19](./samtools/1.19/)
  • [1.20](./samtools/1.20/)
  • [1.20.c](./samtools/1.20.c/)
| https://github.com/samtools/samtools | -| [SeqFu](https://hub.docker.com/r/staphb/SeqFu)
[![docker pulls](https://badgen.net/docker/pulls/staphb/seqfu)](https://hub.docker.com/r/staphb/seqfu) | +| [SeqFu](https://hub.docker.com/r/staphb/SeqFu)
[![docker pulls](https://badgen.net/docker/pulls/staphb/seqfu)](https://hub.docker.com/r/staphb/seqfu) |
  • [1.20.3](./seqfu/1.20.3/)
| https://github.com/telatin/seqfu2 | | [SeqKit](https://hub.docker.com/r/staphb/SeqKit)
[![docker pulls](https://badgen.net/docker/pulls/staphb/seqkit)](https://hub.docker.com/r/staphb/seqkit) |
  • [2.3.1](./seqkit/2.3.1/)
  • [2.6.1](./seqkit/2.6.1/)
  • [2.7.0](./seqkit/2.7.0/)
  • [2.8.0](./seqkit/2.8.0/)
  • [2.8.1](./seqkit/2.8.1/)
  • [2.8.2](./seqkit/2.8.2/)
| https://github.com/shenwei356/seqkit | | [SeqSero](https://hub.docker.com/r/staphb/seqsero/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/seqsero)](https://hub.docker.com/r/staphb/seqsero) |
  • 1.0.1
| https://github.com/denglab/SeqSero | | [SeqSero2](https://hub.docker.com/r/staphb/seqsero2/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/seqsero2)](https://hub.docker.com/r/staphb/seqsero2) |
  • [0.1.0](./seqsero2/0.1.0/)
  • [1.0.0](./seqsero2/1.0.0/)
  • [1.0.2](./seqsero2/1.0.2/)
  • [1.1.0](./seqsero2/1.1.0/)
  • [1.1.1](./seqsero2/1.1.1/)
  • [1.2.1](./seqsero2/1.2.1/)
  • [1.3.1](./seqsero2/1.3.1/)
| https://github.com/denglab/SeqSero2/ | From d42f0e84fffa2f3c7a2d5d3d4e70b1370524a0d4 Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Sat, 14 Sep 2024 14:20:09 +0200 Subject: [PATCH 10/92] removed main.yml and edited dockerfile to removing test data from seqfu container --- .github/workflows/main.yml | 137 ------------------------------------- seqfu/1.20.3/Dockerfile | 6 +- 2 files changed, 4 insertions(+), 139 deletions(-) delete mode 100644 .github/workflows/main.yml diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml deleted file mode 100644 index 09a300dee..000000000 --- a/.github/workflows/main.yml +++ /dev/null @@ -1,137 +0,0 @@ - -##### ------------------------------------------------------------------------------------------------ ##### -##### This caller workflow tests, builds, and pushes the image to Docker Hub and Quay using the most ##### -##### recent version of Freyja and downloading the most recent variant information. ##### -##### It takes no manual input. ##### -##### ------------------------------------------------------------------------------------------------ ##### - -name: Update Freyja - -on: - workflow_dispatch: - schedule: - - cron: '30 7 * * *' - -run-name: Updating Freyja - -jobs: - update: - runs-on: ubuntu-latest - steps: - -# Keeping here in case we want to use it to keep Freyja's version up-to-date as well -# - name: Get latest release -# uses: rez0n/actions-github-release@main -# id: latest_release -# with: -# token: ${{ secrets.GITHUB_TOKEN }} -# repository: andersen-lab/Freyja -# type: "stable" -# - name: Remove V -# id: strip -# run: | -# version=$(echo "${{ steps.latest_release.outputs.release }}" | sed 's/V//g' | sed 's/v//g' ) -# echo "The version is $version" -# echo "version=$version" >> $GITHUB_OUTPUT - - - name: pull repo - uses: actions/checkout@v3 - -# Keeping here in case we want to figure out why this doesn't work -# - name: get latest version of freyja in docker-builds repo -# id: latest_version -# run: | -# file=$(git log -1 --name-only --format=%cd --date=iso freyja/*/Dockerfile | grep Dockerfile | head -n 1 ) -# echo "the latest file is $file" -# echo "file=$file" >> $GITHUB_OUTPUT -# -# version=$(echo $file | cut -f 2 -d "/" | cut -f 1 -d "_") -# echo "the latest version is $version" -# echo "version=$version" >> $GITHUB_OUTPUT - - - name: set freyja version - id: latest_version - run: | - version=1.4.8 - echo "version=$version" >> $GITHUB_OUTPUT - - file=freyja/$version/Dockerfile - ls $file - echo "file=$file" >> $GITHUB_OUTPUT - - name: set up docker buildx - id: buildx - uses: docker/setup-buildx-action@v2 - - - name: cache docker layers - uses: actions/cache@v3 - with: - path: /tmp/.buildx-cache-freyja - key: ${{ runner.os }}-buildx-freyja-${{ github.sha }} - restore-keys: ${{ runner.os }}-buildx-freyja - - - name: build to test - id: docker_build_to_test - uses: docker/build-push-action@v3 - with: - file: ${{ steps.latest_version.outputs.file }} - target: test - load: true - push: false - cache-from: type=local,src=/tmp/.buildx-cache-freyja - cache-to: type=local,mode=max,dest=/tmp/.buildx-cache-freyja-new - tags: freyja:update - - - name: get freyja database version - id: db_version - run: | - docker run freyja:update freyja demix --version - version=$(docker run freyja:update freyja demix --version | grep . | grep -v Barcode | head -n 1) - echo "the latest version is $version" - echo "version=$version" >> $GITHUB_OUTPUT - - name: Get current date - id: date - run: | - date=$(date '+%Y-%m-%d') - echo "the date is $date" - echo "date=$date" >> $GITHUB_OUTPUT - - # - name: Login to DockerHub - # uses: docker/login-action@v2 - # with: - # username: ${{ secrets.DOCKER_HUB_USERNAME }} - # password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }} - - - name: Login to Quay - uses: docker/login-action@v2 - with: - registry: quay.io - username: ${{ secrets.QUAY_USERNAME }} - password: ${{ secrets.QUAY_ROBOT_TOKEN }} - - - name: Build and push user-defined tag to DockerHub - id: docker_build_user_defined_tag - uses: docker/build-push-action@v3 - with: - file: ${{ steps.latest_version.outputs.file }} - target: app - push: true - cache-from: type=local,src=/tmp/.buildx-cache-freyja - cache-to: type=local,mode=max,dest=/tmp/.buildx-cache-freyja-new # mode=max means export layers from all stage to cache - tags: staphb/freyja:${{ steps.latest_version.outputs.version }}-${{ steps.db_version.outputs.version }}-${{ steps.date.outputs.date }} - - - name: Build and push to Quay - id: build - uses: docker/build-push-action@v3 - with: - file: ${{ steps.latest_version.outputs.file }} - target: app - push: true - cache-from: type=local,src=/tmp/.buildx-cache-freyja - cache-to: type=local,mode=max,dest=/tmp/.buildx-cache-freyja-new # mode=max means export - tags: quay.io/staphb/freyja:${{ steps.latest_version.outputs.version }}-${{ steps.db_version.outputs.version }}-${{ steps.date.outputs.date }} - - - name: Move cache # apparently prevents the cache from growing in size forever - run: | - rm -rf /tmp/.buildx-cache-freyja - mv /tmp/.buildx-cache-freyja-new /tmp/.buildx-cache-freyja - - name: Image digest diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index 2dc175901..85b52540d 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -56,7 +56,7 @@ ARG SEQFU_VER # Copy the necessary files from the builder COPY --from=builder /usr/local/bin /usr/local/bin -COPY --from=builder /root/seqfu2-${SEQFU_VER}/data/tests /root/seqfu2-${SEQFU_VER}/data/tests +# COPY --from=builder /root/seqfu2-${SEQFU_VER}/data/tests /root/seqfu2-${SEQFU_VER}/data/tests # Install minimal runtime dependencies RUN apt-get update && apt-get install -y --no-install-recommends \ @@ -68,4 +68,6 @@ RUN apt-get update && apt-get install -y --no-install-recommends \ WORKDIR /data # Verify installation -RUN seqfu --version && seqfu --help +RUN ls -l /usr/local/bin && \ +seqfu --version && seqfu --help + From e39c24290fc9249fd11b74be0bb6d6d3cb97ae5d Mon Sep 17 00:00:00 2001 From: Kincekara Date: Fri, 20 Sep 2024 17:05:16 +0000 Subject: [PATCH 11/92] adds verkko v2.2 --- README.md | 2 +- verkko/2.2/Dockerfile | 48 +++++++++++++++++++++++++++++++++++++++++++ verkko/2.2/README.md | 21 +++++++++++++++++++ 3 files changed, 70 insertions(+), 1 deletion(-) create mode 100644 verkko/2.2/Dockerfile create mode 100644 verkko/2.2/README.md diff --git a/README.md b/README.md index ecf9c9954..67b64283d 100644 --- a/README.md +++ b/README.md @@ -294,7 +294,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Trycycler](https://hub.docker.com/r/staphb/trycycler/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/trycycler)](https://hub.docker.com/r/staphb/trycycler) |
  • [0.3.1](./trycycler/0.3.1/)
  • [0.3.2](./trycycler/0.3.2/)
  • [0.3.3](./trycycler/0.3.3/)
  • [0.5.0](./trycycler/0.5.0/)
  • [0.5.3](./trycycler/0.5.3/)
  • [0.5.4](./trycycler/0.5.4/)
  • [0.5.5](./trycycler/0.5.5/)
| https://github.com/rrwick/Trycycler | | [Unicycler](https://hub.docker.com/r/staphb/unicycler/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/unicycler)](https://hub.docker.com/r/staphb/unicycler) |
  • 0.4.7
  • 0.4.8
  • 0.4.9
  • 0.5.0
| https://github.com/rrwick/Unicycler | | [VADR](https://hub.docker.com/r/staphb/vadr/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/vadr)](https://hub.docker.com/r/staphb/vadr) |
  • 1.1
  • 1.1.2
  • 1.1.3
  • 1.2
  • 1.2.1
  • 1.3 & SARS-CoV-2 models 1.3-1
  • 1.3 & SARS-CoV-2 models 1.3-2
  • 1.4 & SARS-CoV-2 models 1.3-2
  • 1.4.1 & SARS-CoV-2 models 1.3-2
  • [1.4.2 & SARS-CoV-2 models 1.3-2, MPXV models 1.4.2-1](vadr/1.4.2/)
  • [1.5 & SARS-CoV-2 models 1.3-2, MPXV models 1.4.2-1](vadr/1.5/)
  • [1.5.1 & SARS-CoV-2 models 1.3-2, MPXV models 1.4.2-1, RSV models 1.5-2](vadr/1.5.1/)
  • [1.6.3 & SARS-CoV-2 models 1.3-2, MPXV models 1.4.2-1, RSV models 1.5-2, Influenza v1.6.3-1](vadr/1.6.3/)
  • [1.6.3 & SARS-CoV-2 models 1.3-2, MPXV models 1.4.2-1, RSV models 1.5-2, Influenza v1.6.3-1, HAV v1.0.0](vadr/1.6.3-hav/)
  • [1.6.3 & SARS-CoV-2 models 1.3-2, MPXV models 1.4.2-1, RSV models 1.5-2, Influenza v1.6.3-2, HAV v1.0.0](vadr/1.6.3-hav-flu2/)
| https://github.com/nawrockie/vadr (archived, now redirects to ncbi/vadr)
https://github.com/ncbi/vadr | -| [Verkko](https://hub.docker.com/r/staphb/verkko/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/verkko)](https://hub.docker.com/r/staphb/verkko) |
  • [2.0](./verkko/2.0/)
  • [2.1](./verkko/2.1/)
| https://github.com/marbl/verkko | +| [Verkko](https://hub.docker.com/r/staphb/verkko/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/verkko)](https://hub.docker.com/r/staphb/verkko) |
  • [2.0](./verkko/2.0/)
  • [2.1](./verkko/2.1/)
  • [2.1](./verkko/2.2/)
| https://github.com/marbl/verkko | | [VIBRANT](https://hub.docker.com/r/staphb/vibrant/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/vibrant)](https://hub.docker.com/r/staphb/vibrant) |
  • 1.2.1
| https://github.com/AnantharamanLab/VIBRANT | | [VIGOR4](https://hub.docker.com/r/staphb/vigor4/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/vigor4)](https://hub.docker.com/r/staphb/vigor4) |
  • [4.1.20190131](./vigor4/4.1.20190131/)
  • [4.1.20200702](./vigor4/4.1.20200702/)
| https://github.com/JCVenterInstitute/VIGOR4 | | [Viridian](https://hub.docker.com/r/staphb/viridian/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/viridian)](https://hub.docker.com/r/staphb/viridian) |
  • [1.2.2](./viridian/1.2.2/)
| https://github.com/iqbal-lab-org/viridian | diff --git a/verkko/2.2/Dockerfile b/verkko/2.2/Dockerfile new file mode 100644 index 000000000..280bf0910 --- /dev/null +++ b/verkko/2.2/Dockerfile @@ -0,0 +1,48 @@ +FROM mambaorg/micromamba:1.5.9 AS app + +ARG VERKKO_VER="2.2" + +USER root + +WORKDIR / + +LABEL base.image="mambaorg/micromamba:1.5.9" +LABEL dockerfile.version="1" +LABEL software="Verkko" +LABEL software.version="${VERKKO_VER}" +LABEL description="Verkko is a hybrid genome assembly pipeline developed for telomere-to-telomere assembly of PacBio HiFi or Oxford Nanopore Duplex and Oxford Nanopore simplex reads." +LABEL website="https://github.com/marbl/verkko" +LABEL license="https://github.com/marbl/verkko/blob/master/README.licenses" +LABEL maintainer="Kutluhan Incekara" +LABEL maintainer.email="kutluhan.incekara@ct.gov" + +RUN apt-get update && apt-get install --no-install-recommends -y \ + procps &&\ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +RUN micromamba install --name base -c conda-forge -c bioconda verkko=${VERKKO_VER} && \ + micromamba clean -afy + +ENV PATH="/opt/conda/bin/:${PATH}" \ + LC_ALL=C.UTF-8 + +CMD [ "verkko", "--help" ] + +WORKDIR /data + +## Test ## +FROM app AS test + +RUN verkko --help + +RUN apt-get update && apt-get install --no-install-recommends -y curl + +# test data +RUN curl -L https://obj.umiacs.umd.edu/sergek/shared/ecoli_hifi_subset24x.fastq.gz -o hifi.fastq.gz &&\ + curl -L https://obj.umiacs.umd.edu/sergek/shared/ecoli_ont_subset50x.fastq.gz -o ont.fastq.gz + +# verkko test run +RUN verkko -d asm --hifi ./hifi.fastq.gz --nano ./ont.fastq.gz &&\ + head asm/assembly.hifi-coverage.csv &&\ + head -c 1000 asm/assembly.fasta + diff --git a/verkko/2.2/README.md b/verkko/2.2/README.md new file mode 100644 index 000000000..ee3b2e499 --- /dev/null +++ b/verkko/2.2/README.md @@ -0,0 +1,21 @@ +# Verkko container + +Main tool: [verkko](https://github.com/marbl/verkko) + +Code repository: https://github.com/marbl/verkko + +Basic information on how to use this tool: +- executable: verkko +- help: --help +- version: --version +- description: Verkko is a hybrid genome assembly pipeline developed for telomere-to-telomere assembly of PacBio HiFi or Oxford Nanopore Duplex and Oxford Nanopore simplex reads. + +Full documentation: https://github.com/marbl/verkko + +## Example Usage + +```bash +verkko -d --hifi [--nano ] +``` + + \ No newline at end of file From 4632c4130d47ab340aca650466f4c8c315a9bac7 Mon Sep 17 00:00:00 2001 From: Kincekara Date: Fri, 20 Sep 2024 17:11:32 +0000 Subject: [PATCH 12/92] fix version --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 67b64283d..d58578551 100644 --- a/README.md +++ b/README.md @@ -294,7 +294,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Trycycler](https://hub.docker.com/r/staphb/trycycler/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/trycycler)](https://hub.docker.com/r/staphb/trycycler) |
  • [0.3.1](./trycycler/0.3.1/)
  • [0.3.2](./trycycler/0.3.2/)
  • [0.3.3](./trycycler/0.3.3/)
  • [0.5.0](./trycycler/0.5.0/)
  • [0.5.3](./trycycler/0.5.3/)
  • [0.5.4](./trycycler/0.5.4/)
  • [0.5.5](./trycycler/0.5.5/)
| https://github.com/rrwick/Trycycler | | [Unicycler](https://hub.docker.com/r/staphb/unicycler/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/unicycler)](https://hub.docker.com/r/staphb/unicycler) |
  • 0.4.7
  • 0.4.8
  • 0.4.9
  • 0.5.0
| https://github.com/rrwick/Unicycler | | [VADR](https://hub.docker.com/r/staphb/vadr/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/vadr)](https://hub.docker.com/r/staphb/vadr) |
  • 1.1
  • 1.1.2
  • 1.1.3
  • 1.2
  • 1.2.1
  • 1.3 & SARS-CoV-2 models 1.3-1
  • 1.3 & SARS-CoV-2 models 1.3-2
  • 1.4 & SARS-CoV-2 models 1.3-2
  • 1.4.1 & SARS-CoV-2 models 1.3-2
  • [1.4.2 & SARS-CoV-2 models 1.3-2, MPXV models 1.4.2-1](vadr/1.4.2/)
  • [1.5 & SARS-CoV-2 models 1.3-2, MPXV models 1.4.2-1](vadr/1.5/)
  • [1.5.1 & SARS-CoV-2 models 1.3-2, MPXV models 1.4.2-1, RSV models 1.5-2](vadr/1.5.1/)
  • [1.6.3 & SARS-CoV-2 models 1.3-2, MPXV models 1.4.2-1, RSV models 1.5-2, Influenza v1.6.3-1](vadr/1.6.3/)
  • [1.6.3 & SARS-CoV-2 models 1.3-2, MPXV models 1.4.2-1, RSV models 1.5-2, Influenza v1.6.3-1, HAV v1.0.0](vadr/1.6.3-hav/)
  • [1.6.3 & SARS-CoV-2 models 1.3-2, MPXV models 1.4.2-1, RSV models 1.5-2, Influenza v1.6.3-2, HAV v1.0.0](vadr/1.6.3-hav-flu2/)
| https://github.com/nawrockie/vadr (archived, now redirects to ncbi/vadr)
https://github.com/ncbi/vadr | -| [Verkko](https://hub.docker.com/r/staphb/verkko/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/verkko)](https://hub.docker.com/r/staphb/verkko) |
  • [2.0](./verkko/2.0/)
  • [2.1](./verkko/2.1/)
  • [2.1](./verkko/2.2/)
| https://github.com/marbl/verkko | +| [Verkko](https://hub.docker.com/r/staphb/verkko/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/verkko)](https://hub.docker.com/r/staphb/verkko) |
  • [2.0](./verkko/2.0/)
  • [2.1](./verkko/2.1/)
  • [2.2](./verkko/2.2/)
| https://github.com/marbl/verkko | | [VIBRANT](https://hub.docker.com/r/staphb/vibrant/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/vibrant)](https://hub.docker.com/r/staphb/vibrant) |
  • 1.2.1
| https://github.com/AnantharamanLab/VIBRANT | | [VIGOR4](https://hub.docker.com/r/staphb/vigor4/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/vigor4)](https://hub.docker.com/r/staphb/vigor4) |
  • [4.1.20190131](./vigor4/4.1.20190131/)
  • [4.1.20200702](./vigor4/4.1.20200702/)
| https://github.com/JCVenterInstitute/VIGOR4 | | [Viridian](https://hub.docker.com/r/staphb/viridian/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/viridian)](https://hub.docker.com/r/staphb/viridian) |
  • [1.2.2](./viridian/1.2.2/)
| https://github.com/iqbal-lab-org/viridian | From 0f8268fe9c004849ec2b331be6b9bf7c02f4bcdc Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Mon, 23 Sep 2024 17:33:37 +0000 Subject: [PATCH 13/92] adds dockerfile & readme for pdata 1.30 --- pangolin/4.3.1-pdata-1.30/Dockerfile | 217 +++++++++++++++++++++++++++ pangolin/4.3.1-pdata-1.30/README.md | 53 +++++++ 2 files changed, 270 insertions(+) create mode 100644 pangolin/4.3.1-pdata-1.30/Dockerfile create mode 100644 pangolin/4.3.1-pdata-1.30/README.md diff --git a/pangolin/4.3.1-pdata-1.30/Dockerfile b/pangolin/4.3.1-pdata-1.30/Dockerfile new file mode 100644 index 000000000..41078dd00 --- /dev/null +++ b/pangolin/4.3.1-pdata-1.30/Dockerfile @@ -0,0 +1,217 @@ +FROM mambaorg/micromamba:1.5.10 AS app + +# build and run as root users since micromamba image has 'mambauser' set as the $USER +USER root +# set workdir to default for building; set to /data at the end +WORKDIR / + +# ARG variables only persist during build time +# had to include the v for some of these due to GitHub tags. +# using pangolin-data github tag, NOT what is in the GH release title "v1.2.133" +ARG PANGOLIN_VER="v4.3.1" +ARG PANGOLIN_DATA_VER="v1.30" +ARG SCORPIO_VER="v0.3.19" +ARG CONSTELLATIONS_VER="v0.1.12" +ARG USHER_VER="0.6.3" + +# metadata labels +LABEL base.image="mambaorg/micromamba:1.5.10" +LABEL dockerfile.version="1" +LABEL software="pangolin" +LABEL software.version=${PANGOLIN_VER} +LABEL description="Conda environment for Pangolin. Pangolin: Software package for assigning SARS-CoV-2 genome sequences to global lineages." +LABEL website="https://github.com/cov-lineages/pangolin" +LABEL license="GNU General Public License v3.0" +LABEL license.url="https://github.com/cov-lineages/pangolin/blob/master/LICENSE.txt" +LABEL maintainer="Curtis Kapsak" +LABEL maintainer.email="kapsakcj@gmail.com" + +# install dependencies; cleanup apt garbage +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + git \ + procps \ + bsdmainutils && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# get the pangolin repo +RUN wget "https://github.com/cov-lineages/pangolin/archive/${PANGOLIN_VER}.tar.gz" && \ + tar -xf ${PANGOLIN_VER}.tar.gz && \ + rm -v ${PANGOLIN_VER}.tar.gz && \ + mv -v pangolin-* pangolin + +# set the environment; PATH is unnecessary here, but leaving anyways. It's reset later in dockerfile +ENV PATH="$PATH" \ + LC_ALL=C.UTF-8 + +# modify environment.yml to pin specific versions during install +# pin specific versions of usher, scorpio, pangolin-data, constellations, and pulp +# create the conda environment using modified environment.yml +RUN sed -i "s|usher.*|usher=${USHER_VER}|" /pangolin/environment.yml && \ + sed -i "s|scorpio.git|scorpio.git@${SCORPIO_VER}|" /pangolin/environment.yml && \ + sed -i "s|pangolin-data.git|pangolin-data.git@${PANGOLIN_DATA_VER}|" /pangolin/environment.yml && \ + sed -i "s|constellations.git|constellations.git@${CONSTELLATIONS_VER}|" /pangolin/environment.yml && \ + sed -i "12 a\ - pulp=2.7.0" /pangolin/environment.yml && \ + micromamba create -n pangolin -y -f /pangolin/environment.yml && \ + micromamba clean -a -y -f + +# so that mamba/conda env is active when running below commands +ENV ENV_NAME="pangolin" +ARG MAMBA_DOCKERFILE_ACTIVATE=1 + +WORKDIR /pangolin + +# run pip install step; download optional pre-computed assignment hashes for UShER (useful for running on large batches of samples) +# best to skip using the assigment-cache if running on one sample for speed +# print versions +RUN pip install . && \ + pangolin --add-assignment-cache && \ + mkdir /data && \ + pangolin --all-versions && \ + usher --version + +# final working directory in "app" layer is /data for passing data in/out of container +WORKDIR /data + +# hardcode pangolin executable into the PATH variable +ENV PATH="${PATH}:/opt/conda/envs/pangolin/bin/" XDG_CACHE_HOME=/tmp + +# default command is to pull up help options for pangolin; can be overridden of course +CMD ["pangolin", "-h"] + +# new base for testing +FROM app AS test + +# so that mamba/conda env is active when running below commands +ENV ENV_NAME="pangolin" +ARG MAMBA_DOCKERFILE_ACTIVATE=1 + +# test on test sequences supplied with Pangolin code +RUN pangolin /pangolin/pangolin/test/test_seqs.fasta -o /data/test_seqs-output-pusher && \ + column -t -s, /data/test_seqs-output-pusher/lineage_report.csv + +# test functionality of assignment-cache option +RUN pangolin --use-assignment-cache /pangolin/pangolin/test/test_seqs.fasta + +# download B.1.1.7 genome from Utah +ADD https://raw.githubusercontent.com/StaPH-B/docker-builds/master/tests/SARS-CoV-2/SRR13957123.consensus.fa /test-data/SRR13957123.consensus.fa + +# test on a B.1.1.7 genome +RUN pangolin /test-data/SRR13957123.consensus.fa -o /test-data/SRR13957123-pusher && \ + column -t -s, /test-data/SRR13957123-pusher/lineage_report.csv + + # install unzip for unzipping zip archive from NCBI +RUN apt-get update && apt-get install -y --no-install-recommends unzip + +# install ncbi datasets tool (pre-compiled binary); place in $PATH +RUN wget https://ftp.ncbi.nlm.nih.gov/pub/datasets/command-line/LATEST/linux-amd64/datasets && \ + chmod +x datasets && \ + mv -v datasets /usr/local/bin + +# download assembly for a BA.1 from Florida (https://www.ncbi.nlm.nih.gov/biosample?term=SAMN29506515 and https://www.ncbi.nlm.nih.gov/nuccore/ON924087) +# run pangolin in usher analysis mode +RUN datasets download virus genome accession ON924087.1 --filename ON924087.1.zip && \ + unzip ON924087.1.zip && rm ON924087.1.zip && \ + mv -v ncbi_dataset/data/genomic.fna ON924087.1.genomic.fna && \ + rm -vr ncbi_dataset/ README.md && \ + pangolin ON924087.1.genomic.fna -o ON924087.1-usher && \ + column -t -s, ON924087.1-usher/lineage_report.csv + +# test specific for new lineage, XBB.1.16, introduced in pangolin-data v1.19 +# using this assembly: https://www.ncbi.nlm.nih.gov/nuccore/2440446687 +# biosample here: https://www.ncbi.nlm.nih.gov/biosample?term=SAMN33060589 +# one of the sample included in initial pango-designation here: https://github.com/cov-lineages/pango-designation/issues/1723 +RUN datasets download virus genome accession OQ381818.1 --filename OQ381818.1.zip && \ + unzip -o OQ381818.1.zip && rm OQ381818.1.zip && \ + mv -v ncbi_dataset/data/genomic.fna OQ381818.1.genomic.fna && \ + rm -vr ncbi_dataset/ README.md && \ + pangolin OQ381818.1.genomic.fna -o OQ381818.1-usher && \ + column -t -s, OQ381818.1-usher/lineage_report.csv + +# testing another XBB.1.16, trying to test scorpio functionality. Want pangolin to NOT assign lineage based on pango hash match. +# this test runs as expected, uses scorpio to check for constellation of mutations, then assign using PUSHER placement +RUN datasets download virus genome accession OR177999.1 --filename OR177999.1.zip && \ +unzip -o OR177999.1.zip && rm OR177999.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna OR177999.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin OR177999.1.genomic.fna -o OR177999.1-usher && \ +column -t -s, OR177999.1-usher/lineage_report.csv + + ## test for BA.2.86 + # virus identified in MI: https://www.ncbi.nlm.nih.gov/nuccore/OR461132.1 +RUN datasets download virus genome accession OR461132.1 --filename OR461132.1.zip && \ +unzip -o OR461132.1.zip && rm OR461132.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna OR461132.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin OR461132.1.genomic.fna -o OR461132.1-usher && \ +column -t -s, OR461132.1-usher/lineage_report.csv + + ## test for JN.2 (BA.2.86 sublineage) JN.2 is an alias of B.1.1.529.2.86.1.2 + # NY CDC Quest sample: https://www.ncbi.nlm.nih.gov/nuccore/OR598183 +RUN datasets download virus genome accession OR598183.1 --filename OR598183.1.zip && \ +unzip -o OR598183.1.zip && rm OR598183.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna OR598183.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin OR598183.1.genomic.fna -o OR598183.1-usher && \ +column -t -s, OR598183.1-usher/lineage_report.csv + +## test for JQ.1 (BA.2.86.3 sublineage); JQ.1 is an alias of B.1.1.529.2.86.3.1 +# THANK YOU ERIN AND UPHL!! https://www.ncbi.nlm.nih.gov/nuccore/OR716684 +# this test is important due to the fact that this lineage was included in the UShER tree, despite being designated after the pangolin-designation 1.23 release +# it previously caused and error/bug in pangolin, but now is fixed +RUN datasets download virus genome accession OR716684.1 --filename OR716684.1.zip && \ +unzip -o OR716684.1.zip && rm OR716684.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna OR716684.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin OR716684.1.genomic.fna -o OR716684.1-usher && \ +column -t -s, OR716684.1-usher/lineage_report.csv + +## test for JN.1.22 (BA.2.86.x sublineage; full unaliased lineage is B.1.1.529.2.86.1.1.22) +# see here for commit where it was designated https://github.com/cov-lineages/pango-designation/commit/a90c8e31c154621ed86c985debfea09e17541cda +# Here's the genome on NCBI, which was used to designate JN.1.22 lineage +RUN datasets download virus genome accession PP189069.1 --filename PP189069.1.zip && \ +unzip -o PP189069.1.zip && rm PP189069.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna PP189069.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin PP189069.1.genomic.fna -o PP189069.1-usher && \ +column -t -s, PP189069.1-usher/lineage_report.csv + +## test for JN.1.48 (BA.2.86.x sublineage; full unaliased lineage is B.1.1.529.2.86.1.1.48) +# this lineages which was designated in pango-designation v1.27: https://github.com/cov-lineages/pango-designation/releases/tag/v1.27 +# see here for commit where it was designated https://github.com/cov-lineages/pango-designation/commit/67f48bf24283999f1940f3aee8159f404124ff3f +# Here's the genome on NCBI: https://www.ncbi.nlm.nih.gov/nuccore/PP218754 +RUN datasets download virus genome accession PP218754.1 --filename PP218754.1.zip && \ +unzip -o PP218754.1.zip && rm PP218754.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna PP218754.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin PP218754.1.genomic.fna -o PP218754.1-usher && \ +column -t -s, PP218754.1-usher/lineage_report.csv + +# new lineage LK.1 that was introduced in pango-designation v1.28: https://github.com/cov-lineages/pango-designation/commit/922795c90de355e67200cf4d379e8e5ff22472e4 +# thank you Luis, Lorraine, Marcos & team from PR Sci Trust for sharing your data! +# genome on NCBI: https://www.ncbi.nlm.nih.gov/nuccore/2728145425 +RUN datasets download virus genome accession PP770375.1 --filename PP770375.1.zip && \ +unzip -o PP770375.1.zip && rm PP770375.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna PP770375.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin PP770375.1.genomic.fna -o PP770375.1-usher && \ +column -t -s, PP770375.1-usher/lineage_report.csv + +# new lineage KP.3.3.2 that was introduced in pango-designation v1.29: https://github.com/cov-lineages/pango-designation/commit/7125e606818312b78f0756d7fcab6dba92dd0a9e +# genome on NCBI: https://www.ncbi.nlm.nih.gov/nuccore/PQ073669 +RUN datasets download virus genome accession PQ073669.1 --filename PQ073669.1.zip && \ +unzip -o PQ073669.1.zip && rm PQ073669.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna PQ073669.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin PQ073669.1.genomic.fna -o PQ073669.1-usher && \ +column -t -s, PQ073669.1-usher/lineage_report.csv + +# new lineage MC.2 that was introduced in pango-designation v1.30: https://github.com/cov-lineages/pango-designation/commit/c64dbc47fbfbfd7f4da011deeb1a88dd6baa45f1#diff-a121ea4b8cbeb4c0020511b5535bf24489f0223cc83511df7b8209953115d329R2564181 +# genome on NCBI: https://www.ncbi.nlm.nih.gov/nuccore/PQ034842.1 +RUN datasets download virus genome accession PQ034842.1 --filename PQ034842.1.zip && \ +unzip -o PQ034842.1.zip && rm PQ034842.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna PQ034842.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin PQ034842.1.genomic.fna -o PQ034842.1-usher && \ +column -t -s, PQ034842.1-usher/lineage_report.csv diff --git a/pangolin/4.3.1-pdata-1.30/README.md b/pangolin/4.3.1-pdata-1.30/README.md new file mode 100644 index 000000000..16c0da511 --- /dev/null +++ b/pangolin/4.3.1-pdata-1.30/README.md @@ -0,0 +1,53 @@ +# pangolin docker image + +Main tool : [pangolin](https://github.com/cov-lineages/pangolin) + +Full documentation: [https://cov-lineages.org/resources/pangolin.html](https://cov-lineages.org/resources/pangolin.html) + +Phylogenetic Assignment of Named Global Outbreak LINeages + +Additional tools: + +- [pangolin-data](https://github.com/cov-lineages/pangolin-data) 1.30 +- [pangolin-assignment](https://github.com/cov-lineages/pangolin-assignment) 1.30 +- [minimap2](https://github.com/lh3/minimap2) 2.28-r1209 +- [usher](https://github.com/yatisht/usher) 0.6.3 +- [faToVcf](https://github.com/yatisht/usher) 448 +- [scorpio](https://github.com/cov-lineages/scorpio) 0.3.19 +- [constellations](https://github.com/cov-lineages/constellations) 0.1.12 +- [gofasta](https://github.com/virus-evolution/gofasta) 1.2.1 +- [mafft](https://mafft.cbrc.jp/alignment/software/) 7.526 +- python 3.8.19 + +## pangoLEARN deprecation + +As of pangolin version 4.3, pangoLEARN mode has been deprecated. [More info can be found here on the v4.3 release page.](https://github.com/cov-lineages/pangolin/releases/tag/v4.3) + +> If `--analysis-mode fast` or `--analysis-mode pangolearn` is given, pangolin v4.3 will print out a warning and use UShER mode instead, unless `--datadir` is also given specifying a directory with pangoLEARN model files. The next release of pangolin-data (v1.20) will no longer include the model files which have not been updated since v1.18. + +The pangoLEARN model has not been updated since pangolin-data version 1.18. Only the the underlying UShER tree/protobuf file will be maintained for the forseeable future. + +**Please use the UShER mode of pangolin if you want to stay up-to-date with the most recent lineages.** [See pangolin-data release notes here for more details](https://github.com/cov-lineages/pangolin-data/releases) + +## Example Usage + +```bash +# run Pangolin in the default mode (usher). Can optionally supply --analysis-mode usher +$ pangolin /pangolin/pangolin/test/test_seqs.fasta -o /data/test_seqs-output-pusher + +# view the output CSV +$ column -t -s, /data/test_seqs-output-pusher/lineage_report.csv +taxon lineage conflict ambiguity_score scorpio_call scorpio_support scorpio_conflict scorpio_notes version pangolin_version scorpio_version constellation_version is_designated qc_status qc_notes note +India seq B.1.617.1 0.0 B.1.617.1-like 1.0 0.0 scorpio call: Alt alleles 11; Ref alleles 0; Amb alleles 0; Oth alleles 0 PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False pass Ambiguous_content:0.02 Usher placements: B.1.617.1(1/1) +b117 B.1.1.7 0.0 Alpha (B.1.1.7-like) 0.91 0.04 scorpio call: Alt alleles 21; Ref alleles 1; Amb alleles 1; Oth alleles 0 PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False pass Ambiguous_content:0.02 Usher placements: B.1.1.7(2/2) +outgroup_A A 0.0 PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False pass Ambiguous_content:0.02 Usher placements: A(1/1) +issue_57_torsten_seq Unassigned PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False fail failed to map +This_seq_has_6000_Ns_in_18000_bases Unassigned PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False fail failed to map +This_seq_has_no_seq Unassigned PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False fail failed to map +This_seq_is_too_short Unassigned PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False fail Ambiguous_content:0.9 +This_seq_has_lots_of_Ns Unassigned PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False fail Ambiguous_content:0.98 +This_seq_is_literally_just_N Unassigned PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False fail failed to map +Japan_seq B 0.0 PANGO-v1.16 4.1.3 0.3.17 v0.1.10 True pass Ambiguous_content:0.02 Assigned from designation hash. +USA_seq B.1.314 0.0 PANGO-v1.16 4.1.3 0.3.17 v0.1.10 True pass Ambiguous_content:0.02 Assigned from designation hash. +Unassigned_omicron_seq BA.1 0.0 Probable Omicron (BA.1-like) 0.71 0.08 scorpio call: Alt alleles 42; Ref alleles 5; Amb alleles 9; Oth alleles 3 PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False pass Ambiguous_content:0.03 Usher placements: BA.1(1/1) +``` From 08c7bec2e73dce23897caa012b4233816c28050f Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Mon, 23 Sep 2024 17:34:22 +0000 Subject: [PATCH 14/92] add bullet and softlink in main readme --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index bda448883..d6a286024 100644 --- a/README.md +++ b/README.md @@ -222,7 +222,7 @@ To learn more about the docker pull rate limits and the open source software pro | [OrthoFinder](https://hub.docker.com/r/staphb/orthofinder)
[![docker pulls](https://badgen.net/docker/pulls/staphb/orthofinder)](https://hub.docker.com/r/staphb/orthofinder) |
  • 2.17
| https://github.com/davidemms/OrthoFinder | | [Panaroo](https://hub.docker.com/r/staphb/panaroo)
[![docker pulls](https://badgen.net/docker/pulls/staphb/panaroo)](https://hub.docker.com/r/staphb/panaroo) |
  • [1.2.10](panaroo/1.2.10/)
  • [1.3.4](panaroo/1.3.4/)
  • [1.5.0](./panaroo/1.5.0/)
| (https://hub.docker.com/r/staphb/panaroo) | | [pango_aliasor](https://hub.docker.com/r/staphb/pango_aliasor)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pango_aliasor)](https://hub.docker.com/r/staphb/pango_aliasor) |
  • [0.3.0](./pango_aliasor/0.3.0/)
| https://github.com/corneliusroemer/pango_aliasor | -| [Pangolin](https://hub.docker.com/r/staphb/pangolin)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pangolin)](https://hub.docker.com/r/staphb/pangolin) |
Click to see Pangolin v4.2 and older versions! **Pangolin version & pangoLEARN data release date**
  • 1.1.14
  • 2.0.4 & 2020-07-20
  • 2.0.5 & 2020-07-20
  • 2.1.1 & 2020-12-17
  • 2.1.3 & 2020-12-17
  • 2.1.6 & 2021-01-06
  • 2.1.7 & 2021-01-11
  • 2.1.7 & 2021-01-20
  • 2.1.8 & 2021-01-22
  • 2.1.10 & 2021-02-01
  • 2.1.11 & 2021-02-01
  • 2.1.11 & 2021-02-05
  • 2.2.1 & 2021-02-06
  • 2.2.2 & 2021-02-06
  • 2.2.2 & 2021-02-11
  • 2.2.2 & 2021-02-12
  • 2.3.0 & 2021-02-12
  • 2.3.0 & 2021-02-18
  • 2.3.0 & 2021-02-21
  • 2.3.2 & 2021-02-21
  • 2.3.3 & 2021-03-16
  • 2.3.4 & 2021-03-16
  • 2.3.5 & 2021-03-16
  • 2.3.6 & 2021-03-16
  • 2.3.6 & 2021-03-29
  • 2.3.8 & 2021-04-01
  • 2.3.8 & 2021-04-14
  • 2.3.8 & 2021-04-21
  • 2.3.8 & 2021-04-23
  • 2.4 & 2021-04-28
  • 2.4.1 & 2021-04-28
  • 2.4.2 & 2021-04-28
  • 2.4.2 & 2021-05-10
  • 2.4.2 & 2021-05-11
  • 2.4.2 & 2021-05-19
  • 3.0.5 & 2021-06-05
  • 3.1.3 & 2021-06-15
  • 3.1.5 & 2021-06-15
  • 3.1.5 & 2021-07-07-2
  • 3.1.7 & 2021-07-09
  • 3.1.8 & 2021-07-28
  • 3.1.10 & 2021-07-28
  • 3.1.11 & 2021-08-09
  • 3.1.11 & 2021-08-24
  • 3.1.11 & 2021-09-17
  • 3.1.14 & 2021-09-28
  • 3.1.14 & 2021-10-13
  • 3.1.16 & 2021-10-18
  • 3.1.16 & 2021-11-04
  • 3.1.16 & 2021-11-09
  • 3.1.16 & 2021-11-18
  • 3.1.16 & 2021-11-25
  • 3.1.17 & 2021-11-25
  • 3.1.17 & 2021-12-06
  • 3.1.17 & 2022-01-05
  • 3.1.18 & 2022-01-20
  • 3.1.19 & 2022-01-20
  • 3.1.20 & 2022-02-02
  • 3.1.20 & 2022-02-28
**Pangolin version & pangolin-data version**
  • 4.0 & 1.2.133
  • 4.0.1 & 1.2.133
  • 4.0.2 & 1.2.133
  • 4.0.3 & 1.2.133
  • 4.0.4 & 1.2.133
  • 4.0.5 & 1.3
  • 4.0.6 & 1.6
  • 4.0.6 & 1.8
  • 4.0.6 & 1.9
  • 4.1.1 & 1.11
  • 4.1.2 & 1.12
  • 4.1.2 & 1.13
  • 4.1.2 & 1.14
  • 4.1.3 & 1.15.1
  • 4.1.3 & 1.16
  • 4.1.3 & 1.17
  • 4.2 & 1.18
  • 4.2 & 1.18.1
  • 4.2 & 1.18.1.1
  • 4.2 & 1.19
**Pangolin version & pangolin-data version**
  • [4.3 & 1.20](pangolin/4.3-pdata-1.20/)
  • [4.3 & 1.21](pangolin/4.3-pdata-1.21/)
  • [4.3.1 & 1.22](pangolin/4.3.1-pdata-1.22/)
  • [4.3.1 & 1.23](pangolin/4.3.1-pdata-1.23/)
  • [4.3.1 & 1.23.1](pangolin/4.3.1-pdata-1.23.1/)
  • [4.3.1 & 1.23.1 with XDG_CACHE_HOME=/tmp](pangolin/4.3.1-pdata-1.23.1-1/)
  • [4.3.1 & 1.24](pangolin/4.3.1-pdata-1.24/)
  • [4.3.1 & 1.25.1](pangolin/4.3.1-pdata-1.25.1/)
  • [4.3.1 & 1.26](pangolin/4.3.1-pdata-1.26/)
  • [4.3.1 & 1.27](pangolin/4.3.1-pdata-1.27/)
  • [4.3.1 & 1.28](pangolin/4.3.1-pdata-1.28/)
  • [4.3.1 & 1.28.1](pangolin/4.3.1-pdata-1.28.1/)
  • [4.3.1 & 1.29](pangolin/4.3.1-pdata-1.29/)
| https://github.com/cov-lineages/pangolin
https://github.com/cov-lineages/pangoLEARN
https://github.com/cov-lineages/pango-designation
https://github.com/cov-lineages/scorpio
https://github.com/cov-lineages/constellations
https://github.com/cov-lineages/lineages (archived)
https://github.com/hCoV-2019/pangolin (archived) | +| [Pangolin](https://hub.docker.com/r/staphb/pangolin)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pangolin)](https://hub.docker.com/r/staphb/pangolin) |
Click to see Pangolin v4.2 and older versions! **Pangolin version & pangoLEARN data release date**
  • 1.1.14
  • 2.0.4 & 2020-07-20
  • 2.0.5 & 2020-07-20
  • 2.1.1 & 2020-12-17
  • 2.1.3 & 2020-12-17
  • 2.1.6 & 2021-01-06
  • 2.1.7 & 2021-01-11
  • 2.1.7 & 2021-01-20
  • 2.1.8 & 2021-01-22
  • 2.1.10 & 2021-02-01
  • 2.1.11 & 2021-02-01
  • 2.1.11 & 2021-02-05
  • 2.2.1 & 2021-02-06
  • 2.2.2 & 2021-02-06
  • 2.2.2 & 2021-02-11
  • 2.2.2 & 2021-02-12
  • 2.3.0 & 2021-02-12
  • 2.3.0 & 2021-02-18
  • 2.3.0 & 2021-02-21
  • 2.3.2 & 2021-02-21
  • 2.3.3 & 2021-03-16
  • 2.3.4 & 2021-03-16
  • 2.3.5 & 2021-03-16
  • 2.3.6 & 2021-03-16
  • 2.3.6 & 2021-03-29
  • 2.3.8 & 2021-04-01
  • 2.3.8 & 2021-04-14
  • 2.3.8 & 2021-04-21
  • 2.3.8 & 2021-04-23
  • 2.4 & 2021-04-28
  • 2.4.1 & 2021-04-28
  • 2.4.2 & 2021-04-28
  • 2.4.2 & 2021-05-10
  • 2.4.2 & 2021-05-11
  • 2.4.2 & 2021-05-19
  • 3.0.5 & 2021-06-05
  • 3.1.3 & 2021-06-15
  • 3.1.5 & 2021-06-15
  • 3.1.5 & 2021-07-07-2
  • 3.1.7 & 2021-07-09
  • 3.1.8 & 2021-07-28
  • 3.1.10 & 2021-07-28
  • 3.1.11 & 2021-08-09
  • 3.1.11 & 2021-08-24
  • 3.1.11 & 2021-09-17
  • 3.1.14 & 2021-09-28
  • 3.1.14 & 2021-10-13
  • 3.1.16 & 2021-10-18
  • 3.1.16 & 2021-11-04
  • 3.1.16 & 2021-11-09
  • 3.1.16 & 2021-11-18
  • 3.1.16 & 2021-11-25
  • 3.1.17 & 2021-11-25
  • 3.1.17 & 2021-12-06
  • 3.1.17 & 2022-01-05
  • 3.1.18 & 2022-01-20
  • 3.1.19 & 2022-01-20
  • 3.1.20 & 2022-02-02
  • 3.1.20 & 2022-02-28
**Pangolin version & pangolin-data version**
  • 4.0 & 1.2.133
  • 4.0.1 & 1.2.133
  • 4.0.2 & 1.2.133
  • 4.0.3 & 1.2.133
  • 4.0.4 & 1.2.133
  • 4.0.5 & 1.3
  • 4.0.6 & 1.6
  • 4.0.6 & 1.8
  • 4.0.6 & 1.9
  • 4.1.1 & 1.11
  • 4.1.2 & 1.12
  • 4.1.2 & 1.13
  • 4.1.2 & 1.14
  • 4.1.3 & 1.15.1
  • 4.1.3 & 1.16
  • 4.1.3 & 1.17
  • 4.2 & 1.18
  • 4.2 & 1.18.1
  • 4.2 & 1.18.1.1
  • 4.2 & 1.19
**Pangolin version & pangolin-data version**
  • [4.3 & 1.20](pangolin/4.3-pdata-1.20/)
  • [4.3 & 1.21](pangolin/4.3-pdata-1.21/)
  • [4.3.1 & 1.22](pangolin/4.3.1-pdata-1.22/)
  • [4.3.1 & 1.23](pangolin/4.3.1-pdata-1.23/)
  • [4.3.1 & 1.23.1](pangolin/4.3.1-pdata-1.23.1/)
  • [4.3.1 & 1.23.1 with XDG_CACHE_HOME=/tmp](pangolin/4.3.1-pdata-1.23.1-1/)
  • [4.3.1 & 1.24](pangolin/4.3.1-pdata-1.24/)
  • [4.3.1 & 1.25.1](pangolin/4.3.1-pdata-1.25.1/)
  • [4.3.1 & 1.26](pangolin/4.3.1-pdata-1.26/)
  • [4.3.1 & 1.27](pangolin/4.3.1-pdata-1.27/)
  • [4.3.1 & 1.28](pangolin/4.3.1-pdata-1.28/)
  • [4.3.1 & 1.28.1](pangolin/4.3.1-pdata-1.28.1/)
  • [4.3.1 & 1.29](pangolin/4.3.1-pdata-1.29/)
  • [4.3.1 & 1.30](pangolin/4.3.1-pdata-1.30/)
| https://github.com/cov-lineages/pangolin
https://github.com/cov-lineages/pangoLEARN
https://github.com/cov-lineages/pango-designation
https://github.com/cov-lineages/scorpio
https://github.com/cov-lineages/constellations
https://github.com/cov-lineages/lineages (archived)
https://github.com/hCoV-2019/pangolin (archived) | | [panqc](https://hub.docker.com/r/staphb/panqc)
[![docker pulls](https://badgen.net/docker/pulls/staphb/panqc)](https://hub.docker.com/r/staphb/panqc) |
  • [0.4.0](./panqc/0.4.0/)
| https://github.com/maxgmarin/panqc/releases/tag/0.4.0 | | [parallel-perl](https://hub.docker.com/r/staphb/parallel-perl)
[![docker pulls](https://badgen.net/docker/pulls/staphb/parallel-perl)](https://hub.docker.com/r/staphb/parallel-perl) |
  • 20200722
| https://www.gnu.org/software/parallel | | [parsnp](https://hub.docker.com/r/staphb/parsnp)
[![docker pulls](https://badgen.net/docker/pulls/staphb/parsnp)](https://hub.docker.com/r/staphb/parsnp) |
  • [1.5.6](./parsnp/1.5.6/)
  • [2.0.4](./parsnp/2.0.4/)
  • [2.0.5](./parsnp/2.0.5/)
| https://github.com/marbl/parsnp | From 79c98a66d070949b760fda13b68cf06808f06be9 Mon Sep 17 00:00:00 2001 From: Young Date: Mon, 30 Sep 2024 06:49:22 -0600 Subject: [PATCH 15/92] adding bcftools version 1.21 (#1055) * adding bcftools version 1.21 * Update README.md changed v1.20 to 1.21 --------- Co-authored-by: Kutluhan Incekara <46578029+Kincekara@users.noreply.github.com> --- README.md | 2 +- bcftools/1.21/Dockerfile | 117 +++++++++++++++++++++++++++++++++++++++ bcftools/1.21/README.md | 25 +++++++++ 3 files changed, 143 insertions(+), 1 deletion(-) create mode 100644 bcftools/1.21/Dockerfile create mode 100644 bcftools/1.21/README.md diff --git a/README.md b/README.md index d6a286024..2a031db91 100644 --- a/README.md +++ b/README.md @@ -124,7 +124,7 @@ To learn more about the docker pull rate limits and the open source software pro | [bakta](https://hub.docker.com/r/staphb/bakta)
[![docker pulls](https://badgen.net/docker/pulls/staphb/bakta)](https://hub.docker.com/r/staphb/bakta) |
  • [1.9.2](./bakta/1.9.2/)
  • [1.9.2-light](./bakta/1.9.2-5.1-light/)
  • [1.9.3](./bakta/1.9.3/)
  • [1.9.3-light](./bakta/1.9.3-5.1-light/)
  • [1.9.4](./bakta/1.9.4/)
| https://github.com/oschwengers/bakta | | [bandage](https://hub.docker.com/r/staphb/bandage)
[![docker pulls](https://badgen.net/docker/pulls/staphb/bandage)](https://hub.docker.com/r/staphb/bandage) |
  • [0.8.1](./bandage/0.8.1/)
| https://rrwick.github.io/Bandage/ | | [BBTools](https://hub.docker.com/r/staphb/bbtools/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/bbtools)](https://hub.docker.com/r/staphb/bbtools) |
  • [38.76](./bbtools/38.76/)
  • [38.86](./bbtools/38.86/)
  • [38.95](./bbtools/38.95/)
  • [38.96](./bbtools/38.96/)
  • [38.97](./bbtools/38.97/)
  • [38.98](./bbtools/38.98/)
  • [38.99](./bbtools/38.99/)
  • [39.00](./bbtools/39.00/)
  • [39.01](./bbtools/39.01/)
  • [39.06](./bbtools/39.06/)
| https://jgi.doe.gov/data-and-tools/bbtools/ | -| [bcftools](https://hub.docker.com/r/staphb/bcftools/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/bcftools)](https://hub.docker.com/r/staphb/bcftools) |
  • [1.10.2](./bcftools/1.10.2/)
  • [1.11](./bcftools/1.11/)
  • [1.12](./bcftools/1.12/)
  • [1.13](./bcftools/1.13/)
  • [1.14](./bcftools/1.14/)
  • [1.15](./bcftools/1.15/)
  • [1.16](./bcftools/1.16/)
  • [1.17](./bcftools/1.17/)
  • [1.18](bcftools/1.18/)
  • [1.19](./bcftools/1.19/)
  • [1.20](./bcftools/1.20/)
  • [1.20.c](./bcftools/1.20.c/)
| https://github.com/samtools/bcftools | +| [bcftools](https://hub.docker.com/r/staphb/bcftools/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/bcftools)](https://hub.docker.com/r/staphb/bcftools) |
  • [1.10.2](./bcftools/1.10.2/)
  • [1.11](./bcftools/1.11/)
  • [1.12](./bcftools/1.12/)
  • [1.13](./bcftools/1.13/)
  • [1.14](./bcftools/1.14/)
  • [1.15](./bcftools/1.15/)
  • [1.16](./bcftools/1.16/)
  • [1.17](./bcftools/1.17/)
  • [1.18](bcftools/1.18/)
  • [1.19](./bcftools/1.19/)
  • [1.20](./bcftools/1.20/)
  • [1.20.c](./bcftools/1.20.c/)
  • [1.21](./bcftools/1.21/)
| https://github.com/samtools/bcftools | | [bedtools](https://hub.docker.com/r/staphb/bedtools/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/bedtools)](https://hub.docker.com/r/staphb/bedtools) |
  • 2.29.2
  • 2.30.0
  • [2.31.0](bedtools/2.31.0/)
  • [2.31.1](bedtools/2.31.1/)
| https://bedtools.readthedocs.io/en/latest/
https://github.com/arq5x/bedtools2 | | [berrywood-report-env](https://hub.docker.com/r/staphb/berrywood-report-env/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/berrywood-report-env)](https://hub.docker.com/r/staphb/berrywood-report-env) |
  • 1.0
| none | | [blast+](https://hub.docker.com/r/staphb/blast/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/blast)](https://hub.docker.com/r/staphb/blast) |
  • [2.13.0](blast/2.13.0/)
  • [2.14.0](blast/2.14.0/)
  • [2.14.1](blast/2.14.1/)
  • [2.15.0](blast/2.15.0/)
  • [2.16.0](./blast/2.16.0/)
| https://www.ncbi.nlm.nih.gov/books/NBK279690/ | diff --git a/bcftools/1.21/Dockerfile b/bcftools/1.21/Dockerfile new file mode 100644 index 000000000..7e14bc796 --- /dev/null +++ b/bcftools/1.21/Dockerfile @@ -0,0 +1,117 @@ +# for easy upgrade later. ARG variables only persist during build time +ARG BCFTOOLS_VER="1.21" + +FROM ubuntu:jammy as builder + +# re-instantiate variable +ARG BCFTOOLS_VER + +# install dependencies, cleanup apt garbage +RUN apt-get update && apt-get install --no-install-recommends -y \ + wget \ + ca-certificates \ + perl \ + bzip2 \ + autoconf \ + automake \ + make \ + gcc \ + zlib1g-dev \ + libbz2-dev \ + liblzma-dev \ + libcurl4-gnutls-dev \ + libssl-dev \ + libperl-dev \ + libgsl0-dev \ + libdeflate-dev \ + procps && \ + rm -rf /var/lib/apt/lists/* && apt-get autoclean + + +# download, compile, and install bcftools +RUN wget https://github.com/samtools/bcftools/releases/download/${BCFTOOLS_VER}/bcftools-${BCFTOOLS_VER}.tar.bz2 && \ + tar -xjf bcftools-${BCFTOOLS_VER}.tar.bz2 && \ + rm -v bcftools-${BCFTOOLS_VER}.tar.bz2 && \ + cd bcftools-${BCFTOOLS_VER} && \ + ./configure --enable-libgsl --enable-perl-filters &&\ + make && \ + make install && \ + make test + +### start of app stage ### +FROM ubuntu:jammy as app + +# re-instantiate variable +ARG BCFTOOLS_VER + +# putting the labels in +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="bcftools" +LABEL software.version="${BCFTOOLS_VER}" +LABEL description="Variant calling and manipulating files in the Variant Call Format (VCF) and its binary counterpart BCF" +LABEL website="https://github.com/samtools/bcftools" +LABEL license="https://github.com/samtools/bcftools/blob/develop/LICENSE" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" +LABEL maintainer2="Curtis Kapsak" +LABEL maintainer2.email="kapsakcj@gmail.com" + +# install dependencies required for running bcftools +# https://github.com/samtools/bcftools/blob/develop/INSTALL#L29 +RUN apt-get update && apt-get install --no-install-recommends -y \ + perl\ + zlib1g \ + gsl-bin \ + bzip2 \ + liblzma5 \ + libcurl3-gnutls \ + libdeflate0 \ + procps \ + && apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# copy in bcftools executables from builder stage +COPY --from=builder /usr/local/bin/* /usr/local/bin/ +# copy in bcftools plugins from builder stage +COPY --from=builder /usr/local/libexec/bcftools/* /usr/local/libexec/bcftools/ + +# set locale settings for singularity compatibility +ENV LC_ALL=C + +# set final working directory +WORKDIR /data + +# default command is to pull up help optoins +CMD ["bcftools", "--help"] + +### start of test stage ### +FROM app as test + +# running --help and listing plugins +RUN bcftools --help && bcftools plugin -lv + +# install wget for downloading test files +RUN apt-get update && apt-get install -y wget vcftools + +RUN echo "downloading test SC2 BAM and FASTA and running bcftools mpileup and bcftools call test commands..." && \ + wget -q https://raw.githubusercontent.com/artic-network/artic-ncov2019/master/primer_schemes/nCoV-2019/V4/SARS-CoV-2.reference.fasta && \ + wget -q https://raw.githubusercontent.com/StaPH-B/docker-builds/master/tests/SARS-CoV-2/SRR13957123.primertrim.sorted.bam && \ + bcftools mpileup -A -d 200 -B -Q 0 -f SARS-CoV-2.reference.fasta SRR13957123.primertrim.sorted.bam | \ + bcftools call -mv -Ov -o SRR13957123.vcf + +RUN echo "testing plugins..." && \ + bcftools +counts SRR13957123.vcf + +RUN echo "testing polysomy..." && \ + wget https://samtools.github.io/bcftools/howtos/cnv-calling/usage-example.tgz &&\ + tar -xvf usage-example.tgz &&\ + zcat test.fcr.gz | ./fcr-to-vcf -b bcftools -a map.tab.gz -o outdir/ &&\ + bcftools cnv -o cnv/ outdir/test.vcf.gz &&\ + bcftools polysomy -o psmy/ outdir/test.vcf.gz &&\ + head psmy/dist.dat + +RUN echo "reading test data from Google Cloud to validate GCS support" && \ + bcftools head -h 20 gs://genomics-public-data/references/hg38/v0/1000G_phase1.snps.high_confidence.hg38.vcf.gz + +RUN echo "reading test data from S3 to validate AWS support" && \ + bcftools head -h 20 s3://human-pangenomics/T2T/CHM13/assemblies/variants/GATK_CHM13v2.0_Resource_Bundle/resources-broad-hg38-v0-1000G_phase1.snps.high_confidence.hg38.t2t-chm13-v2.0.vcf.gz diff --git a/bcftools/1.21/README.md b/bcftools/1.21/README.md new file mode 100644 index 000000000..005643cf1 --- /dev/null +++ b/bcftools/1.21/README.md @@ -0,0 +1,25 @@ +# bcftools container + +Main tool: [bcftools](https://github.com/samtools/bcftools) + +Code repository: https://github.com/samtools/bcftools + +Basic information on how to use this tool: +- executable: bcftools +- help: --help +- version: --version +- description: BCFtools is a program for variant calling and manipulating files in the Variant Call Format (VCF) and its binary counterpart BCF. + +Additional information: + +This container includes bcftools v1.21 compiled with **libdeflate** for a better cloud performance. Also, "polysomy" and plugins are enabled in this image. + +Full documentation: https://samtools.github.io/bcftools/howtos/index.html + +## Example Usage + +```bash +bcftools mpileup -A -d 200 -B -Q 0 -f {reference_genome} {bam} | bcftools call -mv -Ov -o bcftools_variants/{sample}.vcf +``` + + From 3e3785a94b29ade7343021fdb1c2d712ae325f8c Mon Sep 17 00:00:00 2001 From: Young Date: Mon, 30 Sep 2024 06:56:09 -0600 Subject: [PATCH 16/92] updating htslib to 1.21 (#1060) * updating htslib to 1.21 * Update README.md v.1.20 -> v.1.21 --------- Co-authored-by: Kutluhan Incekara <46578029+Kincekara@users.noreply.github.com> --- README.md | 2 +- htslib/1.21/Dockerfile | 97 ++++++++++++++++++++++++++++++++++++++++++ htslib/1.21/README.md | 35 +++++++++++++++ 3 files changed, 133 insertions(+), 1 deletion(-) create mode 100644 htslib/1.21/Dockerfile create mode 100644 htslib/1.21/README.md diff --git a/README.md b/README.md index 2a031db91..584bf2ff7 100644 --- a/README.md +++ b/README.md @@ -177,7 +177,7 @@ To learn more about the docker pull rate limits and the open source software pro | [heatcluster](https://hub.docker.com/r/staphb/heatcluster)
[![docker pulls](https://badgen.net/docker/pulls/staphb/heatcluster)](https://hub.docker.com/r/staphb/heatcluster) |
  • [1.0.2c](./heatcluster/1.0.2c/)
| https://github.com/DrB-S/heatcluster/tree/main | | [hmmer](https://hub.docker.com/r/staphb/hmmer)
[![docker pulls](https://badgen.net/docker/pulls/staphb/hmmer)](https://hub.docker.com/r/staphb/hmmer) |
  • [3.3](hmmer/3.3/)
  • [3.3.2](hmmer/3.3.2/)
  • [3.4](./hmmer/3.4/)
| http://hmmer.org/ | | [homopolish](https://hub.docker.com/r/staphb/homopolish)
[![docker pulls](https://badgen.net/docker/pulls/staphb/homopolish)](https://hub.docker.com/r/staphb/homopolish) |
  • 0.4.1
| https://github.com/ythuang0522/homopolish/ | -| [htslib](https://hub.docker.com/r/staphb/htslib)
[![docker pulls](https://badgen.net/docker/pulls/staphb/htslib)](https://hub.docker.com/r/staphb/htslib) |
  • [1.14](./htslib/1.14)
  • [1.15](./htslib/1.15)
  • [1.16](./htslib/1.16)
  • [1.17](./htslib/1.17)
  • [1.18](./htslib/1.18/)
  • [1.19](./htslib/1.19/)
  • [1.20](./htslib/1.20/)
  • [1.20.c](./htslib/1.20.c/)
| https://www.htslib.org/ | +| [htslib](https://hub.docker.com/r/staphb/htslib)
[![docker pulls](https://badgen.net/docker/pulls/staphb/htslib)](https://hub.docker.com/r/staphb/htslib) |
  • [1.14](./htslib/1.14)
  • [1.15](./htslib/1.15)
  • [1.16](./htslib/1.16)
  • [1.17](./htslib/1.17)
  • [1.18](./htslib/1.18/)
  • [1.19](./htslib/1.19/)
  • [1.20](./htslib/1.20/)
  • [1.20.c](./htslib/1.20.c/)
  • [1.21](./htslib/1.21/)
| https://www.htslib.org/ | | [iqtree](https://hub.docker.com/r/staphb/iqtree/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/iqtree)](https://hub.docker.com/r/staphb/iqtree) |
  • 1.6.7
| http://www.iqtree.org/ | | [iqtree2](https://hub.docker.com/r/staphb/iqtree2/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/iqtree2)](https://hub.docker.com/r/staphb/iqtree2) |
  • 2.1.2
  • 2.2.2.2
  • [2.2.2.6](iqtree2/2.2.2.6/)
  • [2.2.2.7](iqtree2/2.2.2.7/)
  • [2.3.1](iqtree2/2.3.1/)
  • [2.3.4](iqtree2/2.3.4/)
| http://www.iqtree.org/ | | [IPA](https://hub.docker.com/r/staphb/pbipa)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pbipa)](https://hub.docker.com/r/staphb/pbipa) |
  • [1.8.0](./pbipa/1.8.0/)
| https://github.com/PacificBiosciences/pbipa | diff --git a/htslib/1.21/Dockerfile b/htslib/1.21/Dockerfile new file mode 100644 index 000000000..47f42bfc8 --- /dev/null +++ b/htslib/1.21/Dockerfile @@ -0,0 +1,97 @@ +# for easy upgrade later. ARG variables only persist during build time +ARG HTSLIB_VER="1.21" + +FROM ubuntu:jammy as builder + +ARG HTSLIB_VER + +# install dependencies, cleanup apt garbage +# It's helpful when they're all listed on https://github.com/samtools/htslib/blob/develop/INSTALL +RUN apt-get update && apt-get install --no-install-recommends -y \ + wget \ + ca-certificates \ + make \ + bzip2 \ + autoconf \ + automake \ + make \ + gcc \ + perl \ + zlib1g-dev \ + libbz2-dev \ + liblzma-dev \ + libcurl4-gnutls-dev \ + libssl-dev \ + libdeflate-dev \ + procps && \ + rm -rf /var/lib/apt/lists/* && apt-get autoclean + +# get htslib, compile, install, run test suite +RUN wget -q https://github.com/samtools/htslib/releases/download/${HTSLIB_VER}/htslib-${HTSLIB_VER}.tar.bz2 && \ + tar -vxjf htslib-${HTSLIB_VER}.tar.bz2 && \ + rm -v htslib-${HTSLIB_VER}.tar.bz2 && \ + cd htslib-${HTSLIB_VER} && \ + ./configure && \ + make && \ + make install && \ + make test + +### start of app stage ### +FROM ubuntu:jammy as app + +ARG HTSLIB_VER + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="htslib" +LABEL software.version="${HTSLIB_VER}" +LABEL description="A C library for reading/writing high-throughput sequencing data" +LABEL website="https://github.com/samtools/htslib" +LABEL license="https://github.com/samtools/htslib/blob/develop/LICENSE" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" +LABEL maintainer2="Curtis Kapsak" +LABEL maintainer2.email="kapsakcj@gmail.com" + +# install runtime dependencies & cleanup apt garbage +# installed as recommend here: https://github.com/samtools/htslib/blob/develop/INSTALL#L31 +RUN apt-get update && apt-get install --no-install-recommends -y \ + bzip2 \ + zlib1g \ + libbz2-1.0 \ + liblzma5 \ + libcurl3-gnutls \ + libdeflate0 \ + ca-certificates \ + && apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# copy in htslib executables from builder stage +COPY --from=builder /usr/local/bin/* /usr/local/bin/ +COPY --from=builder /usr/local/lib/ /usr/local/lib/ +COPY --from=builder /usr/local/include/ /usr/local/include/ + +# set locale settings for singularity compatibility +ENV LC_ALL=C + +# set working directory +WORKDIR /data + +# default command is to show help options +CMD ["htsfile", "--help"] + +### start of test stage ### +FROM app as test + +# check that these three executables are available +RUN bgzip --help && tabix --help && htsfile --help + +RUN apt-get update && apt-get install --no-install-recommends -y wget + +# use on actual files +RUN wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_1.fastq.gz && \ + gunzip SRR13957123_1.fastq.gz && \ + bgzip SRR13957123_1.fastq + +# FYI Test suite "make test" now performed in the builder stage since app and +# test stages do not include htslib source code. +# This is to avoid having to re-download source code simply to run test suite \ No newline at end of file diff --git a/htslib/1.21/README.md b/htslib/1.21/README.md new file mode 100644 index 000000000..1b505f02c --- /dev/null +++ b/htslib/1.21/README.md @@ -0,0 +1,35 @@ +# htslib container + +Main tool: [htslib](https://www.htslib.org/) + +Code repository: https://github.com/samtools/htslib + +Additional tools: + +* perl 5.34.0 + +Basic information on how to use this tool: +- executable: htsfile +- help: --help +- version: --version +- description: The htsfile utility attempts to identify what kind of high-throughput sequencing data files the specified files are, and provides minimal viewing capabilities for some kinds of data file. + +Additional information: + +This container includes htslib v1.21 compiled with **libdeflate** for a better cloud performance. + +Full documentation: https://www.htslib.org/doc/samtools.html + +## Example Usage + +```bash +# determine file formats for various BAM and SAM files +$ htsfile tests/SARS-CoV-2/SRR13957123.primertrim.sorted.bam +tests/SARS-CoV-2/SRR13957123.primertrim.sorted.bam: BAM version 1 compressed sequence data + +$ htsfile ce_tag_padded.sam +ce_tag_padded.sam: SAM version 1.4 sequence text + +# compresses sample.fastq to sample.fastq.gz in BGZF format (blocked GNU Zip Format) +$ bgzip sample.fastq +``` From 7cf7b86e8033b31f05f3d2c0cb4c79d06885e966 Mon Sep 17 00:00:00 2001 From: Young Date: Mon, 30 Sep 2024 09:28:11 -0600 Subject: [PATCH 17/92] adding assembly_snptyper version 0.1.1 (#1016) --- Program_Licenses.md | 1 + README.md | 1 + assembly_snptyper/0.1.1/Dockerfile | 109 +++++++++++++++++++++++++++++ assembly_snptyper/0.1.1/README.md | 34 +++++++++ 4 files changed, 145 insertions(+) create mode 100644 assembly_snptyper/0.1.1/Dockerfile create mode 100644 assembly_snptyper/0.1.1/README.md diff --git a/Program_Licenses.md b/Program_Licenses.md index 1479c2fd6..8bb262fe0 100644 --- a/Program_Licenses.md +++ b/Program_Licenses.md @@ -13,6 +13,7 @@ The licenses of the open-source software that is contained in these Docker image | artic-ncov2019-epi2me | MPL 2.0 | https://github.com/epi2me-labs/wf-artic/blob/master/LICENSE | | any2fasta | GNU GPLv3 | https://github.com/tseemann/any2fasta/blob/master/LICENSE | | ARIBA | GNU GPLv3 | https://github.com/sanger-pathogens/ariba/blob/master/LICENSE | +| assembly_snptyper | MIT | https://github.com/boasvdp/assembly_snptyper/blob/main/LICENSE | | Augur | GNU Affero GPLv3 | https://github.com/nextstrain/augur/blob/master/LICENSE.txt | | Auspice | GNU Affero GPLv3 | https://github.com/nextstrain/auspice/blob/master/LICENSE.txt | | Bakta | GNU GPLv3 | https://github.com/oschwengers/bakta/blob/main/LICENSE | diff --git a/README.md b/README.md index 584bf2ff7..9b9a4a963 100644 --- a/README.md +++ b/README.md @@ -119,6 +119,7 @@ To learn more about the docker pull rate limits and the open source software pro | [artic-ncov2019-epi2me](https://hub.docker.com/r/staphb/artic-ncov2019-epi2me)
[![docker pulls](https://badgen.net/docker/pulls/staphb/artic-ncov2019-epi2me)](https://hub.docker.com/r/staphb/artic-ncov2019-epi2me) |
  • 0.3.10
| https://github.com/epi2me-labs/wf-artic | | [artic-ncov2019-medaka](https://hub.docker.com/r/staphb/artic-ncov2019-medaka)
[![docker pulls](https://badgen.net/docker/pulls/staphb/artic-ncov2019-medaka)](https://hub.docker.com/r/staphb/artic-ncov2019-medaka) |
  • 1.1.0
| https://github.com/artic-network/artic-ncov2019 | | [artic-ncov2019-nanopolish](https://hub.docker.com/r/staphb/artic-ncov2019-nanopolish)
[![docker pulls](https://badgen.net/docker/pulls/staphb/artic-ncov2019-nanopolish)](https://hub.docker.com/r/staphb/artic-ncov2019-nanopolish) |
  • 1.1.0
| https://github.com/artic-network/artic-ncov2019 | +| [assembly_snptyper](https://hub.docker.com/r/staphb/assembly_snptyperh)
[![docker pulls](https://badgen.net/docker/pulls/staphb/assembly_snptyper)](https://hub.docker.com/r/staphb/assembly_snptyper) |
  • [0.1.1](./assembly_snptyper/0.1.1/)
| https://github.com/boasvdp/assembly_snptyper | | [Augur](https://hub.docker.com/r/staphb/augur)
[![docker pulls](https://badgen.net/docker/pulls/staphb/augur)](https://hub.docker.com/r/staphb/augur) |
  • [6.3.0](./augur/6.3.0/)
  • [7.0.2](./augur/7.0.2/)
  • [8.0.0](./augur/8.0.0/)
  • [9.0.0](./augur/9.0.0/)
  • [16.0.3](./augur/16.0.3/)
  • [24.2.2](./augur/24.2.2/)
  • [24.2.3](./augur/24.2.3/)
  • [24.3.0](./augur/24.3.0/)
  • [24.4.0](./augur/24.4.0/)
| https://github.com/nextstrain/augur | | [Auspice](https://hub.docker.com/r/staphb/auspice)
[![docker pulls](https://badgen.net/docker/pulls/staphb/auspice)](https://hub.docker.com/r/staphb/auspice) |
  • 2.12.0
| https://github.com/nextstrain/auspice | | [bakta](https://hub.docker.com/r/staphb/bakta)
[![docker pulls](https://badgen.net/docker/pulls/staphb/bakta)](https://hub.docker.com/r/staphb/bakta) |
  • [1.9.2](./bakta/1.9.2/)
  • [1.9.2-light](./bakta/1.9.2-5.1-light/)
  • [1.9.3](./bakta/1.9.3/)
  • [1.9.3-light](./bakta/1.9.3-5.1-light/)
  • [1.9.4](./bakta/1.9.4/)
| https://github.com/oschwengers/bakta | diff --git a/assembly_snptyper/0.1.1/Dockerfile b/assembly_snptyper/0.1.1/Dockerfile new file mode 100644 index 000000000..5f19ebdf5 --- /dev/null +++ b/assembly_snptyper/0.1.1/Dockerfile @@ -0,0 +1,109 @@ +ARG ASSEMBLYSNPTYPER_VER="0.1.1" +ARG SAMTOOLS_VER="1.19" +ARG MINIMAP2_VER="2.28" + +FROM ubuntu:jammy as builder + +ARG SAMTOOLS_VER +ARG MINIMAP2_VER + +# install dependencies required for compiling samtools +RUN apt-get update && apt-get install --no-install-recommends -y \ + libncurses5-dev \ + libbz2-dev \ + liblzma-dev \ + libcurl4-gnutls-dev \ + zlib1g-dev \ + libssl-dev \ + gcc \ + wget \ + make \ + perl \ + bzip2 \ + gnuplot \ + ca-certificates \ + curl + +# download, compile, and install samtools +RUN wget https://github.com/samtools/samtools/releases/download/${SAMTOOLS_VER}/samtools-${SAMTOOLS_VER}.tar.bz2 && \ + tar -xjf samtools-${SAMTOOLS_VER}.tar.bz2 && \ + cd samtools-${SAMTOOLS_VER} && \ + ./configure && \ + make && \ + make install + +WORKDIR /usr/local/bin + +RUN curl -L https://github.com/lh3/minimap2/releases/download/v${MINIMAP2_VER}/minimap2-${MINIMAP2_VER}_x64-linux.tar.bz2 | tar -jxvf - --no-same-owner + +### start of app stage ### +FROM ubuntu:jammy as app + +ARG ASSEMBLYSNPTYPER_VER="0.1.1" + +# 'LABEL' instructions tag the image with metadata that might be important to the user +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="assembly_snptyper" +LABEL software.version="${ASSEMBLYSNPTYPER_VER}" +LABEL description="Type assembly based on a VCF using minimap2 + samtools" +LABEL website="https://github.com/boasvdp/assembly_snptyper" +LABEL license="https://github.com/boasvdp/assembly_snptyper/blob/main/LICENSE" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" + +ARG DEBIAN_FRONTEND=noninteractive +RUN apt-get update && apt-get install --no-install-recommends -y \ + perl \ + zlib1g \ + libncurses5 \ + bzip2 \ + liblzma-dev \ + libcurl4-gnutls-dev \ + wget \ + ca-certificates \ + procps \ + python3 \ + python3-pip \ + python-is-python3 \ + curl \ + unzip \ + && apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# copy in samtools and minimap2 executables from builder stage +COPY --from=builder /usr/local/bin/* /usr/local/bin/ + +RUN pip install pandas + +# install assembly_snptyper; make /data dir +RUN wget -q https://github.com/boasvdp/assembly_snptyper/archive/refs/tags/v${ASSEMBLYSNPTYPER_VER}.tar.gz && \ + pip install --no-cache-dir v${ASSEMBLYSNPTYPER_VER}.tar.gz && \ + tar -vxf v${ASSEMBLYSNPTYPER_VER}.tar.gz && \ + mv /assembly_snptyper-${ASSEMBLYSNPTYPER_VER} /assembly_snptyper && \ + rm v${ASSEMBLYSNPTYPER_VER}.tar.gz && \ + mkdir /data + +ENV LC_ALL=C + +CMD [ "assembly_snptyper", "--help" ] + +# 'WORKDIR' sets working directory +WORKDIR /data + +# A second FROM insruction creates a new stage +FROM app as test + +RUN assembly_snptyper --help && \ + assembly_snptyper --version + +WORKDIR /test + +# running on S. pyogenes representative genome +RUN wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/900/475/035/GCA_900475035.1_41965_F01/GCA_900475035.1_41965_F01_genomic.fna.gz && \ + gunzip GCA_900475035.1_41965_F01_genomic.fna.gz && \ + ls *genomic.fna > fastas.txt && \ + assembly_snptyper --list_input fastas.txt -p 4 --reference /assembly_snptyper/data/MGAS5005.fa --vcf /assembly_snptyper/data/M1UK.vcf > m1uk.txt && \ + head m1uk.txt + +RUN cd /assembly_snptyper && \ + bash tests/test_e2e.sh \ No newline at end of file diff --git a/assembly_snptyper/0.1.1/README.md b/assembly_snptyper/0.1.1/README.md new file mode 100644 index 000000000..bf0137750 --- /dev/null +++ b/assembly_snptyper/0.1.1/README.md @@ -0,0 +1,34 @@ +# assembly_snptyper container + +Main tool: [assembly_snptyper](https://github.com/boasvdp/assembly_snptyper) + +Code repository: https://github.com/boasvdp/assembly_snptyper + +Additional tools: +- samtools: 1.19 +- minimap2: 2.28 + +Basic information on how to use this tool: +- executable: assembly_snptyper +- help: -h +- version: -v +- description: | + +> This software can take a bacterial genome assembly in fasta format, align it to a reference genome and search for specific SNPs based on the alignment. It uses minimap2 and samtools to do this. You would typically only run this tool instead of a read mapping tool if you don't have access to the sequence reads. + + +> The tool was written with M1UK typing in mind. In this specific case, the reference genome is an M1global strain, from which M1UK can be discerned by only 27 lineage-specific SNPs. Important assumptions here are that the type of interest (here, M1UK) is closely related to the reference genome, warranting the use of the asm5 preset for minimap2. + +Additional information: + +M1UK reference and SNP vcf are located in /assembly_snptyper/data + +Full documentation: https://github.com/boasvdp/assembly_snptyper + +## Example Usage + +```bash +# with a list of fasta files listed in fastas.txt +assembly_snptyper --list_input fastas.txt -p 20 --reference /assembly_snptyper/data/MGAS5005.fa --vcf /assembly_snptyper/data/M1UK.vcf > m1uk.txt +``` + From fbb0b10625094a1822d16ce6bc49c2b60e5b4325 Mon Sep 17 00:00:00 2001 From: Young Date: Mon, 30 Sep 2024 09:41:07 -0600 Subject: [PATCH 18/92] adding iqtree2 version 2.3.6 (#1061) --- README.md | 2 +- iqtree2/2.3.6/Dockerfile | 52 ++++++++++++++++++++++++++++++++++++++++ iqtree2/2.3.6/README.md | 28 ++++++++++++++++++++++ 3 files changed, 81 insertions(+), 1 deletion(-) create mode 100644 iqtree2/2.3.6/Dockerfile create mode 100644 iqtree2/2.3.6/README.md diff --git a/README.md b/README.md index 9b9a4a963..ed883044d 100644 --- a/README.md +++ b/README.md @@ -180,7 +180,7 @@ To learn more about the docker pull rate limits and the open source software pro | [homopolish](https://hub.docker.com/r/staphb/homopolish)
[![docker pulls](https://badgen.net/docker/pulls/staphb/homopolish)](https://hub.docker.com/r/staphb/homopolish) |
  • 0.4.1
| https://github.com/ythuang0522/homopolish/ | | [htslib](https://hub.docker.com/r/staphb/htslib)
[![docker pulls](https://badgen.net/docker/pulls/staphb/htslib)](https://hub.docker.com/r/staphb/htslib) |
  • [1.14](./htslib/1.14)
  • [1.15](./htslib/1.15)
  • [1.16](./htslib/1.16)
  • [1.17](./htslib/1.17)
  • [1.18](./htslib/1.18/)
  • [1.19](./htslib/1.19/)
  • [1.20](./htslib/1.20/)
  • [1.20.c](./htslib/1.20.c/)
  • [1.21](./htslib/1.21/)
| https://www.htslib.org/ | | [iqtree](https://hub.docker.com/r/staphb/iqtree/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/iqtree)](https://hub.docker.com/r/staphb/iqtree) |
  • 1.6.7
| http://www.iqtree.org/ | -| [iqtree2](https://hub.docker.com/r/staphb/iqtree2/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/iqtree2)](https://hub.docker.com/r/staphb/iqtree2) |
  • 2.1.2
  • 2.2.2.2
  • [2.2.2.6](iqtree2/2.2.2.6/)
  • [2.2.2.7](iqtree2/2.2.2.7/)
  • [2.3.1](iqtree2/2.3.1/)
  • [2.3.4](iqtree2/2.3.4/)
| http://www.iqtree.org/ | +| [iqtree2](https://hub.docker.com/r/staphb/iqtree2/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/iqtree2)](https://hub.docker.com/r/staphb/iqtree2) |
  • 2.1.2
  • 2.2.2.2
  • [2.2.2.6](iqtree2/2.2.2.6/)
  • [2.2.2.7](iqtree2/2.2.2.7/)
  • [2.3.1](iqtree2/2.3.1/)
  • [2.3.4](iqtree2/2.3.4/)
  • [2.3.6](iqtree2/2.3.6/)
| http://www.iqtree.org/ | | [IPA](https://hub.docker.com/r/staphb/pbipa)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pbipa)](https://hub.docker.com/r/staphb/pbipa) |
  • [1.8.0](./pbipa/1.8.0/)
| https://github.com/PacificBiosciences/pbipa | | [IRMA](https://hub.docker.com/r/staphb/irma/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/irma)](https://hub.docker.com/r/staphb/irma) |
  • 1.0.2
  • 1.0.3
  • 1.1.2
  • 1.1.3
  • [1.1.4](./irma/1.1.4/)
| https://wonder.cdc.gov/amd/flu/irma/| | [isPcr](https://users.soe.ucsc.edu/~kent/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ispcr)](https://hub.docker.com/r/staphb/ispcr) |
  • [33](ispcr/33/)
| https://users.soe.ucsc.edu/~kent/ | diff --git a/iqtree2/2.3.6/Dockerfile b/iqtree2/2.3.6/Dockerfile new file mode 100644 index 000000000..e652ef886 --- /dev/null +++ b/iqtree2/2.3.6/Dockerfile @@ -0,0 +1,52 @@ +ARG IQTREE2_VER="2.3.6" + +FROM ubuntu:jammy as app + +# for easy upgrade later. ARG variables only persist during build time. +ARG IQTREE2_VER + +# metadata +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="IQ-Tree2" +LABEL software.version="${IQTREE2_VER}" +LABEL description="Efficient software for phylogenomic inference" +LABEL website="http://www.iqtree.org/" +LABEL source.code.website="https://github.com/iqtree/iqtree2" +LABEL license="https://github.com/iqtree/iqtree2/blob/master/LICENSE" +LABEL maintainer="Jade Wang" +LABEL maintainer.email="jwang7@health.nyc.gov" +LABEL maintainer2="Erin Young" +LABEL maintainer2.email="eriny@utah.gov" + +#install dependencies +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget ca-certificates procps && \ + apt-get autoclean && \ + rm -rf /var/lib/apt/lists/* + +# download, uncompress iqtree2 tarball; make /data +RUN wget -q https://github.com/iqtree/iqtree2/releases/download/v${IQTREE2_VER}/iqtree-${IQTREE2_VER}-Linux-intel.tar.gz && \ + tar -xvf iqtree-${IQTREE2_VER}-Linux-intel.tar.gz && \ + rm -v iqtree-${IQTREE2_VER}-Linux-intel.tar.gz && \ + mkdir /data + +# set PATH and locale settings for singularity compatibility +ENV PATH="/iqtree-${IQTREE2_VER}-Linux-intel/bin:${PATH}"\ + LC_ALL=C + +# final working directory is /data +WORKDIR /data + +# default command is to pull up help options +CMD [ "iqtree2", "--help" ] + +FROM app as test + +ARG IQTREE2_VER + +# print version and help +RUN iqtree2 --version && iqtree2 --help + +###TEST TREE TOPOLOGY +RUN iqtree2 -s /iqtree-${IQTREE2_VER}-Linux-intel/example.phy --rate diff --git a/iqtree2/2.3.6/README.md b/iqtree2/2.3.6/README.md new file mode 100644 index 000000000..4c53969e5 --- /dev/null +++ b/iqtree2/2.3.6/README.md @@ -0,0 +1,28 @@ +# IQ-TREE2 container + +Main tool : [iqtree2](https://github.com/iqtree/iqtree2) + +Full documentation: [https://github.com/rrwick/Polypolish/wiki](http://www.iqtree.org/doc/) + +| Efficient and versatile phylogenomic software by maximum likelihood + +## Example Usage + +An example phylip file (IQ-TREE2 also supports other file formats such as FASTA, NEXUS, CLUSTALW) + +``` +7 28 +Frog AAATTTGGTCCTGTGATTCAGCAGTGAT +Turtle CTTCCACACCCCAGGACTCAGCAGTGAT +Bird CTACCACACCCCAGGACTCAGCAGTAAT +Human CTACCACACCCCAGGAAACAGCAGTGAT +Cow CTACCACACCCCAGGAAACAGCAGTGAC +Whale CTACCACGCCCCAGGACACAGCAGTGAT +Mouse CTACCACACCCCAGGACTCAGCAGTGAT +``` + +Can be aligned with the following command: + +```bash +iqtree2 -s example.phy --redo +``` From 195539ab8057c6ec7076ab47b40ef76ddbd2eaf4 Mon Sep 17 00:00:00 2001 From: Fraser Combe Date: Mon, 30 Sep 2024 10:49:15 -0500 Subject: [PATCH 19/92] Add Dorado 0.8.0 (#1051) * Add Dorado 0.8.0 Dockerfile and README * PR changes dorado * Update Program_Licenses.md * Update README.md * clarified section on test POD5 file --------- Co-authored-by: Curtis Kapsak --- Program_Licenses.md | 1 + README.md | 4 + dorado/0.8.0/Dockerfile | 64 ++++++++++++ dorado/0.8.0/README.md | 219 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 288 insertions(+) create mode 100755 dorado/0.8.0/Dockerfile create mode 100644 dorado/0.8.0/README.md diff --git a/Program_Licenses.md b/Program_Licenses.md index 8bb262fe0..398acb32e 100644 --- a/Program_Licenses.md +++ b/Program_Licenses.md @@ -39,6 +39,7 @@ The licenses of the open-source software that is contained in these Docker image | datasets-sars-cov-2 | Apache 2.0 | https://github.com/CDCgov/datasets-sars-cov-2/blob/master/LICENSE | | diamond | GNU GPLv3 | https://github.com/bbuchfink/diamond/blob/master/LICENSE | | dnaapler | MIT | https://github.com/gbouras13/dnaapler/blob/main/LICENSE | +| dorado | Oxford Nanopore Technologies PLC Public License | [ONT License](https://github.com/nanoporetech/dorado/blob/master/LICENCE.txt) | | dragonflye | GNU GPLv3 | https://github.com/rpetit3/dragonflye/blob/main/LICENSE | | drprg | MIT | https://github.com/mbhall88/drprg/blob/main/LICENSE | | DSK | GNU Affero GPLv3 | https://github.com/GATB/dsk/blob/master/LICENSE | diff --git a/README.md b/README.md index ed883044d..508a1dcaa 100644 --- a/README.md +++ b/README.md @@ -149,6 +149,7 @@ To learn more about the docker pull rate limits and the open source software pro | [datasets-sars-cov-2](https://github.com/CDCgov/datasets-sars-cov-2)
[![docker pulls](https://badgen.net/docker/pulls/staphb/datasets-sars-cov-2)](https://hub.docker.com/r/staphb/datasets-sars-cov-2) |
  • 0.6.2
  • 0.6.3
  • 0.7.2
| https://github.com/CDCgov/datasets-sars-cov-2 | | [diamond](https://github.com/bbuchfink/diamond)
[![docker pulls](https://badgen.net/docker/pulls/staphb/diamond)](https://hub.docker.com/r/staphb/diamond) |
  • [2.1.9](./diamond/2.1.9)
| https://github.com/bbuchfink/diamond| | [dnaapler](https://hub.docker.com/r/staphb/dnaapler)
[![docker pulls](https://badgen.net/docker/pulls/staphb/dnaapler)](https://hub.docker.com/r/staphb/dnaapler) |
  • [0.1.0](dnaapler/0.1.0/)
  • [0.4.0](dnaapler/0.4.0/)
  • [0.5.0](dnaapler/0.5.0/)
  • [0.5.1](dnaapler/0.5.1/)
  • [0.7.0](dnaapler/0.7.0/)
  • [0.8.0](dnaapler/0.8.0/)
| https://github.com/gbouras13/dnaapler | +| [dorado](https://hub.docker.com/r/staphb/dorado)
[![docker pulls](https://badgen.net/docker/pulls/staphb/dorado)](https://hub.docker.com/r/staphb/dorado) |
  • [0.8.0](dorado/0.8.0/)
| [https://github.com/nanoporetech/dorado](https://github.com/nanoporetech/dorado) | | [dragonflye](https://hub.docker.com/r/staphb/dragonflye)
[![docker pulls](https://badgen.net/docker/pulls/staphb/dragonflye)](https://hub.docker.com/r/staphb/dragonflye) |
  • [1.0.14](./dragonflye/1.0.14/)
  • [1.1.1](./dragonflye/1.1.1/)
  • [1.1.2](./dragonflye/1.1.2/)
  • [1.2.0](./dragonflye/1.2.0/)
  • [1.2.1](./dragonflye/1.2.1/)
| https://github.com/rpetit3/dragonflye | | [Dr. PRG ](https://hub.docker.com/r/staphb/drprg)
[![docker pulls](https://badgen.net/docker/pulls/staphb/drprg)](https://hub.docker.com/r/staphb/drprg) |
  • [0.1.1](drprg/0.1.1/)
| https://mbh.sh/drprg/ | | [DSK](https://hub.docker.com/r/staphb/dsk)
[![docker pulls](https://badgen.net/docker/pulls/staphb/dsk)](https://hub.docker.com/r/staphb/dsk) |
  • [0.0.100](./dsk/0.0.100/)
  • [2.3.3](./dsk/2.3.3/)
| https://gatb.inria.fr/software/dsk/ | @@ -376,3 +377,6 @@ Each Dockerfile lists the author(s)/maintainer(s) as a metadata `LABEL`, but the * [@stephenturner](https://github.com/stephenturner) * [@soejun](https://github.com/soejun) * [@taylorpaisie](https://github.com/taylorpaisie) + * [@fraser-combe](https://github.com/fraser-combe) + + diff --git a/dorado/0.8.0/Dockerfile b/dorado/0.8.0/Dockerfile new file mode 100755 index 000000000..523efa26f --- /dev/null +++ b/dorado/0.8.0/Dockerfile @@ -0,0 +1,64 @@ +# Use NVIDIA CUDA image as the base image +FROM nvidia/cuda:12.2.0-devel-ubuntu20.04 AS app + +ARG DORADO_VER=0.8.0 + +# Metadata +LABEL base.image="nvidia/cuda:12.2.0-devel-ubuntu20.04" +LABEL dockerfile.version="1" +LABEL software="dorado ${DORADO_VER}" +LABEL software.version="${DORADO_VER}" +LABEL description="A tool for basecalling Fast5/Pod5 files from Oxford Nanopore sequencing" +LABEL website="https://github.com/nanoporetech/dorado" +LABEL license="https://github.com/nanoporetech/dorado/blob/master/LICENSE" +LABEL original.website="https://nanoporetech.github.io/dorado/" +LABEL maintainer="Fraser Combe" +LABEL maintainer.email="fraser.combe@theiagen.com" + +# Set working directory +WORKDIR /usr/src/app + +# Install dependencies +RUN apt-get update && \ + apt-get install -y --no-install-recommends wget ca-certificates && \ + rm -rf /var/lib/apt/lists/* && apt-get autoclean + +# Download and extract Dorado package +RUN wget https://cdn.oxfordnanoportal.com/software/analysis/dorado-${DORADO_VER}-linux-x64.tar.gz \ + && tar -xzvf dorado-${DORADO_VER}-linux-x64.tar.gz -C /opt \ + && rm dorado-${DORADO_VER}-linux-x64.tar.gz + +# Set environment variables for Dorado binary +ENV PATH="/opt/dorado-${DORADO_VER}-linux-x64/bin:${PATH}" + +# Download basecalling models +RUN mkdir /dorado_models && \ + cd /dorado_models && \ + dorado download --model all + +# Default command +CMD ["dorado"] + +# ----------------------------- +# Test Stage +# ----------------------------- +FROM app AS test + + +# Download the specific Pod5 test file +RUN wget -O /usr/src/app/dna_r10.4.1_e8.2_260bps-FLO_PRO114-SQK_NBD114_96_260-4000.pod5 \ + https://github.com/nanoporetech/dorado/raw/release-v0.7/tests/data/pod5/dna_r10.4.1_e8.2_260bps/\ +dna_r10.4.1_e8.2_260bps-FLO_PRO114-SQK_NBD114_96_260-4000.pod5 + +# Set working directory +WORKDIR /usr/src/app + +# Run test command (using CPU mode) +RUN dorado basecaller \ + --device cpu \ + /dorado_models/dna_r10.4.1_e8.2_260bps_sup@v3.5.2 \ + dna_r10.4.1_e8.2_260bps-FLO_PRO114-SQK_NBD114_96_260-4000.pod5 \ + --emit-moves --max-reads 10 > basecalled.sam + +# Verify the output file exists and is not empty +RUN test -s basecalled.sam diff --git a/dorado/0.8.0/README.md b/dorado/0.8.0/README.md new file mode 100644 index 000000000..9267d7ce5 --- /dev/null +++ b/dorado/0.8.0/README.md @@ -0,0 +1,219 @@ +# Dorado Docker Image + +This Dockerfile sets up an environment for running **Dorado**, a tool for basecalling Fast5/Pod5 files from Oxford Nanopore sequencing. + +## Table of Contents + +- [Introduction](#introduction) +- [Requirements](#requirements) +- [Building the Docker Image](#building-the-docker-image) +- [Running the Docker Container](#running-the-docker-container) +- [Testing the Docker Image](#testing-the-docker-image) +- [Basecalling Test](#basecalling-test) +- [Verifying the Output](#verifying-the-output) +- [Additional Notes](#additional-notes) +- [License](#license) + +## Introduction + +This Docker image includes: + +- **Dorado**: Version **0.8.0**, a tool for basecalling Oxford Nanopore sequencing data. +- **NVIDIA CUDA**: Version **12.2.0**, for GPU acceleration (requires NVIDIA GPU). +- **Pre-downloaded basecalling models**: All models are downloaded during the build process for basecalling. + +## Requirements + +- **Docker**: Installed on your system. +- **NVIDIA GPU and Drivers**: Installed and configured. +- **NVIDIA Container Toolkit**: To enable GPU support in Docker containers. + +## Running the Docker Container + +To run the Dorado tool within the Docker container, use the following command: + +```bash +docker run --gpus all -it dorado-image dorado --help +``` + +This command will display the help information for Dorado, confirming that it's installed correctly. + +## Testing the Docker Image + +To test that Dorado is working correctly, you will need to download a sample Pod5 file and perform a basecalling operation using the pre-downloaded basecalling models. + +```bash +wget -O dna_r10.4.1_e8.2_260bps-FLO_PRO114-SQK_NBD114_96_260-4000.pod5 \ + https://github.com/nanoporetech/dorado/raw/release-v0.7/tests/data/pod5/dna_r10.4.1_e8.2_260bps/dna_r10.4.1_e8.2_260bps-FLO_PRO114-SQK_NBD114_96_260-4000.pod5 + +### Basecalling Test + +Run the following command: + +```bash +docker run --gpus all -v $(pwd):/usr/src/app -it dorado-image bash -c "\ + dorado basecaller /dorado_models/dna_r10.4.1_e8.2_260bps_sup@v3.5.2 \ + /usr/src/app/dna_r10.4.1_e8.2_260bps-FLO_PRO114-SQK_NBD114_96_260-4000.pod5 \ + --emit-moves > /usr/src/app/basecalled.sam" +``` + +**Explanation:** + +- `--gpus all`: Enables GPU support. +- `-v $(pwd):/usr/src/app`: Mounts the current directory to `/usr/src/app` inside the container. +- `bash -c "...":` Runs the basecalling command inside the container. +- `> /usr/src/app/basecalled.sam`: Redirects the output to `basecalled.sam` in your current directory. + +### Verifying the Output + +Check the output file to ensure basecalling was successful: + +```bash +samtools view basecalled.sam +``` + +You should see SAM-formatted basecalling results. + +## Additional Notes + +- **Sample Data**: The sample Pod5 file is downloaded to `/usr/src/app` during the docker image build. + - _Note: If you are using the pre-built StaPH-B docker image downloaded from dockerhub or quay.io, it will only include the `app` stage. This means that the sample Pod5 file will not be available in the container. You will need to download the sample Pod5 file manually using the `wget` example command shown above._ +- **Internal Testing**: An internal test stage is included in the Dockerfile to verify installation. +- **Basecalling Models**: All models are downloaded to `/dorado_models` during the build process. + Below is the list of basecalling models included in the Docker image: + ```yaml + + modification models: + - "dna_r9.4.1_e8_fast@v3.4_5mCG@v0.1" + - "dna_r9.4.1_e8_hac@v3.3_5mCG@v0.1" + - "dna_r9.4.1_e8_sup@v3.3_5mCG@v0.1" + - "dna_r9.4.1_e8_fast@v3.4_5mCG_5hmCG@v0" + - "dna_r9.4.1_e8_hac@v3.3_5mCG_5hmCG@v0" + - "dna_r9.4.1_e8_sup@v3.3_5mCG_5hmCG@v0" + - "dna_r10.4.1_e8.2_260bps_fast@v3.5.2_5mCG@v2" + - "dna_r10.4.1_e8.2_260bps_hac@v3.5.2_5mCG@v2" + - "dna_r10.4.1_e8.2_260bps_sup@v3.5.2_5mCG@v2" + - "dna_r10.4.1_e8.2_400bps_fast@v3.5.2_5mCG@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v3.5.2_5mCG@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v3.5.2_5mCG@v2" + - "dna_r10.4.1_e8.2_260bps_fast@v4.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_260bps_hac@v4.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_260bps_sup@v4.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_fast@v4.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v4.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_260bps_fast@v4.1.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_260bps_hac@v4.1.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_260bps_sup@v4.1.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_fast@v4.1.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v4.1.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.1.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_fast@v4.2.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v4.2.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0_5mCG_5hmCG@v3.1" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0_5mC@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0_6mA@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0_6mA@v3" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0_5mC_5hmC@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v4.3.0_5mC_5hmC@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v4.3.0_5mC_5hmC@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v4.3.0_6mA@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v4.3.0_6mA@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v4.3.0_6mA@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.3.0_6mA@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v4.3.0_5mCG_5hmCG@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v4.3.0_5mCG_5hmCG@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_4mC_5mC@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_4mC_5mC@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_4mC_5mC@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_4mC_5mC@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_5mC_5hmC@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_5mC_5hmC@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_5mC_5hmC@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_5mC_5hmC@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_5mCG_5hmCG@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_5mCG_5hmCG@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_6mA@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_6mA@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_6mA@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_6mA@v2" + - "rna004_130bps_sup@v3.0.1_m6A_DRACH@v1" + - "rna004_130bps_hac@v5.0.0_m6A@v1" + - "rna004_130bps_sup@v5.0.0_m6A@v1" + - "rna004_130bps_hac@v5.0.0_m6A_DRACH@v1" + - "rna004_130bps_sup@v5.0.0_m6A_DRACH@v1" + - "rna004_130bps_hac@v5.0.0_pseU@v1" + - "rna004_130bps_sup@v5.0.0_pseU@v1" + - "rna004_130bps_hac@v5.1.0_m5C@v1" + - "rna004_130bps_sup@v5.1.0_m5C@v1" + - "rna004_130bps_hac@v5.1.0_inosine_m6A@v1" + - "rna004_130bps_sup@v5.1.0_inosine_m6A@v1" + - "rna004_130bps_hac@v5.1.0_m6A_DRACH@v1" + - "rna004_130bps_sup@v5.1.0_m6A_DRACH@v1" + - "rna004_130bps_hac@v5.1.0_pseU@v1" + - "rna004_130bps_sup@v5.1.0_pseU@v1" + stereo models: + - "dna_r10.4.1_e8.2_4khz_stereo@v1.1" + - "dna_r10.4.1_e8.2_4khz_stereo@v1.1" + - "dna_r10.4.1_e8.2_5khz_stereo@v1.1" + - "dna_r10.4.1_e8.2_5khz_stereo@v1.2" + - "dna_r10.4.1_e8.2_5khz_stereo@v1.3" + simplex models: + - "dna_r9.4.1_e8_fast@v3.4" + - "dna_r9.4.1_e8_hac@v3.3" + - "dna_r9.4.1_e8_sup@v3.3" + - "dna_r9.4.1_e8_sup@v3.6" + - "dna_r10.4.1_e8.2_260bps_fast@v3.5.2" + - "dna_r10.4.1_e8.2_260bps_hac@v3.5.2" + - "dna_r10.4.1_e8.2_260bps_sup@v3.5.2" + - "dna_r10.4.1_e8.2_400bps_fast@v3.5.2" + - "dna_r10.4.1_e8.2_400bps_hac@v3.5.2" + - "dna_r10.4.1_e8.2_400bps_sup@v3.5.2" + - "dna_r10.4.1_e8.2_260bps_fast@v4.0.0" + - "dna_r10.4.1_e8.2_260bps_hac@v4.0.0" + - "dna_r10.4.1_e8.2_260bps_sup@v4.0.0" + - "dna_r10.4.1_e8.2_400bps_fast@v4.0.0" + - "dna_r10.4.1_e8.2_400bps_hac@v4.0.0" + - "dna_r10.4.1_e8.2_400bps_sup@v4.0.0" + - "dna_r10.4.1_e8.2_260bps_fast@v4.1.0" + - "dna_r10.4.1_e8.2_260bps_hac@v4.1.0" + - "dna_r10.4.1_e8.2_260bps_sup@v4.1.0" + - "dna_r10.4.1_e8.2_400bps_fast@v4.1.0" + - "dna_r10.4.1_e8.2_400bps_hac@v4.1.0" + - "dna_r10.4.1_e8.2_400bps_sup@v4.1.0" + - "dna_r10.4.1_e8.2_400bps_fast@v4.2.0" + - "dna_r10.4.1_e8.2_400bps_hac@v4.2.0" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0" + - "dna_r10.4.1_e8.2_400bps_fast@v4.3.0" + - "dna_r10.4.1_e8.2_400bps_hac@v4.3.0" + - "dna_r10.4.1_e8.2_400bps_sup@v4.3.0" + - "dna_r10.4.1_e8.2_400bps_fast@v5.0.0" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0" + - "dna_r10.4.1_e8.2_apk_sup@v5.0.0" + - "rna002_70bps_fast@v3" + - "rna002_70bps_hac@v3" + - "rna004_130bps_fast@v3.0.1" + - "rna004_130bps_hac@v3.0.1" + - "rna004_130bps_sup@v3.0.1" + - "rna004_130bps_fast@v5.0.0" + - "rna004_130bps_hac@v5.0.0" + - "rna004_130bps_sup@v5.0.0" + - "rna004_130bps_fast@v5.1.0" + - "rna004_130bps_hac@v5.1.0" + - "rna004_130bps_sup@v5.1.0" + ``` + +## License + +Dorado is licensed under [Oxford Nanopore Technologies' License](https://github.com/nanoporetech/dorado/blob/master/LICENSE). + + +--- + +**Note**: Please ensure that you have the necessary NVIDIA drivers and the NVIDIA Container Toolkit installed to utilize GPU acceleration. + +--- From 1cc13c1e97e1a8ae2124f1613f30cb4f6aa142d1 Mon Sep 17 00:00:00 2001 From: Young Date: Mon, 30 Sep 2024 09:52:52 -0600 Subject: [PATCH 20/92] adding samtools version 1.21 (#1068) * adding samtools version 1.21 * Update README.md v1.20 -> v1.21 --------- Co-authored-by: Kutluhan Incekara <46578029+Kincekara@users.noreply.github.com> --- samtools/1.21/Dockerfile | 100 +++++++++++++++++++++++++++++++++++++++ samtools/1.21/README.md | 30 ++++++++++++ 2 files changed, 130 insertions(+) create mode 100644 samtools/1.21/Dockerfile create mode 100644 samtools/1.21/README.md diff --git a/samtools/1.21/Dockerfile b/samtools/1.21/Dockerfile new file mode 100644 index 000000000..8b7be7bd7 --- /dev/null +++ b/samtools/1.21/Dockerfile @@ -0,0 +1,100 @@ +ARG SAMTOOLS_VER="1.21" + +FROM ubuntu:jammy as builder + +ARG SAMTOOLS_VER + +# install dependencies required for compiling samtools +RUN apt-get update && apt-get install --no-install-recommends -y \ + libncurses5-dev \ + libbz2-dev \ + liblzma-dev \ + libcurl4-gnutls-dev \ + zlib1g-dev \ + libssl-dev \ + libdeflate-dev \ + gcc \ + wget \ + make \ + perl \ + bzip2 \ + gnuplot \ + ca-certificates + +# download, compile, and install samtools +RUN wget -q https://github.com/samtools/samtools/releases/download/${SAMTOOLS_VER}/samtools-${SAMTOOLS_VER}.tar.bz2 && \ + tar -xjf samtools-${SAMTOOLS_VER}.tar.bz2 && \ + cd samtools-${SAMTOOLS_VER} && \ + ./configure && \ + make && \ + make install && \ + make test + +### start of app stage ### +FROM ubuntu:jammy as app + +ARG SAMTOOLS_VER + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="samtools" +LABEL software.version="${SAMTOOLS_VER}" +LABEL description="Tools (written in C using htslib) for manipulating next-generation sequencing data" +LABEL website="https://github.com/samtools/samtools" +LABEL license="https://github.com/samtools/samtools/blob/develop/LICENSE" +LABEL maintainer="Shelby Bennett" +LABEL maintainer.email="shelby.bennett@dgs.virginia.gov" +LABEL maintainer2="Curtis Kapsak" +LABEL maintainer2.email="kapsakcj@gmail.com" +LABEL maintainer3="Erin Young" +LABEL maintainer3.email="eriny@utah.gov" +LABEL maintainer4="Kutluhan Incekara" +LABEL maintainer4.email="kutluhan.incekara@ct.gov" + +ARG DEBIAN_FRONTEND=noninteractive + +# install dependencies required for running samtools +# 'gnuplot' required for plot-ampliconstats +RUN apt-get update && apt-get install --no-install-recommends -y \ + perl \ + zlib1g \ + libncurses5 \ + bzip2 \ + liblzma5 \ + libcurl3-gnutls \ + libdeflate0 \ + gnuplot \ + && apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# copy in samtools executables from builder stage +COPY --from=builder /usr/local/bin/* /usr/local/bin/ + +ENV LC_ALL=C + +# final working directory is /data +WORKDIR /data + +# default command is to pull up help options +CMD ["samtools", "--help"] + +### start of test stage ### +FROM app as test + +ARG SAMTOOLS_VER + +# check PATH +RUN samtools --help + +# install make and wget for downloading test files +RUN apt-get update && apt-get install --no-install-recommends -y wget ca-certificates + +WORKDIR /test + +RUN wget -q https://raw.githubusercontent.com/StaPH-B/docker-builds/master/tests/SARS-CoV-2/SRR13957123.consensus.fa && \ + wget -q https://raw.githubusercontent.com/StaPH-B/docker-builds/master/tests/SARS-CoV-2/SRR13957123.primertrim.sorted.bam && \ + wget -q https://raw.githubusercontent.com/artic-network/artic-ncov2019/master/primer_schemes/nCoV-2019/V3/nCoV-2019.primer.bed && \ + samtools stats SRR13957123.primertrim.sorted.bam && \ + samtools faidx SRR13957123.consensus.fa && \ + samtools ampliconstats nCoV-2019.primer.bed SRR13957123.primertrim.sorted.bam > SRR13957123_ampliconstats.txt && \ + plot-ampliconstats plot SRR13957123_ampliconstats.txt && \ + ls diff --git a/samtools/1.21/README.md b/samtools/1.21/README.md new file mode 100644 index 000000000..fe346b6b3 --- /dev/null +++ b/samtools/1.21/README.md @@ -0,0 +1,30 @@ +# samtools container + +Main tool: [samtools](https://www.htslib.org/) + +Code repository: https://github.com/samtools/samtools + +Additional tools: + +* perl 5.34.0 + +Basic information on how to use this tool: +- executable: samtools +- help: --help +- version: --version +- description: Utilities for the Sequence Alignment/Map (SAM) format + +Additional information: + +This container includes samtools v1.21 compiled with **libdeflate** for a better cloud performance. + +Full documentation: https://www.htslib.org/doc/samtools.html + +## Example Usage + +```bash +samtools ampliconclip -b bed.file input.bam + +samtools sort -T /tmp/aln.sorted -o aln.sorted.bam aln.bam +``` + From 799681465b098e0cf57e460bb783c33efe81aa2c Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Mon, 30 Sep 2024 13:21:47 -0400 Subject: [PATCH 21/92] cleaning and fixing up seqfu dockerfile --- seqfu/1.20.3/Dockerfile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index 85b52540d..6f1d5b9a1 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -37,13 +37,13 @@ RUN apt-get update && apt-get install -y --no-install-recommends \ WORKDIR /root # Install Nim and SeqFu -RUN curl https://nim-lang.org/choosenim/init.sh -sSf | sh -s -- -y && \ +RUN curl https://nim-lang.org/choosenim/init.sh -sSf | sh -s -- -y --ver 1.22.2 && \ wget https://github.com/telatin/seqfu2/archive/refs/tags/v${SEQFU_VER}.tar.gz && \ tar -xzf v${SEQFU_VER}.tar.gz && \ rm v${SEQFU_VER}.tar.gz && \ cd seqfu2-${SEQFU_VER} && \ make && \ - make test VERBOSE=1 || (echo "Tests failed, but continuing build"; exit 0) + /bin/bash # Start an interactive shell to manually inspect and debug tests # Copy the built binary to a location in the PATH RUN ls -l /root/seqfu2-${SEQFU_VER}/bin && \ From 8d227f9ac8a3c776648ebb7cbd8f6dca8fe66641 Mon Sep 17 00:00:00 2001 From: Young Date: Mon, 30 Sep 2024 11:33:08 -0600 Subject: [PATCH 22/92] adding bakta version 1.9.4 with light database (#1059) * adding bakta version 1.9.4 with light database * Update Dockerfile micromamba clean -a -f -y --------- Co-authored-by: Kutluhan Incekara <46578029+Kincekara@users.noreply.github.com> --- README.md | 2 +- bakta/1.9.4-5.1-light/Dockerfile | 54 ++++++++++++++++++++++++++++++++ bakta/1.9.4-5.1-light/README.md | 24 ++++++++++++++ 3 files changed, 79 insertions(+), 1 deletion(-) create mode 100644 bakta/1.9.4-5.1-light/Dockerfile create mode 100644 bakta/1.9.4-5.1-light/README.md diff --git a/README.md b/README.md index 508a1dcaa..f0c5d67ce 100644 --- a/README.md +++ b/README.md @@ -122,7 +122,7 @@ To learn more about the docker pull rate limits and the open source software pro | [assembly_snptyper](https://hub.docker.com/r/staphb/assembly_snptyperh)
[![docker pulls](https://badgen.net/docker/pulls/staphb/assembly_snptyper)](https://hub.docker.com/r/staphb/assembly_snptyper) |
  • [0.1.1](./assembly_snptyper/0.1.1/)
| https://github.com/boasvdp/assembly_snptyper | | [Augur](https://hub.docker.com/r/staphb/augur)
[![docker pulls](https://badgen.net/docker/pulls/staphb/augur)](https://hub.docker.com/r/staphb/augur) |
  • [6.3.0](./augur/6.3.0/)
  • [7.0.2](./augur/7.0.2/)
  • [8.0.0](./augur/8.0.0/)
  • [9.0.0](./augur/9.0.0/)
  • [16.0.3](./augur/16.0.3/)
  • [24.2.2](./augur/24.2.2/)
  • [24.2.3](./augur/24.2.3/)
  • [24.3.0](./augur/24.3.0/)
  • [24.4.0](./augur/24.4.0/)
| https://github.com/nextstrain/augur | | [Auspice](https://hub.docker.com/r/staphb/auspice)
[![docker pulls](https://badgen.net/docker/pulls/staphb/auspice)](https://hub.docker.com/r/staphb/auspice) |
  • 2.12.0
| https://github.com/nextstrain/auspice | -| [bakta](https://hub.docker.com/r/staphb/bakta)
[![docker pulls](https://badgen.net/docker/pulls/staphb/bakta)](https://hub.docker.com/r/staphb/bakta) |
  • [1.9.2](./bakta/1.9.2/)
  • [1.9.2-light](./bakta/1.9.2-5.1-light/)
  • [1.9.3](./bakta/1.9.3/)
  • [1.9.3-light](./bakta/1.9.3-5.1-light/)
  • [1.9.4](./bakta/1.9.4/)
| https://github.com/oschwengers/bakta | +| [bakta](https://hub.docker.com/r/staphb/bakta)
[![docker pulls](https://badgen.net/docker/pulls/staphb/bakta)](https://hub.docker.com/r/staphb/bakta) |
  • [1.9.2](./bakta/1.9.2/)
  • [1.9.2-light](./bakta/1.9.2-5.1-light/)
  • [1.9.3](./bakta/1.9.3/)
  • [1.9.3-light](./bakta/1.9.3-5.1-light/)
  • [1.9.4](./bakta/1.9.4/)
  • [1.9.4-5.1-light](./bakta/1.9.4-5.1-light/)
| https://github.com/oschwengers/bakta | | [bandage](https://hub.docker.com/r/staphb/bandage)
[![docker pulls](https://badgen.net/docker/pulls/staphb/bandage)](https://hub.docker.com/r/staphb/bandage) |
  • [0.8.1](./bandage/0.8.1/)
| https://rrwick.github.io/Bandage/ | | [BBTools](https://hub.docker.com/r/staphb/bbtools/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/bbtools)](https://hub.docker.com/r/staphb/bbtools) |
  • [38.76](./bbtools/38.76/)
  • [38.86](./bbtools/38.86/)
  • [38.95](./bbtools/38.95/)
  • [38.96](./bbtools/38.96/)
  • [38.97](./bbtools/38.97/)
  • [38.98](./bbtools/38.98/)
  • [38.99](./bbtools/38.99/)
  • [39.00](./bbtools/39.00/)
  • [39.01](./bbtools/39.01/)
  • [39.06](./bbtools/39.06/)
| https://jgi.doe.gov/data-and-tools/bbtools/ | | [bcftools](https://hub.docker.com/r/staphb/bcftools/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/bcftools)](https://hub.docker.com/r/staphb/bcftools) |
  • [1.10.2](./bcftools/1.10.2/)
  • [1.11](./bcftools/1.11/)
  • [1.12](./bcftools/1.12/)
  • [1.13](./bcftools/1.13/)
  • [1.14](./bcftools/1.14/)
  • [1.15](./bcftools/1.15/)
  • [1.16](./bcftools/1.16/)
  • [1.17](./bcftools/1.17/)
  • [1.18](bcftools/1.18/)
  • [1.19](./bcftools/1.19/)
  • [1.20](./bcftools/1.20/)
  • [1.20.c](./bcftools/1.20.c/)
  • [1.21](./bcftools/1.21/)
| https://github.com/samtools/bcftools | diff --git a/bakta/1.9.4-5.1-light/Dockerfile b/bakta/1.9.4-5.1-light/Dockerfile new file mode 100644 index 000000000..82af4e434 --- /dev/null +++ b/bakta/1.9.4-5.1-light/Dockerfile @@ -0,0 +1,54 @@ +FROM mambaorg/micromamba:1.5.8 as app + +ARG BAKTA_VER="1.9.4" +ARG DIAMOND_VER="2.1.8" + +# 'LABEL' instructions tag the image with metadata that might be important to the user +LABEL base.image="mambaorg/micromamba:1.5.8" +LABEL dockerfile.version="1" +LABEL software="Bakta" +LABEL software.version="${BAKTA_VER}" +LABEL description="rapid & standardized annotation of bacterial genomes, MAGs & plasmids" +LABEL website="https://github.com/oschwengers/bakta" +LABEL license="https://github.com/oschwengers/bakta/blob/main/LICENSE" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" + +USER root + +WORKDIR / + +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + procps \ + ca-certificates && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +RUN micromamba install --name base -c conda-forge -c bioconda -c defaults bakta=${BAKTA_VER} diamond=${DIAMOND_VER} && \ + micromamba clean -a -f -y && \ + mkdir /data + +ENV PATH="/opt/conda/bin/:$PATH" \ + LC_ALL=C \ + BAKTA_DB=/db/db-light + +WORKDIR /db + +RUN bakta_db download --type light + +CMD bakta --help + +WORKDIR /data + +FROM app as test + +WORKDIR /test + +RUN bakta --help && \ + bakta_db --help && \ + bakta --version + +RUN wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/195/815/GCF_000195815.1_ASM19581v1/GCF_000195815.1_ASM19581v1_genomic.fna.gz && \ + gunzip GCF_000195815.1_ASM19581v1_genomic.fna.gz && \ + bakta GCF_000195815.1_ASM19581v1_genomic.fna && \ + head GCF_000195815.1_ASM19581v1_genomic.gbff diff --git a/bakta/1.9.4-5.1-light/README.md b/bakta/1.9.4-5.1-light/README.md new file mode 100644 index 000000000..a30801510 --- /dev/null +++ b/bakta/1.9.4-5.1-light/README.md @@ -0,0 +1,24 @@ +# bakta container + +Main tool: [bakta](https://github.com/oschwengers/bakta) + +Code repository: https://github.com/oschwengers/bakta + +Basic information on how to use this tool: +- executable: bakta +- help: -h +- version: -v +- description: Annotates bacterial genomes + +> Bakta is a tool for the rapid & standardized annotation of bacterial genomes and plasmids from both isolates and MAGs. It provides dbxref-rich, sORF-including and taxon-independent annotations in machine-readable JSON & bioinformatics standard file formats for automated downstream analysis. + +Additional information: + +This image contains the version 5.1 light database. It is located in /db/db-light and set as BAKTA_DB so that --db doesn't have to be used. + +Full documentation: https://github.com/oschwengers/bakta/ + +Example Usage +```bash +bakta sample.fasta --threads 20 --prefix sample +``` From df9da92509924d050465e3b52d0c9ece2bd30ab3 Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Mon, 30 Sep 2024 13:44:44 -0400 Subject: [PATCH 23/92] cleaning up seqfu dockerfile --- seqfu/1.20.3/Dockerfile | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index 6f1d5b9a1..76a7ad9b8 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -42,8 +42,7 @@ RUN curl https://nim-lang.org/choosenim/init.sh -sSf | sh -s -- -y --ver 1.22.2 tar -xzf v${SEQFU_VER}.tar.gz && \ rm v${SEQFU_VER}.tar.gz && \ cd seqfu2-${SEQFU_VER} && \ - make && \ - /bin/bash # Start an interactive shell to manually inspect and debug tests + make # Copy the built binary to a location in the PATH RUN ls -l /root/seqfu2-${SEQFU_VER}/bin && \ @@ -56,7 +55,6 @@ ARG SEQFU_VER # Copy the necessary files from the builder COPY --from=builder /usr/local/bin /usr/local/bin -# COPY --from=builder /root/seqfu2-${SEQFU_VER}/data/tests /root/seqfu2-${SEQFU_VER}/data/tests # Install minimal runtime dependencies RUN apt-get update && apt-get install -y --no-install-recommends \ From 7eaf78329936ca47315ace8d17b6f518d26683dd Mon Sep 17 00:00:00 2001 From: Young Date: Mon, 30 Sep 2024 11:45:59 -0600 Subject: [PATCH 24/92] adding multiqc version 1.25 (#1062) --- README.md | 2 +- multiqc/1.25/Dockerfile | 47 +++++++++++++++++++++++++++++++++++++++++ multiqc/1.25/README.md | 13 ++++++++++++ 3 files changed, 61 insertions(+), 1 deletion(-) create mode 100644 multiqc/1.25/Dockerfile create mode 100644 multiqc/1.25/README.md diff --git a/README.md b/README.md index f0c5d67ce..178e12394 100644 --- a/README.md +++ b/README.md @@ -212,7 +212,7 @@ To learn more about the docker pull rate limits and the open source software pro | [minipolish](https://hub.docker.com/r/staphb/minipolish)
[![docker pulls](https://badgen.net/docker/pulls/staphb/minipolish)](https://hub.docker.com/r/staphb/minipolish) |
  • 0.1.3
| https://github.com/rrwick/Minipolish | | [mlst](https://hub.docker.com/r/staphb/mlst)
[![docker pulls](https://badgen.net/docker/pulls/staphb/mlst)](https://hub.docker.com/r/staphb/mlst) |
  • 2.16.2
  • 2.17.6
  • 2.19.0
  • 2.22.0
  • 2.22.1
  • 2.23.0
  • [2.23.0-2023-07 (databases updated July 2023)](mlst/2.23.0-2023-07/)
  • [2.23.0-2023-08 (databases updated Aug 2023)](mlst/2.23.0-2023-08/)
  • [2.23.0-2024-01 (databases updated Jan 2024)](mlst/2.23.0-2024-01/)
  • [2.23.0-2024-03 (databases updated March 2024)](mlst/2.23.0-2024-03/)
| https://github.com/tseemann/mlst | | [Mugsy](https://hub.docker.com/r/staphb/mugsy)
[![docker pulls](https://badgen.net/docker/pulls/staphb/mugsy)](https://hub.docker.com/r/staphb/mugsy) |
  • 1r2.3
| http://mugsy.sourceforge.net/ | -| [MultiQC](https://hub.docker.com/r/staphb/multiqc)
[![docker pulls](https://badgen.net/docker/pulls/staphb/multiqc)](https://hub.docker.com/r/staphb/multiqc) |
  • [1.7](./multiqc/1.7/)
  • [1.8](./multiqc/1.8/)
  • [1.18](./multiqc/1.18/)
  • [1.19](./multiqc/1.19/)
  • [1.22.2](./multiqc/1.22.2/)
  • [1.22.3](./multiqc/1.22.3/)
| https://github.com/MultiQC/MultiQC | +| [MultiQC](https://hub.docker.com/r/staphb/multiqc)
[![docker pulls](https://badgen.net/docker/pulls/staphb/multiqc)](https://hub.docker.com/r/staphb/multiqc) |
  • [1.7](./multiqc/1.7/)
  • [1.8](./multiqc/1.8/)
  • [1.18](./multiqc/1.18/)
  • [1.19](./multiqc/1.19/)
  • [1.22.2](./multiqc/1.22.2/)
  • [1.22.3](./multiqc/1.22.3/)
  • [1.25](./multiqc/1.25/)
| https://github.com/MultiQC/MultiQC | | [Mummer](https://hub.docker.com/r/staphb/mummer)
[![docker pulls](https://badgen.net/docker/pulls/staphb/mummer)](https://hub.docker.com/r/staphb/mummer) |
  • 4.0.0
  • 4.0.0 + RGDv2
  • 4.0.0 + RGDv2 + gnuplot
| https://github.com/mummer4/mummer | | [Mykrobe + Genotyphi + sonneityping](https://hub.docker.com/r/staphb/mykrobe)
[![docker pulls](https://badgen.net/docker/pulls/staphb/mykrobe)](https://hub.docker.com/r/staphb/mykrobe) |
  • 0.11.0 (Mykrobe) & 1.9.1 (Genotyphi)
  • 0.12.1 (Mykrobe) & 1.9.1 (Genotyphi) & v20210201 (sonneityping)
  • 0.12.1 (Mykrobe) & 2.0 (Genotyphi) & v20210201 (sonneityping)
  • [0.12.2 (Mykrobe) & 2.0 (Genotyphi) & v20210201 (sonneityping)](mykrobe/0.12.2/)
  • [0.13.0](./mykrobe/0.13.0)
| https://github.com/Mykrobe-tools/mykrobe
https://github.com/typhoidgenomics/genotyphi
https://github.com/katholt/sonneityping | | [NanoPlot](https://hub.docker.com/r/staphb/nanoplot)
[![docker pulls](https://badgen.net/docker/pulls/staphb/nanoplot)](https://hub.docker.com/r/staphb/nanoplot) |
  • [1.27.0](./nanoplot/1.27.0/)
  • [1.29.0](./nanoplot/1.29.0/)
  • [1.30.1](./nanoplot/1.30.1/)
  • [1.32.0](./nanoplot/1.32.0/)
  • [1.33.0](./nanoplot/1.33.0/)
  • [1.40.0](./nanoplot/1.40.0/)
  • [1.41.6](./nanoplot/1.41.6/)
  • [1.42.0](./nanoplot/1.42.0/)
| https://github.com/wdecoster/NanoPlot | diff --git a/multiqc/1.25/Dockerfile b/multiqc/1.25/Dockerfile new file mode 100644 index 000000000..4e0fd9953 --- /dev/null +++ b/multiqc/1.25/Dockerfile @@ -0,0 +1,47 @@ +FROM ubuntu:jammy as app + +ARG MULTIQC_VER="1.25" + +# metadata +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="MultiQC" +LABEL software.version="${MULTIQC_VER}" +LABEL description="Aggregate bioinformatics results across many samples into a single report." +LABEL website="https://github.com/MultiQC/MultiQC" +LABEL license="https://github.com/MultiQC/MultiQC/blob/main/LICENSE" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" + +RUN apt-get update && apt-get install --no-install-recommends -y \ + python3-pip && \ + apt-get clean && apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# install multiqc +RUN pip3 install --no-cache-dir -vv "multiqc==${MULTIQC_VER}" + +ENV LC_ALL='C.UTF-8' \ + LANG='C.UTF-8' + +CMD multiqc --help + +RUN mkdir /data +WORKDIR /data + +# testing layer starts here +FROM app as test + +# getting git +RUN apt-get update && apt-get install -y git + +# to ensure multiqc is in PATH +RUN multiqc --help + +# set working directory so that all test inputs & outputs are kept in /test +RUN mkdir /test +WORKDIR /test + +# getting multiqc test data +RUN git clone https://github.com/ewels/MultiQC_TestData && \ + multiqc . && \ + ls multiqc_report.html diff --git a/multiqc/1.25/README.md b/multiqc/1.25/README.md new file mode 100644 index 000000000..879cb9cd8 --- /dev/null +++ b/multiqc/1.25/README.md @@ -0,0 +1,13 @@ +# MultiQC container + +Main tool : [MultiQC](https://multiqc.info/) + +Aggregate results from bioinformatics analyses across many samples into a single report. + +Full documentation: [Docs] (https://multiqc.info/docs/) + +# Example Usage + +``` +multiqc -f --cl_config "prokka_fn_snames: True" . +``` From d27fdc1386be5cec34e6920cfdd7e05dad10cd8a Mon Sep 17 00:00:00 2001 From: Young Date: Mon, 30 Sep 2024 11:51:17 -0600 Subject: [PATCH 25/92] adding datasets version 16.30.0 (#1063) --- README.md | 2 +- ncbi-datasets/16.30.0/Dockerfile | 47 ++++++++++++++++++++++++++++++++ ncbi-datasets/16.30.0/README.md | 20 ++++++++++++++ 3 files changed, 68 insertions(+), 1 deletion(-) create mode 100644 ncbi-datasets/16.30.0/Dockerfile create mode 100644 ncbi-datasets/16.30.0/README.md diff --git a/README.md b/README.md index 178e12394..598e38871 100644 --- a/README.md +++ b/README.md @@ -217,7 +217,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Mykrobe + Genotyphi + sonneityping](https://hub.docker.com/r/staphb/mykrobe)
[![docker pulls](https://badgen.net/docker/pulls/staphb/mykrobe)](https://hub.docker.com/r/staphb/mykrobe) |
  • 0.11.0 (Mykrobe) & 1.9.1 (Genotyphi)
  • 0.12.1 (Mykrobe) & 1.9.1 (Genotyphi) & v20210201 (sonneityping)
  • 0.12.1 (Mykrobe) & 2.0 (Genotyphi) & v20210201 (sonneityping)
  • [0.12.2 (Mykrobe) & 2.0 (Genotyphi) & v20210201 (sonneityping)](mykrobe/0.12.2/)
  • [0.13.0](./mykrobe/0.13.0)
| https://github.com/Mykrobe-tools/mykrobe
https://github.com/typhoidgenomics/genotyphi
https://github.com/katholt/sonneityping | | [NanoPlot](https://hub.docker.com/r/staphb/nanoplot)
[![docker pulls](https://badgen.net/docker/pulls/staphb/nanoplot)](https://hub.docker.com/r/staphb/nanoplot) |
  • [1.27.0](./nanoplot/1.27.0/)
  • [1.29.0](./nanoplot/1.29.0/)
  • [1.30.1](./nanoplot/1.30.1/)
  • [1.32.0](./nanoplot/1.32.0/)
  • [1.33.0](./nanoplot/1.33.0/)
  • [1.40.0](./nanoplot/1.40.0/)
  • [1.41.6](./nanoplot/1.41.6/)
  • [1.42.0](./nanoplot/1.42.0/)
| https://github.com/wdecoster/NanoPlot | | [ngmaster](https://hub.docker.com/r/staphb/ngmaster)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ngmaster)](https://hub.docker.com/r/staphb/ngmaster) |
  • 0.5.8
  • 1.0.0
| https://github.com/MDU-PHL/ngmaster | -| [NCBI Datasets](https://hub.docker.com/r/staphb/ncbi-datasets)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ncbi-datasets)](https://hub.docker.com/r/staphb/ncbi-datasets) |
Click to see all datasets versions **datasets versions**
  • [13.31.0](./ncbi-datasets/13.31.0/)
  • [13.35.0](./ncbi-datasets/13.35.0/)
  • [13.43.2](./ncbi-datasets/13.43.2/)
  • [14.0.0](./ncbi-datasets/14.0.0/)
  • [14.3.0](./ncbi-datasets/14.3.0/)
  • [14.7.0](./ncbi-datasets/14.7.0/)
  • [14.13.2](./ncbi-datasets/14.13.2/)
  • [14.20.0](./ncbi-datasets/14.20.0/)
  • [14.27.0](ncbi-datasets/14.27.0/)
  • [15.1.0](ncbi-datasets/15.1.0/)
  • [15.2.0](ncbi-datasets/15.2.0/)
  • [15.11.0](ncbi-datasets/15.11.0/)
  • [15.27.1](ncbi-datasets/15.27.1/)
  • [15.31.0](ncbi-datasets/15.31.1/)
  • [16.2.0](ncbi-datasets/16.2.0/)
  • [16.8.1](./ncbi-datasets/16.8.1/)
  • [16.10.3](./ncbi-datasets/16.10.3/)
  • [16.15.0](./ncbi-datasets/16.15.0/)
  • [16.22.1](./ncbi-datasets/16.22.1/)
| [https://github.com/ncbi/datasets](https://github.com/ncbi/datasets)
[https://www.ncbi.nlm.nih.gov/datasets/docs/v1/](https://www.ncbi.nlm.nih.gov/datasets/docs/v1/) | +| [NCBI Datasets](https://hub.docker.com/r/staphb/ncbi-datasets)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ncbi-datasets)](https://hub.docker.com/r/staphb/ncbi-datasets) |
Click to see all datasets versions **datasets versions**
  • [13.31.0](./ncbi-datasets/13.31.0/)
  • [13.35.0](./ncbi-datasets/13.35.0/)
  • [13.43.2](./ncbi-datasets/13.43.2/)
  • [14.0.0](./ncbi-datasets/14.0.0/)
  • [14.3.0](./ncbi-datasets/14.3.0/)
  • [14.7.0](./ncbi-datasets/14.7.0/)
  • [14.13.2](./ncbi-datasets/14.13.2/)
  • [14.20.0](./ncbi-datasets/14.20.0/)
  • [14.27.0](ncbi-datasets/14.27.0/)
  • [15.1.0](ncbi-datasets/15.1.0/)
  • [15.2.0](ncbi-datasets/15.2.0/)
  • [15.11.0](ncbi-datasets/15.11.0/)
  • [15.27.1](ncbi-datasets/15.27.1/)
  • [15.31.0](ncbi-datasets/15.31.1/)
  • [16.2.0](ncbi-datasets/16.2.0/)
  • [16.8.1](./ncbi-datasets/16.8.1/)
  • [16.10.3](./ncbi-datasets/16.10.3/)
  • [16.15.0](./ncbi-datasets/16.15.0/)
  • [16.22.1](./ncbi-datasets/16.22.1/)
  • [16.30.0](./ncbi-datasets/16.30.0/)
| [https://github.com/ncbi/datasets](https://github.com/ncbi/datasets)
[https://www.ncbi.nlm.nih.gov/datasets/docs/v1/](https://www.ncbi.nlm.nih.gov/datasets/docs/v1/) | | [NCBI AMRFinderPlus](https://hub.docker.com/r/staphb/ncbi-amrfinderplus)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ncbi-amrfinderplus)](https://hub.docker.com/r/staphb/ncbi-amrfinderplus) | **AMRFinderPlus & database verion**
Click to see AMRFinderplus v3.11.4 and older versions!
  • 3.1.1b
  • 3.8.4
  • 3.8.28
  • 3.9.3
  • 3.9.8
  • 3.10.1
  • 3.10.5
  • 3.10.16
  • 3.10.20
  • 3.10.24
  • 3.10.30
  • 3.10.36
  • 3.10.42
  • 3.11.2 & 2022-12-19.1
  • [3.11.2 & 2023-02-23.1](ncbi-amrfinderplus/3.11.2-2023-02-23.1/)
  • [3.11.4 & 2023-02-23.1](ncbi-amrfinderplus/3.11.4-2023-02-23.1/)
  • [3.11.8 & 2023-02-23.1](ncbi-amrfinderplus/3.11.8-2023-02-23.1/)
  • [3.11.11 & 2023-04-17.1](ncbi-amrfinderplus/3.11.11-2023-04-17.1)
  • [3.11.14 & 2023-04-17.1](ncbi-amrfinderplus/3.11.14-2023-04-17.1/)
  • [3.11.17 & 2023-07-13.2](ncbi-amrfinderplus/3.11.17-2023-07-13.2/)
  • [3.11.18 & 2023-08-08.2](ncbi-amrfinderplus/3.11.18-2023-08-08.2/)
  • [3.11.20 & 2023-09-26.1](ncbi-amrfinderplus/3.11.20-2023-09-26.1/)
  • [3.11.26 & 2023-11-15.1](ncbi-amrfinderplus/3.11.26-2023-11-15.1/)
  • [3.12.8 & 2024-01-31.1](ncbi-amrfinderplus/3.12.8-2024-01-31.1/)
  • [3.12.8 & 2024-05-02.2](./ncbi-amrfinderplus/3.12.8-2024-05-02.2/)
  • [3.12.8 & 2024-07-22.1](./ncbi-amrfinderplus/3.12.8-2024-07-22.1/)
| [https://github.com/ncbi/amr](https://github.com/ncbi/amr) | | [NCBI table2asn](https://hub.docker.com/r/staphb/ncbi-table2asn)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ncbi-table2asn)](https://hub.docker.com/r/staphb/ncbi-table2asn) |
  • [1.26.678](./ncbi-table2asn/1.26.678/)
  • [1.28.943](./ncbi-table2asn/1.28.943/)
  • [1.28.1021](./ncbi-table2asn/1021/)
| [https://www.ncbi.nlm.nih.gov/genbank/table2asn/](https://www.ncbi.nlm.nih.gov/genbank/table2asn/)
[https://ftp.ncbi.nlm.nih.gov/asn1-converters/versions/2022-06-14/by_program/table2asn/](https://ftp.ncbi.nlm.nih.gov/asn1-converters/versions/2022-06-14/by_program/table2asn/) | | [ONTime](https://hub.docker.com/r/staphb/ontime)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ontime)](https://hub.docker.com/r/staphb/ontime) |
  • [0.2.3](ontime/0.2.3/)
  • [0.3.1](ontime/0.3.1/)
| https://github.com/mbhall88/ontime | diff --git a/ncbi-datasets/16.30.0/Dockerfile b/ncbi-datasets/16.30.0/Dockerfile new file mode 100644 index 000000000..1fc28593c --- /dev/null +++ b/ncbi-datasets/16.30.0/Dockerfile @@ -0,0 +1,47 @@ +FROM ubuntu:jammy as app + +ARG DATASETS_VER="16.30.0" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="NCBI's datasets and dataformat" +LABEL software.version="${DATASETS_VER}" +LABEL description="Downloads biological sequence data from NCBI" +LABEL website="https://github.com/ncbi/datasets" +LABEL documentation="https://www.ncbi.nlm.nih.gov/datasets/docs/v1/" +LABEL license="https://github.com/ncbi/datasets/blob/master/pkgs/ncbi-datasets-cli/LICENSE.md" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" + +# unzip isn't needed for datasets/dataformat, but it is often used after downloading files with datasets +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + unzip && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +WORKDIR /usr/local/bin + +# install ncbi datasets tool (pre-compiled binary) +RUN wget https://github.com/ncbi/datasets/releases/download/v${DATASETS_VER}/linux-amd64.cli.package.zip && \ + unzip linux-amd64.cli.package.zip && \ + rm linux-amd64.cli.package.zip && \ + chmod +x dataformat datasets + +ENV LC_ALL=C + +WORKDIR /data + +# datasets is generally datasets --help, but just typing in 'datasets' should bring up a help menu +CMD [ "datasets", "--help" ] + +FROM app as test + +RUN dataformat --help && datasets --help + +# stolen from Curtis at https://github.com/StaPH-B/docker-builds/blob/master/pangolin/4.1.2/Dockerfile +RUN datasets download virus genome accession ON924087.1 --filename ON924087.1.zip && \ + unzip ON924087.1.zip && \ + rm ON924087.1.zip && \ + cp ncbi_dataset/data/genomic.fna ON924087.1.fna && \ + wc -c ON924087.1.fna diff --git a/ncbi-datasets/16.30.0/README.md b/ncbi-datasets/16.30.0/README.md new file mode 100644 index 000000000..6474b9282 --- /dev/null +++ b/ncbi-datasets/16.30.0/README.md @@ -0,0 +1,20 @@ +# NCBI datasets and dataformat container + +Main tool : [datasets](https://www.ncbi.nlm.nih.gov/datasets/docs/v1/download-and-install/#use-the-datasets-tool-to-download-biological-data) and [dataformat](https://www.ncbi.nlm.nih.gov/datasets/docs/v1/download-and-install/#use-the-dataformat-tool-to-convert-data-reports-to-other-formats) + +Full documentation: [https://www.ncbi.nlm.nih.gov/datasets/docs/v1/how-tos/](https://www.ncbi.nlm.nih.gov/datasets/docs/v1/how-tos/) + +> Use NCBI Datasets to gather metadata, download data packages, view reports and more + +## Example Usage + +```bash +# will download the fasta for ON924087.1 in a zipped directory +datasets download virus genome accession ON924087.1 --filename ON924087.1.zip + +# unzipping the directory and the fasta file will be located at ncbi_dataset/data/genomic.fna +unzip ON924087.1.zip + +# copying the file into something with a better name +cp ncbi_dataset/data/genomic.fna ncbi_dataset/data/ON924087.1.genomic.fna +``` From 46b792e7ac1368e2e49757cf47f9e6df47f038ad Mon Sep 17 00:00:00 2001 From: Young Date: Mon, 30 Sep 2024 12:01:44 -0600 Subject: [PATCH 26/92] adding ska2 version 0.3.10 (#1069) --- README.md | 2 +- ska2/0.3.10/Dockerfile | 46 ++++++++++++++++++++++++++++++++++++++++++ ska2/0.3.10/README.md | 24 ++++++++++++++++++++++ 3 files changed, 71 insertions(+), 1 deletion(-) create mode 100644 ska2/0.3.10/Dockerfile create mode 100644 ska2/0.3.10/README.md diff --git a/README.md b/README.md index 598e38871..550af8968 100644 --- a/README.md +++ b/README.md @@ -278,7 +278,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Shovill-se](https://hub.docker.com/r/staphb/shovill-se/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/shovill-se)](https://hub.docker.com/r/staphb/shovill-se) |
  • 1.1.0
| https://github.com/rpetit3/shovill/tree/v1.1.0se | | [SISTR](https://hub.docker.com/r/staphb/sistr/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/sistr)](https://hub.docker.com/r/staphb/sistr) |
  • 1.0.2
  • 1.1.1
| https://github.com/phac-nml/sistr_cmd | | [SKA](https://hub.docker.com/r/staphb/ska/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ska)](https://hub.docker.com/r/staphb/ska) |
  • 1.0
| https://github.com/simonrharris/SKA | -| [SKA2](https://hub.docker.com/r/staphb/ska2/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ska2)](https://hub.docker.com/r/staphb/ska2) |
  • [0.3.6](./ska2/0.3.6/)
  • [0.3.7](./ska2/0.3.7/)
| https://github.com/bacpop/ska.rust | +| [SKA2](https://hub.docker.com/r/staphb/ska2/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ska2)](https://hub.docker.com/r/staphb/ska2) |
  • [0.3.6](./ska2/0.3.6/)
  • [0.3.7](./ska2/0.3.7/)
  • [0.3.10](./ska2/0.3.10/)
| https://github.com/bacpop/ska.rust | | [skani](https://github.com/bluenote-1577/skani)
[![docker pulls](https://badgen.net/docker/pulls/staphb/skani)](https://hub.docker.com/r/staphb/skani) |
  • [0.2.0](./skani/0.2.0)
  • [0.2.1](./skani/0.2.1)
  • [0.2.2](./skani/0.2.2)
| https://github.com/bluenote-1577/skani | | [SKESA](https://hub.docker.com/r/staphb/skesa)
[![docker pulls](https://badgen.net/docker/pulls/staphb/skesa)](https://hub.docker.com/r/staphb/skesa) |
  • [2.3.0](./skesa/2.3.0/)
  • [2.4.0 (`gfa_connector` & `kmercounter` included)](./skesa/2.4.0/)
  • [skesa.2.4.0_saute.1.3.0_2 (also known as 2.5.1)](./skesa/skesa.2.4.0_saute.1.3.0_2/)
| https://github.com/ncbi/SKESA | | [Smalt](https://hub.docker.com/r/staphb/smalt)
[![docker pulls](https://badgen.net/docker/pulls/staphb/smalt)](https://hub.docker.com/r/staphb/smalt) |
  • 0.7.6
| https://www.sanger.ac.uk/tool/smalt-0/ | diff --git a/ska2/0.3.10/Dockerfile b/ska2/0.3.10/Dockerfile new file mode 100644 index 000000000..950a5ca8f --- /dev/null +++ b/ska2/0.3.10/Dockerfile @@ -0,0 +1,46 @@ +FROM ubuntu:jammy as app + +ARG SKA2_VER="0.3.10" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="SKA2" +LABEL software.version="${SKA2_VER}" +LABEL description="A reimplementation of the SKA package in the rust language" +LABEL website="https://github.com/bacpop/ska.rust" +LABEL license="https://github.com/bacpop/ska.rust/blob/master/LICENSE" +LABEL maintainer="Kutluhan Incekara" +LABEL maintainer.email="kutluhan.incekara@ct.gov" + +RUN apt-get update && apt-get install --no-install-recommends -y \ + wget &&\ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +RUN wget --no-check-certificate https://github.com/bacpop/ska.rust/releases/download/v${SKA2_VER}/ska-v${SKA2_VER}-ubuntu-latest-stable.tar.gz &&\ + tar -C /usr/local/bin -xvf ska-v${SKA2_VER}-ubuntu-latest-stable.tar.gz ska &&\ + rm ska-v${SKA2_VER}-ubuntu-latest-stable.tar.gz + +ENV LC_ALL=C + +CMD [ "ska", "-h" ] + +WORKDIR /data + +## Test ## +FROM app as test + +# force bash to avoid shell errors +SHELL ["/bin/bash", "-c"] + +# adapted from tutorial https://www.bacpop.org/guides/building_trees_with_ska/ +RUN wget --no-check-certificate https://zenodo.org/record/8172518/files/building_trees_with_ska.tar &&\ + tar -xvf building_trees_with_ska.tar assemblies/LA002.fa.gz assemblies/LA022.fa.gz assemblies/LA023.fa.gz assemblies/LA026.fa.gz &&\ + paste <(ls assemblies | sed 's/[.].*$//g') <(ls -d assemblies/*) > laos_ska_input.tsv + +RUN ska build -f laos_ska_input.tsv -k 31 -o laos_ska_index --threads 4 &&\ + ska align --min-freq 1 --filter no-filter laos_ska_index.skf -o laos_ska_alignment.aln --threads 4 &&\ + head -c 1000 laos_ska_alignment.aln &&\ + grep ">" laos_ska_alignment.aln + + + diff --git a/ska2/0.3.10/README.md b/ska2/0.3.10/README.md new file mode 100644 index 000000000..abf740604 --- /dev/null +++ b/ska2/0.3.10/README.md @@ -0,0 +1,24 @@ +# SKA2 container + +Main tool: [SKA2](https://github.com/bacpop/ska.rust) + +Code repository: https://github.com/bacpop/ska.rust + +Basic information on how to use this tool: +- executable: ska +- help: -h, --help +- version: -V, --version +- description: SKA2 is a reimplementation of the SKA package in the rust language. Split k-mer analysis (version 2) uses exact matching of split k-mer sequences to align closely related sequences, typically small haploid genomes such as bacteria and viruses. + +Full documentation: https://docs.rs/ska/latest/ska/ + +## Example Usage + +```bash +# Build from two input FASTA files with a k-mer size of 31 +ska build -o seqs -k 31 assemblies/seq1.fa assemblies/seq2.fa +# align +ska align --min-freq 1 --filter no-filter -o seqs seqs.skf +# map +ska map ref.fa seqs.skf -o ref_mapped.aln +``` From 30fedfb4c9f0cb5ba1bdc0f799b4820af560b057 Mon Sep 17 00:00:00 2001 From: Kincekara Date: Mon, 30 Sep 2024 19:06:10 +0000 Subject: [PATCH 27/92] adds integron finder --- Program_Licenses.md | 1 + README.md | 1 + integron_finder/2.0.5/Dockerfile | 41 ++++++++++++++++++++++++++++++++ integron_finder/2.0.5/README.md | 29 ++++++++++++++++++++++ 4 files changed, 72 insertions(+) create mode 100644 integron_finder/2.0.5/Dockerfile create mode 100644 integron_finder/2.0.5/README.md diff --git a/Program_Licenses.md b/Program_Licenses.md index 398acb32e..84442d2d8 100644 --- a/Program_Licenses.md +++ b/Program_Licenses.md @@ -71,6 +71,7 @@ The licenses of the open-source software that is contained in these Docker image | Hmmer | BSD-3 | http://eddylab.org/software/hmmer/Userguide.pdf | | homopolish | GNU GPLv3 | https://github.com/ythuang0522/homopolish/blob/master/LICENSE | | htslib | MIT | https://github.com/samtools/htslib/blob/develop/LICENSE | +| Integron Finder | GNU GPLv3 | https://github.com/gem-pasteur/Integron_Finder/blob/master/COPYING | | iqtree | GNU GPLv2 | https://github.com/Cibiv/IQ-TREE/blob/master/LICENSE | | iqtree2 | GNU GPLv2 | https://github.com/iqtree/iqtree2/blob/master/LICENSE | | IPA | BSD-3 | https://github.com/PacificBiosciences/pbipa/blob/master/LICENSE.txt | diff --git a/README.md b/README.md index 550af8968..46cbd15a5 100644 --- a/README.md +++ b/README.md @@ -180,6 +180,7 @@ To learn more about the docker pull rate limits and the open source software pro | [hmmer](https://hub.docker.com/r/staphb/hmmer)
[![docker pulls](https://badgen.net/docker/pulls/staphb/hmmer)](https://hub.docker.com/r/staphb/hmmer) |
  • [3.3](hmmer/3.3/)
  • [3.3.2](hmmer/3.3.2/)
  • [3.4](./hmmer/3.4/)
| http://hmmer.org/ | | [homopolish](https://hub.docker.com/r/staphb/homopolish)
[![docker pulls](https://badgen.net/docker/pulls/staphb/homopolish)](https://hub.docker.com/r/staphb/homopolish) |
  • 0.4.1
| https://github.com/ythuang0522/homopolish/ | | [htslib](https://hub.docker.com/r/staphb/htslib)
[![docker pulls](https://badgen.net/docker/pulls/staphb/htslib)](https://hub.docker.com/r/staphb/htslib) |
  • [1.14](./htslib/1.14)
  • [1.15](./htslib/1.15)
  • [1.16](./htslib/1.16)
  • [1.17](./htslib/1.17)
  • [1.18](./htslib/1.18/)
  • [1.19](./htslib/1.19/)
  • [1.20](./htslib/1.20/)
  • [1.20.c](./htslib/1.20.c/)
  • [1.21](./htslib/1.21/)
| https://www.htslib.org/ | +| [Integron Finder](https://hub.docker.com/r/staphb/integron_finder/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/integron_finder)](https://hub.docker.com/r/staphb/integron_finder) |
  • [2.0.5](./integron_finder/2.0.5/)
| https://github.com/gem-pasteur/Integron_Finder | | [iqtree](https://hub.docker.com/r/staphb/iqtree/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/iqtree)](https://hub.docker.com/r/staphb/iqtree) |
  • 1.6.7
| http://www.iqtree.org/ | | [iqtree2](https://hub.docker.com/r/staphb/iqtree2/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/iqtree2)](https://hub.docker.com/r/staphb/iqtree2) |
  • 2.1.2
  • 2.2.2.2
  • [2.2.2.6](iqtree2/2.2.2.6/)
  • [2.2.2.7](iqtree2/2.2.2.7/)
  • [2.3.1](iqtree2/2.3.1/)
  • [2.3.4](iqtree2/2.3.4/)
  • [2.3.6](iqtree2/2.3.6/)
| http://www.iqtree.org/ | | [IPA](https://hub.docker.com/r/staphb/pbipa)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pbipa)](https://hub.docker.com/r/staphb/pbipa) |
  • [1.8.0](./pbipa/1.8.0/)
| https://github.com/PacificBiosciences/pbipa | diff --git a/integron_finder/2.0.5/Dockerfile b/integron_finder/2.0.5/Dockerfile new file mode 100644 index 000000000..a2bdfcb51 --- /dev/null +++ b/integron_finder/2.0.5/Dockerfile @@ -0,0 +1,41 @@ +FROM ubuntu:jammy AS app + +ARG INTEGRON_FINDER_VER="2.0.5" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="Integron Finder" +LABEL software.version="${INTEGRON_FINDER_VER}" +LABEL description="Finds integrons in DNA sequences" +LABEL website="https://github.com/gem-pasteur/Integron_Finder" +LABEL license="https://github.com/gem-pasteur/Integron_Finder/blob/master/COPYING" +LABEL maintainer="Kutluhan Incekara" +LABEL maintainer.email="kutluhan.incekara@ct.gov" + +RUN apt-get update && apt-get install --no-install-recommends -y \ + python3-pip \ + hmmer \ + infernal \ + prodigal && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +RUN pip3 install --no-cache-dir integron_finder==${INTEGRON_FINDER_VER} + +ENV LC_ALL=C + +CMD [ "integron_finder", "--help" ] + +WORKDIR /data + +## Test ## +FROM app AS test + +RUN apt-get update && apt-get install -y wget + +RUN wget -q https://github.com/gem-pasteur/Integron_Finder/raw/master/tests/data/Replicons/NZ_CP016323.fna &&\ + integron_finder --local-max --circ --keep-tmp NZ_CP016323.fna &&\ + cat Results_Integron_Finder_NZ_CP016323/NZ_CP016323.summary &&\ + head Results_Integron_Finder_NZ_CP016323/NZ_CP016323.integrons + + + diff --git a/integron_finder/2.0.5/README.md b/integron_finder/2.0.5/README.md new file mode 100644 index 000000000..63c84cab3 --- /dev/null +++ b/integron_finder/2.0.5/README.md @@ -0,0 +1,29 @@ +# Integron Finder container + +Main tool: [Integron Finder](https://integronfinder.readthedocs.io/en/latest/) + +Code repository: https://github.com/gem-pasteur/Integron_Finder + +Additional tools: + - Python 3.10.12 + - numpy 2.1.1 + - pandas 2.2.3 + - matplolib 3.9.2 + - biopython 1.84 + - Prodigal V2.6.3 + - INFERNAL 1.1.4 + - HMMER 3.3.2 + +Basic information on how to use this tool: +- executable: integron_finder +- help: --help +- version: --version +- description: Finds integrons in DNA sequences + +Full documentation: https://integronfinder.readthedocs.io/en/latest/ + +## Example Usage + +```bash +integron_finder --local-max --circ --keep-tmp genome.fna +``` From 2c5daa51154dff498d32d90e7943407c557e26b2 Mon Sep 17 00:00:00 2001 From: Young Date: Tue, 1 Oct 2024 08:35:00 -0600 Subject: [PATCH 28/92] adding dnaapler version 0.8.1 (#1056) Co-authored-by: Kutluhan Incekara <46578029+Kincekara@users.noreply.github.com> --- README.md | 2 +- dnaapler/0.8.1/Dockerfile | 57 +++++++++++++++++++++++++++++++++++++++ dnaapler/0.8.1/README.md | 37 +++++++++++++++++++++++++ 3 files changed, 95 insertions(+), 1 deletion(-) create mode 100644 dnaapler/0.8.1/Dockerfile create mode 100644 dnaapler/0.8.1/README.md diff --git a/README.md b/README.md index 550af8968..1bd899397 100644 --- a/README.md +++ b/README.md @@ -148,7 +148,7 @@ To learn more about the docker pull rate limits and the open source software pro | [cutshaw-report-env](https://hub.docker.com/r/staphb/cutshaw-report-env)
[![docker pulls](https://badgen.net/docker/pulls/staphb/cutshaw-report-env)](https://hub.docker.com/r/staphb/cutshaw-report-env) |
  • 1.0.0
| https://github.com/VADGS/CutShaw | | [datasets-sars-cov-2](https://github.com/CDCgov/datasets-sars-cov-2)
[![docker pulls](https://badgen.net/docker/pulls/staphb/datasets-sars-cov-2)](https://hub.docker.com/r/staphb/datasets-sars-cov-2) |
  • 0.6.2
  • 0.6.3
  • 0.7.2
| https://github.com/CDCgov/datasets-sars-cov-2 | | [diamond](https://github.com/bbuchfink/diamond)
[![docker pulls](https://badgen.net/docker/pulls/staphb/diamond)](https://hub.docker.com/r/staphb/diamond) |
  • [2.1.9](./diamond/2.1.9)
| https://github.com/bbuchfink/diamond| -| [dnaapler](https://hub.docker.com/r/staphb/dnaapler)
[![docker pulls](https://badgen.net/docker/pulls/staphb/dnaapler)](https://hub.docker.com/r/staphb/dnaapler) |
  • [0.1.0](dnaapler/0.1.0/)
  • [0.4.0](dnaapler/0.4.0/)
  • [0.5.0](dnaapler/0.5.0/)
  • [0.5.1](dnaapler/0.5.1/)
  • [0.7.0](dnaapler/0.7.0/)
  • [0.8.0](dnaapler/0.8.0/)
| https://github.com/gbouras13/dnaapler | +| [dnaapler](https://hub.docker.com/r/staphb/dnaapler)
[![docker pulls](https://badgen.net/docker/pulls/staphb/dnaapler)](https://hub.docker.com/r/staphb/dnaapler) |
  • [0.1.0](dnaapler/0.1.0/)
  • [0.4.0](dnaapler/0.4.0/)
  • [0.5.0](./dnaapler/0.5.0/)
  • [0.5.1](./dnaapler/0.5.1/)
  • [0.7.0](./dnaapler/0.7.0/)
  • [0.8.0](./dnaapler/0.8.0/)
  • [0.8.1](./dnaapler/0.8.1/)
| https://github.com/gbouras13/dnaapler | | [dorado](https://hub.docker.com/r/staphb/dorado)
[![docker pulls](https://badgen.net/docker/pulls/staphb/dorado)](https://hub.docker.com/r/staphb/dorado) |
  • [0.8.0](dorado/0.8.0/)
| [https://github.com/nanoporetech/dorado](https://github.com/nanoporetech/dorado) | | [dragonflye](https://hub.docker.com/r/staphb/dragonflye)
[![docker pulls](https://badgen.net/docker/pulls/staphb/dragonflye)](https://hub.docker.com/r/staphb/dragonflye) |
  • [1.0.14](./dragonflye/1.0.14/)
  • [1.1.1](./dragonflye/1.1.1/)
  • [1.1.2](./dragonflye/1.1.2/)
  • [1.2.0](./dragonflye/1.2.0/)
  • [1.2.1](./dragonflye/1.2.1/)
| https://github.com/rpetit3/dragonflye | | [Dr. PRG ](https://hub.docker.com/r/staphb/drprg)
[![docker pulls](https://badgen.net/docker/pulls/staphb/drprg)](https://hub.docker.com/r/staphb/drprg) |
  • [0.1.1](drprg/0.1.1/)
| https://mbh.sh/drprg/ | diff --git a/dnaapler/0.8.1/Dockerfile b/dnaapler/0.8.1/Dockerfile new file mode 100644 index 000000000..c9ba438a7 --- /dev/null +++ b/dnaapler/0.8.1/Dockerfile @@ -0,0 +1,57 @@ +FROM mambaorg/micromamba:1.5.8 as app + +USER root + +WORKDIR / + +ARG DNAAPLER_VER="0.8.1" + +# metadata labels +LABEL base.image="mambaorg/micromamba:1.5.8" +LABEL dockerfile.version="1" +LABEL software="dnaapler" +LABEL software.version="${DNAAPLER_VER}" +LABEL description="Rotates chromosomes and more" +LABEL website="https://github.com/gbouras13/dnaapler" +LABEL license="MIT" +LABEL license.url="https://github.com/gbouras13/dnaapler/blob/main/LICENSE" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" + +# install dependencies; cleanup apt garbage +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + procps && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# create the conda environment, install mykrobe via bioconda package; cleanup conda garbage +RUN micromamba create -n dnaapler -y -c bioconda -c defaults -c conda-forge dnaapler=${DNAAPLER_VER} && \ + micromamba clean -a -f -y + +# set the PATH and LC_ALL for singularity compatibility +ENV PATH="/opt/conda/envs/dnaapler/bin/:${PATH}" \ + LC_ALL=C.UTF-8 + +# set final working directory as /data +WORKDIR /data + +# default command is to print help options +CMD [ "dnaapler", "--help" ] + +# new base for testing +FROM app as test + +# set working directory to /test +WORKDIR /test + +# checking that tool is in PATH +RUN dnaapler --help && dnaapler --version + +# downloads genome sequence and then extracts the last plasmid in the laziest way possible +RUN wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/025/259/185/GCA_025259185.1_ASM2525918v1/GCA_025259185.1_ASM2525918v1_genomic.fna.gz && \ + gunzip GCA_025259185.1_ASM2525918v1_genomic.fna.gz && \ + grep "CP104365.1" GCA_025259185.1_ASM2525918v1_genomic.fna -A 50000 > CP104365.1.fasta && \ + dnaapler mystery --prefix mystery_test --output mystery_test -i CP104365.1.fasta && \ + dnaapler plasmid --prefix plasmid_test --output plasmid_test -i CP104365.1.fasta && \ + ls mystery_test plasmid_test diff --git a/dnaapler/0.8.1/README.md b/dnaapler/0.8.1/README.md new file mode 100644 index 000000000..79e17f4a5 --- /dev/null +++ b/dnaapler/0.8.1/README.md @@ -0,0 +1,37 @@ +# dnaapler container + +Main tool : [dnappler](https://github.com/gbouras13/dnaapler) + +Full documentation: [https://github.com/gbouras13/dnaapler](https://github.com/gbouras13/dnaapler) + +> `dnaapler` is a simple python program that takes a single nucleotide input sequence (in FASTA format), finds the desired start gene using blastx against an amino acid sequence database, checks that the start codon of this gene is found, and if so, then reorients the chromosome to begin with this gene on the forward strand. + +dnaapler has several commands for chromosomes, plasmids, and more. + +``` +Usage: dnaapler [OPTIONS] COMMAND [ARGS]... + +Options: + -h, --help Show this message and exit. + -V, --version Show the version and exit. + +Commands: + chromosome Reorients your sequence to begin with the dnaA chromosomal... + citation Print the citation(s) for this tool + custom Reorients your sequence with a custom database + mystery Reorients your sequence with a random gene + phage Reorients your sequence to begin with the terL large... + plasmid Reorients your sequence to begin with the repA replication... +``` + +WARNING: Does not support multifasta files. Each sequence must be processed individually. + +## Example Usage + +```bash +# for a fasta of a chromsome sequence +dnaapler chromosome --input chromosome.fasta --output dnaapler_chr + +# for a fasta of a plasmid sequence +dnaapler plasmid --input plasmid.fasta --output dnaapler_plasmid +``` From 296e5dd955ed2af08bde35db7bdbf8b6a84b0293 Mon Sep 17 00:00:00 2001 From: Young Date: Tue, 1 Oct 2024 11:15:00 -0600 Subject: [PATCH 29/92] updating for pycirclize version 1.7.1 (#1066) --- README.md | 2 +- pycirclize/1.7.1/Dockerfile | 43 ++++++++++++++++++++++++++ pycirclize/1.7.1/README.md | 61 +++++++++++++++++++++++++++++++++++++ 3 files changed, 105 insertions(+), 1 deletion(-) create mode 100644 pycirclize/1.7.1/Dockerfile create mode 100644 pycirclize/1.7.1/README.md diff --git a/README.md b/README.md index 1bd899397..c6fa34688 100644 --- a/README.md +++ b/README.md @@ -247,7 +247,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Porechop](https://hub.docker.com/r/staphb/porechop/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/porechop)](https://hub.docker.com/r/staphb/porechop) |
  • 0.2.4
| https://github.com/rrwick/Porechop | | [PPanGGOLiN](https://hub.docker.com/r/staphb/ppanggolin/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ppanggolin)](https://hub.docker.com/r/staphb/ppanggolin) |
  • [1.2.105](./ppanggolin/1.2.105/)
  • [2.0.3](./ppanggolin/2.0.3/)
  • [2.0.5](./ppanggolin/2.0.5/)
| https://github.com/labgem/PPanGGOLiN | | [Prokka](https://hub.docker.com/r/staphb/prokka/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/prokka)](https://hub.docker.com/r/staphb/prokka) |
  • 1.13.4
  • 1.14.0
  • 1.14.5
  • 1.14.6
| https://github.com/tseemann/prokka | -| [pyCirclize](https://hub.docker.com/r/staphb/pycirclize/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pycirclize)](https://hub.docker.com/r/staphb/pycirclize) |
  • [1.0.0](pycirclize/1.0.0/)
  • [1.2.0](./pycirclize/1.2.0/)
  • [1.5.0](./pycirclize/1.5.0/)
  • [1.6.0](./pycirclize/1.6.0/)
| https://github.com/moshi4/pyCirclize | +| [pyCirclize](https://hub.docker.com/r/staphb/pycirclize/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pycirclize)](https://hub.docker.com/r/staphb/pycirclize) |
  • [1.0.0](pycirclize/1.0.0/)
  • [1.2.0](./pycirclize/1.2.0/)
  • [1.5.0](./pycirclize/1.5.0/)
  • [1.6.0](./pycirclize/1.6.0/)
  • [1.71](./pycirclize/1.7.1/)
| https://github.com/moshi4/pyCirclize | | [pyGenomeViz](https://hub.docker.com/r/staphb/pygenomeviz/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pygenomeviz)](https://hub.docker.com/r/staphb/pygenomeviz) |
  • 0.2.2
  • 0.3.2
  • [0.4.2](pygenomeviz/0.4.2/)
  • [0.4.3](pygenomeviz/0.4.3/)
  • [0.4.4](pygenomeviz/0.4.4/)
  • [1.1.0](pygenomeviz/1.1.0/)
| https://github.com/moshi4/pyGenomeViz | | [pyMLST](https://hub.docker.com/r/staphb/pymlst/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pymlst)](https://hub.docker.com/r/staphb/pymlst) |
  • [2.1.5](./pymlst/2.1.5/)
  • [2.1.6](./pymlst/2.1.6/)
| https://github.com/bvalot/pyMLST | | [pypolca](https://hub.docker.com/r/staphb/pypolca/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pypolca)](https://hub.docker.com/r/staphb/pypolca) |
  • [0.3.1](./pypolca/0.3.1/)
| https://github.com/gbouras13/pypolca | diff --git a/pycirclize/1.7.1/Dockerfile b/pycirclize/1.7.1/Dockerfile new file mode 100644 index 000000000..dd1eb7e61 --- /dev/null +++ b/pycirclize/1.7.1/Dockerfile @@ -0,0 +1,43 @@ +FROM python:3.9.17-slim as app + +ARG PYCIRCLIZE_VER="1.7.1" + +# 'LABEL' instructions tag the image with metadata that might be important to the user +LABEL base.image="python:3.9.17-slim" +LABEL dockerfile.version="1" +LABEL software="pyCirclize" +LABEL software.version="${PYCIRCLIZE_VER}" +LABEL description="Circular visualization in Python" +LABEL website="https://github.com/moshi4/pyCirclize" +LABEL license="https://github.com/moshi4/pyCirclize/blob/main/LICENSE" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" + +RUN apt-get update && apt-get install -y --no-install-recommends \ + procps && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +RUN pip install --no-cache pycirclize==${PYCIRCLIZE_VER} -vv + +ENV PATH=$PATH \ + LC_ALL=C + +CMD pip show pycirclize + +WORKDIR /data + +FROM app as test + +WORKDIR /test + +RUN pip show pycirclize + +RUN apt-get update && apt-get install -y --no-install-recommends wget + +RUN wget -q https://raw.githubusercontent.com/StaPH-B/docker-builds/master/pycirclize/1.5.0/tests/example1.py && \ + wget -q https://raw.githubusercontent.com/StaPH-B/docker-builds/master/pycirclize/1.5.0/tests/example2.py && \ + wget -q https://raw.githubusercontent.com/StaPH-B/docker-builds/master/pycirclize/1.5.0/tests/example3.py + +RUN python example1.py && ls example01.png && \ + python example2.py && ls example02.png && \ + python example3.py && ls example03.png diff --git a/pycirclize/1.7.1/README.md b/pycirclize/1.7.1/README.md new file mode 100644 index 000000000..39f05ac66 --- /dev/null +++ b/pycirclize/1.7.1/README.md @@ -0,0 +1,61 @@ +# pyCirclize container + +Main tool: [pyCirclize](https://pypi.org/project/pyCirclize/) + +Code repository: https://github.com/moshi4/pyCirclize + +Basic information on how to use this tool: +- executable: NA +- help: NA +- version: NA +- description: pyCirclize is a python package for creating visual images of circular genomes (like those of bacteria) + +Full documentation: https://pypi.org/project/pyCirclize/ + +## Example Usage + +This is for running containers with a specific python package, and is not really meant to be run from the command line. Instead, a bioinformatician could create a python script that uses pycirclize. + +example1.py: +```python +from pycirclize import Circos +import numpy as np +np.random.seed(0) + +# Initialize Circos sectors +sectors = {"A": 10, "B": 15, "C": 12, "D": 20, "E": 15} +circos = Circos(sectors, space=5) + +for sector in circos.sectors: + # Plot sector name + sector.text(f"Sector: {sector.name}", r=110, size=15) + # Create x positions & random y values + x = np.arange(sector.start, sector.end) + 0.5 + y = np.random.randint(0, 100, len(x)) + # Plot lines + track1 = sector.add_track((80, 100), r_pad_ratio=0.1) + track1.xticks_by_interval(interval=1) + track1.axis() + track1.line(x, y) + # Plot points + track2 = sector.add_track((55, 75), r_pad_ratio=0.1) + track2.axis() + track2.scatter(x, y) + # Plot bars + track3 = sector.add_track((30, 50), r_pad_ratio=0.1) + track3.axis() + track3.bar(x, y) + +# Plot links +circos.link(("A", 0, 3), ("B", 15, 12)) +circos.link(("B", 0, 3), ("C", 7, 11), color="skyblue") +circos.link(("C", 2, 5), ("E", 15, 12), color="chocolate", direction=1) +circos.link(("D", 3, 5), ("D", 18, 15), color="lime", ec="black", lw=0.5, hatch="//", direction=2) +circos.link(("D", 8, 10), ("E", 2, 8), color="violet", ec="red", lw=1.0, ls="dashed") + +circos.savefig("example01.png") +``` + +```bash +python example1.py +``` From 4903747cc4765df30f376b1f1ac2d7dac78ba0db Mon Sep 17 00:00:00 2001 From: Kincekara Date: Tue, 1 Oct 2024 19:22:39 +0000 Subject: [PATCH 30/92] adds elgato 1.20.0 --- README.md | 2 +- elgato/1.20.0/Dockerfile | 55 ++++++++++++++++++++++++++++++++++++++++ elgato/1.20.0/README.md | 33 ++++++++++++++++++++++++ 3 files changed, 89 insertions(+), 1 deletion(-) create mode 100644 elgato/1.20.0/Dockerfile create mode 100644 elgato/1.20.0/README.md diff --git a/README.md b/README.md index c6fa34688..d50c41eab 100644 --- a/README.md +++ b/README.md @@ -153,7 +153,7 @@ To learn more about the docker pull rate limits and the open source software pro | [dragonflye](https://hub.docker.com/r/staphb/dragonflye)
[![docker pulls](https://badgen.net/docker/pulls/staphb/dragonflye)](https://hub.docker.com/r/staphb/dragonflye) |
  • [1.0.14](./dragonflye/1.0.14/)
  • [1.1.1](./dragonflye/1.1.1/)
  • [1.1.2](./dragonflye/1.1.2/)
  • [1.2.0](./dragonflye/1.2.0/)
  • [1.2.1](./dragonflye/1.2.1/)
| https://github.com/rpetit3/dragonflye | | [Dr. PRG ](https://hub.docker.com/r/staphb/drprg)
[![docker pulls](https://badgen.net/docker/pulls/staphb/drprg)](https://hub.docker.com/r/staphb/drprg) |
  • [0.1.1](drprg/0.1.1/)
| https://mbh.sh/drprg/ | | [DSK](https://hub.docker.com/r/staphb/dsk)
[![docker pulls](https://badgen.net/docker/pulls/staphb/dsk)](https://hub.docker.com/r/staphb/dsk) |
  • [0.0.100](./dsk/0.0.100/)
  • [2.3.3](./dsk/2.3.3/)
| https://gatb.inria.fr/software/dsk/ | -| [el_gato](https://hub.docker.com/r/staphb/elgato)
[![docker pulls](https://badgen.net/docker/pulls/staphb/elgato)](https://hub.docker.com/r/staphb/elgato) |
  • [1.15.2](./elgato/1.15.2)
  • [1.18.2](./elgato/1.18.2)
  • [1.19.0](./elgato/1.19.0)
| https://github.com/appliedbinf/el_gato | +| [el_gato](https://hub.docker.com/r/staphb/elgato)
[![docker pulls](https://badgen.net/docker/pulls/staphb/elgato)](https://hub.docker.com/r/staphb/elgato) |
  • [1.15.2](./elgato/1.15.2)
  • [1.18.2](./elgato/1.18.2)
  • [1.19.0](./elgato/1.19.0)
    • [1.20.0](./elgato/1.20.0)
| https://github.com/appliedbinf/el_gato | | [emboss](https://hub.docker.com/r/staphb/emboss)
[![docker pulls](https://badgen.net/docker/pulls/staphb/emboss)](https://hub.docker.com/r/staphb/emboss) |
  • 6.6.0 (no version)
| http://emboss.sourceforge.net | | [emmtyper](https://hub.docker.com/r/staphb/emmtyper)
[![docker pulls](https://badgen.net/docker/pulls/staphb/emmtyper)](https://hub.docker.com/r/staphb/emmtyper) |
  • 0.2.0
| https://github.com/MDU-PHL/emmtyper | | [emm-typing-tool](https://hub.docker.com/r/staphb/emm-typing-tool)
[![docker pulls](https://badgen.net/docker/pulls/staphb/emm-typing-tool)](https://hub.docker.com/r/staphb/emm-typing-tool) |
  • 0.0.1 (no version)
| https://github.com/phe-bioinformatics/emm-typing-tool | diff --git a/elgato/1.20.0/Dockerfile b/elgato/1.20.0/Dockerfile new file mode 100644 index 000000000..7d8aa1611 --- /dev/null +++ b/elgato/1.20.0/Dockerfile @@ -0,0 +1,55 @@ +FROM staphb/ispcr:33 as app + +ARG ELGATO_VER="1.20.0" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="el_gato" +LABEL software.version="${ELGATO_VER}" +LABEL description="Epidemiology of Legionella : Genome-bAsed Typing" +LABEL website="https://github.com/appliedbinf/el_gato" +LABEL license="https://github.com/appliedbinf/el_gato/blob/main/LICENSE" +LABEL maintainer="Kutluhan Incekara" +LABEL maintainer.email="kutluhan.incekara@ct.gov" + +WORKDIR / + +# dependencies +RUN apt-get update && apt-get install --no-install-recommends -y \ + wget \ + python3-pip \ + minimap2 \ + samtools \ + ncbi-blast+ && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# install el_gato +RUN wget --no-check-certificate https://github.com/appliedbinf/el_gato/archive/refs/tags/${ELGATO_VER}.tar.gz &&\ + tar -xvf ${ELGATO_VER}.tar.gz && rm ${ELGATO_VER}.tar.gz &&\ + cd el_gato-${ELGATO_VER} &&\ + python3 -m pip install . -vv --no-cache-dir &&\ + mv ./el_gato/db/ /usr/local/bin/db/ + +# install fpd2 for pdf reports +RUN pip install --no-cache-dir fpdf2 packaging + +ENV LC_ALL=C + +CMD el_gato.py -h + +WORKDIR /data + +## Test ## +FROM app as test + +RUN apt-get update && apt-get install unzip + +# download Legionella pneumophila ST62 genome +RUN wget -P /usr/local/bin/ https://ftp.ncbi.nlm.nih.gov/pub/datasets/command-line/v2/linux-amd64/datasets &&\ + chmod 755 /usr/local/bin/datasets &&\ + datasets download genome accession GCF_900119765.1 --include genome &&\ + unzip -j ncbi_dataset.zip ncbi_dataset/data/GCF_900119765.1/GCF_900119765.1_2532STDY5467631_genomic.fna -d . + +# test el_gato +RUN el_gato.py --assembly GCF_900119765.1_2532STDY5467631_genomic.fna --out test/ &&\ + cat test/run.log diff --git a/elgato/1.20.0/README.md b/elgato/1.20.0/README.md new file mode 100644 index 000000000..8a83429f7 --- /dev/null +++ b/elgato/1.20.0/README.md @@ -0,0 +1,33 @@ +# el_gato container + +Main tool: [el_gato](https://github.com/appliedbinf/el_gato) + +Code repository: https://github.com/appliedbinf/el_gato + +Additional tools: +- minimap2: 2.24-r1122 +- samtools: 1.13 +- ncbi-blast+: 2.12.0+ +- isPCR: v33x2 + +Basic information on how to use this tool: +- executable: el_gato.py +- help: -h +- version: -v +- description: Epidemiology of Legionella : Genome-bAsed Typing + +Additional information: + +Container contains necessary database of Legionella sequence types + +Full documentation: https://github.com/appliedbinf/el_gato + +## Example Usage + +```bash +# Paired-end: +el_gato.py --read1 read1.fastq.gz --read2 read2.fastq.gz --out output_folder/ + +# Assembly: +el_gato.py --assembly assembly_file.fna --out output_folder/ +``` \ No newline at end of file From d3b662d1f24cc67265a06e833d38e3e245c89b24 Mon Sep 17 00:00:00 2001 From: Young Date: Wed, 2 Oct 2024 10:32:39 -0600 Subject: [PATCH 31/92] adding ppanggolin version 2.1.2 (#1065) * adding ppanggolin version 2.1.2 * Force micromamba cleaning --- README.md | 2 +- ppanggolin/2.1.2/Dockerfile | 51 +++++++++++++++++++++++++++++++++++++ ppanggolin/2.1.2/README.md | 33 ++++++++++++++++++++++++ 3 files changed, 85 insertions(+), 1 deletion(-) create mode 100644 ppanggolin/2.1.2/Dockerfile create mode 100644 ppanggolin/2.1.2/README.md diff --git a/README.md b/README.md index 04e51a90f..1a93a29de 100644 --- a/README.md +++ b/README.md @@ -246,7 +246,7 @@ To learn more about the docker pull rate limits and the open source software pro | [polypolish](https://hub.docker.com/r/staphb/polypolish/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/polypolish)](https://hub.docker.com/r/staphb/polypolish) |
  • [0.5.0](./polypolish/0.5.0/)
  • [0.6.0](./polypolish/0.6.0/)
| https://github.com/rrwick/Polypolish | | [PopPUNK](https://hub.docker.com/r/staphb/poppunk/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/poppunk)](https://hub.docker.com/r/staphb/poppunk) |
  • [2.4.0](./poppunk/2.4.0/)
  • [2.5.0](./poppunk/2.5.0/)
  • [2.6.0](./poppunk/2.6.0/)
  • [2.6.2](./poppunk/2.6.2/)
  • [2.6.3](./poppunk/2.6.3/)
  • [2.6.5](./poppunk/2.6.5/)
| https://github.com/bacpop/PopPUNK | | [Porechop](https://hub.docker.com/r/staphb/porechop/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/porechop)](https://hub.docker.com/r/staphb/porechop) |
  • 0.2.4
| https://github.com/rrwick/Porechop | -| [PPanGGOLiN](https://hub.docker.com/r/staphb/ppanggolin/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ppanggolin)](https://hub.docker.com/r/staphb/ppanggolin) |
  • [1.2.105](./ppanggolin/1.2.105/)
  • [2.0.3](./ppanggolin/2.0.3/)
  • [2.0.5](./ppanggolin/2.0.5/)
| https://github.com/labgem/PPanGGOLiN | +| [PPanGGOLiN](https://hub.docker.com/r/staphb/ppanggolin/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ppanggolin)](https://hub.docker.com/r/staphb/ppanggolin) |
  • [1.2.105](./ppanggolin/1.2.105/)
  • [2.0.3](./ppanggolin/2.0.3/)
  • [2.0.5](./ppanggolin/2.0.5/)
  • [2.1.2](./ppanggolin/2.1.2/)
| https://github.com/labgem/PPanGGOLiN | | [Prokka](https://hub.docker.com/r/staphb/prokka/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/prokka)](https://hub.docker.com/r/staphb/prokka) |
  • 1.13.4
  • 1.14.0
  • 1.14.5
  • 1.14.6
| https://github.com/tseemann/prokka | | [pyCirclize](https://hub.docker.com/r/staphb/pycirclize/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pycirclize)](https://hub.docker.com/r/staphb/pycirclize) |
  • [1.0.0](pycirclize/1.0.0/)
  • [1.2.0](./pycirclize/1.2.0/)
  • [1.5.0](./pycirclize/1.5.0/)
  • [1.6.0](./pycirclize/1.6.0/)
  • [1.71](./pycirclize/1.7.1/)
| https://github.com/moshi4/pyCirclize | | [pyGenomeViz](https://hub.docker.com/r/staphb/pygenomeviz/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pygenomeviz)](https://hub.docker.com/r/staphb/pygenomeviz) |
  • 0.2.2
  • 0.3.2
  • [0.4.2](pygenomeviz/0.4.2/)
  • [0.4.3](pygenomeviz/0.4.3/)
  • [0.4.4](pygenomeviz/0.4.4/)
  • [1.1.0](pygenomeviz/1.1.0/)
| https://github.com/moshi4/pyGenomeViz | diff --git a/ppanggolin/2.1.2/Dockerfile b/ppanggolin/2.1.2/Dockerfile new file mode 100644 index 000000000..2496adc96 --- /dev/null +++ b/ppanggolin/2.1.2/Dockerfile @@ -0,0 +1,51 @@ +ARG PPANGGOLIN_VER="2.1.2" + +FROM mambaorg/micromamba:1.5.8 as app + +ARG PPANGGOLIN_VER + +# 'LABEL' instructions tag the image with metadata that might be important to the user +LABEL base.image="mambaorg/micromamba:1.5.8" +LABEL dockerfile.version="1" +LABEL software="PPanGGOLiN" +LABEL software.version="${PPANGGOLIN_VER}" +LABEL description="Depicting microbial species diversity via a Partitioned PanGenome Graph Of Linked Neighbors" +LABEL website="https://github.com/labgem/PPanGGOLiN" +LABEL license="https://github.com/labgem/PPanGGOLiN/blob/master/LICENSE.txt" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" + +USER root + +RUN apt-get update && apt-get install -y --no-install-recommends \ + ca-certificates \ + procps \ + wget && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +ENV PATH="/opt/conda/envs/base/bin/:/opt/conda/bin/:$PATH" LC_ALL=C + +RUN micromamba install --name base -c conda-forge -c bioconda -c defaults ppanggolin=${PPANGGOLIN_VER} && \ + micromamba clean -a -f -y + +# 'CMD' instructions set a default command when the container is run. This is typically 'tool --help.' +CMD ppanggolin -h + +# 'WORKDIR' sets working directory +WORKDIR /data + +FROM app as test + +ARG PPANGGOLIN_VER + +WORKDIR /test + +RUN ppanggolin --help && \ + ppanggolin --version + +# getting test files from github repo +RUN wget -q https://github.com/labgem/PPanGGOLiN/archive/refs/tags/${PPANGGOLIN_VER}.tar.gz && \ + tar -xvf ${PPANGGOLIN_VER}.tar.gz + +RUN cd PPanGGOLiN-${PPANGGOLIN_VER}/testingDataset && \ + ppanggolin all --fasta genomes.fasta.list --output output diff --git a/ppanggolin/2.1.2/README.md b/ppanggolin/2.1.2/README.md new file mode 100644 index 000000000..ad910731d --- /dev/null +++ b/ppanggolin/2.1.2/README.md @@ -0,0 +1,33 @@ +# PPanGGOLiN container + +Main tool: [PPanGGOLiN](https://github.com/labgem/PPanGGOLiN) + +Code repository: https://github.com/labgem/PPanGGOLiN + +Basic information on how to use this tool: +- executable: ppanggolin +- help: --help +- version: --version +- description: | +> PPanGGOLiN builds pangenomes through a graphical model and a statistical method to partition gene families in persistent, shell and cloud genomes. + +Additional information: + +PPanGGOLiN only creates the pangenome graphs. It is recommended to use another tool to visualize them. Please read https://github.com/labgem/PPanGGOLiN/wiki for more information. + +Full documentation: https://github.com/labgem/PPanGGOLiN/wiki + +## Example Usage + +```bash +ppanggolin annotate --fasta organisms.fasta.list --output output + +# many of the commands manipulate the 'pangenome.h5' file in place +ppanggolin cluster -p pangenome.h5 +ppanggolin graph -p pangenome.h5 +ppanggolin partition -p pangenome.h5 +ppanggolin draw -p pangenome.h5 --ucurve + +# there are some human-readable files that can be generated as well +ppanggolin write -p pangenome.h5 --stats --output stats +``` From a85d15d33d8f7a1d562d2ac4d6f13fb975b3357e Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 2 Oct 2024 13:12:58 -0400 Subject: [PATCH 32/92] adding tests data for seqfu in dockerfile --- seqfu/1.20.3/Dockerfile | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index 76a7ad9b8..68f2b92ec 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -59,6 +59,8 @@ COPY --from=builder /usr/local/bin /usr/local/bin # Install minimal runtime dependencies RUN apt-get update && apt-get install -y --no-install-recommends \ curl \ + git \ + ca-certificates \ wget && \ rm -rf /var/lib/apt/lists/* @@ -69,3 +71,26 @@ WORKDIR /data RUN ls -l /usr/local/bin && \ seqfu --version && seqfu --help +# Running RDP on test controls +FROM app AS test + +RUN mkdir tests && cd tests && \ + wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_1.fastq.gz && \ + wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_2.fastq.gz && \ + seqfu check SRR13957123_1.fastq.gz SRR13957123_2.fastq.gz && \ + seqfu count -f SRR13957123_1.fastq.gz -r SRR13957123_2.fastq.gz + + +# RUN wget -q https://github.com/telatin/seqfu2/blob/main/data/tests/sample1_1.fq && \ +# wget -q https://github.com/telatin/seqfu2/blob/main/data/tests/sample1_2.fq && \ +# seqfu count -f sample1_1.fq -r sample1_2.fq + +# RUN wget -q https://github.com/telatin/seqfu2/blob/main/data/tests/sample1_R1.fq && \ +# wget -q https://github.com/telatin/seqfu2/blob/main/data/tests/sample1_R2.fq && \ +# seqfu count -f sample1_R1.fq -r sample1_R2.fq + + + + + + From 183227580de4f4bb2bc3898cddfa2d29a3b6fa2a Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 2 Oct 2024 13:15:43 -0400 Subject: [PATCH 33/92] updating test data in seqfu dockerfile --- seqfu/1.20.3/Dockerfile | 18 ------------------ 1 file changed, 18 deletions(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index 68f2b92ec..8fcf217c0 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -71,26 +71,8 @@ WORKDIR /data RUN ls -l /usr/local/bin && \ seqfu --version && seqfu --help -# Running RDP on test controls -FROM app AS test - RUN mkdir tests && cd tests && \ wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_1.fastq.gz && \ wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_2.fastq.gz && \ seqfu check SRR13957123_1.fastq.gz SRR13957123_2.fastq.gz && \ seqfu count -f SRR13957123_1.fastq.gz -r SRR13957123_2.fastq.gz - - -# RUN wget -q https://github.com/telatin/seqfu2/blob/main/data/tests/sample1_1.fq && \ -# wget -q https://github.com/telatin/seqfu2/blob/main/data/tests/sample1_2.fq && \ -# seqfu count -f sample1_1.fq -r sample1_2.fq - -# RUN wget -q https://github.com/telatin/seqfu2/blob/main/data/tests/sample1_R1.fq && \ -# wget -q https://github.com/telatin/seqfu2/blob/main/data/tests/sample1_R2.fq && \ -# seqfu count -f sample1_R1.fq -r sample1_R2.fq - - - - - - From 8d846457862d3ea7adbe4f2c66a2cd17cf8062c6 Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 2 Oct 2024 13:22:10 -0400 Subject: [PATCH 34/92] updating seqfu tests in dockerfile --- seqfu/1.20.3/Dockerfile | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index 8fcf217c0..64338ca30 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -71,8 +71,12 @@ WORKDIR /data RUN ls -l /usr/local/bin && \ seqfu --version && seqfu --help +# Running seqfu on test staph-b test dataset +FROM app AS test + RUN mkdir tests && cd tests && \ wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_1.fastq.gz && \ wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_2.fastq.gz && \ - seqfu check SRR13957123_1.fastq.gz SRR13957123_2.fastq.gz && \ - seqfu count -f SRR13957123_1.fastq.gz -r SRR13957123_2.fastq.gz + seqfu check SRR13957123_1.fastq.gz SRR13957123_2.fastq.gz > seqfu_check_test.txt && \ + seqfu count -f SRR13957123_1.fastq.gz -r SRR13957123_2.fastq.gz > seqfu_count_test.txt + From 1581984f6471c0fd9dedfa7bbbb7c1e64b2fd2cb Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 2 Oct 2024 13:36:23 -0400 Subject: [PATCH 35/92] fixing seqfu dockerfile labels for staph-b template --- seqfu/1.20.3/Dockerfile | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index 64338ca30..3cdf718a8 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -6,15 +6,15 @@ FROM ubuntu:focal AS builder ARG SEQFU_VER # Metadata -LABEL base.image="ubuntu:focal" \ - dockerfile.version="1" \ - software="SeqFu" \ - software.version="${SEQFU_VER}" \ - description="A general-purpose program to manipulate and parse information from FASTA/FASTQ files, supporting gzipped input files." \ - website="https://github.com/telatin/seqfu2" \ - license.url="https://github.com/telatin/seqfu2?tab=GPL-3.0-1-ov-file#readme" \ - maintainer="Taylor K. Paisie" \ - maintainer.email="ltj8@cdc.gov" +LABEL base.image="ubuntu:focal" +LABEL dockerfile.version="1" +LABEL software="SeqFu" +LABEL software.version="${SEQFU_VER}" +LABEL description="A general-purpose program to manipulate and parse information from FASTA/FASTQ files, supporting gzipped input files." +LABEL website="https://github.com/telatin/seqfu2" +LABEL license.url="https://github.com/telatin/seqfu2?tab=GPL-3.0-1-ov-file#readme" +LABEL maintainer="Taylor K. Paisie" +LABEL maintainer.email="ltj8@cdc.gov" # Set non-interactive frontend and update PATH ENV DEBIAN_FRONTEND=noninteractive \ From d982925aa369d22cdd7f8495cc75f9dfd14ddd1f Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 2 Oct 2024 13:48:59 -0400 Subject: [PATCH 36/92] making edits to seqfu test in dockerfile --- seqfu/1.20.3/Dockerfile | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index 3cdf718a8..c2a597be1 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -64,8 +64,8 @@ RUN apt-get update && apt-get install -y --no-install-recommends \ wget && \ rm -rf /var/lib/apt/lists/* -# Set working directory -WORKDIR /data + + # Verify installation RUN ls -l /usr/local/bin && \ @@ -74,9 +74,11 @@ seqfu --version && seqfu --help # Running seqfu on test staph-b test dataset FROM app AS test -RUN mkdir tests && cd tests && \ - wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_1.fastq.gz && \ +WORKDIR /data/test + +RUN wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_1.fastq.gz && \ wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_2.fastq.gz && \ seqfu check SRR13957123_1.fastq.gz SRR13957123_2.fastq.gz > seqfu_check_test.txt && \ seqfu count -f SRR13957123_1.fastq.gz -r SRR13957123_2.fastq.gz > seqfu_count_test.txt +WORKDIR /data From a63df03e33ba70b31d52ebbd8861ba33b32c2f9a Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 2 Oct 2024 13:51:28 -0400 Subject: [PATCH 37/92] updating seqfu docker container readme --- seqfu/1.20.3/README.md | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/seqfu/1.20.3/README.md b/seqfu/1.20.3/README.md index 98d5794f9..e8e7fbbb5 100644 --- a/seqfu/1.20.3/README.md +++ b/seqfu/1.20.3/README.md @@ -37,10 +37,16 @@ Full documentation: https://telatin.github.io/seqfu2/ # Testing SeqFU analysis ``` +wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_1.fastq.gz + +wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_2.fastq.gz + seqfu check \ - --deep \ - --verbose \ - /root/seqfu2-1.20.3/data/tests/sample1_R1.fq \ - /root/seqfu2-1.20.3/data/tests/sample1_R2.fq + SRR13957123_1.fastq.gz \ + SRR13957123_2.fastq.gz + +seqfu count \ + -f SRR13957123_1.fastq.gz \ + -r SRR13957123_2.fastq.gz ``` From 43978a71e924ec3c2c9c3def34b633fc2e7950e6 Mon Sep 17 00:00:00 2001 From: taylorpaisie Date: Wed, 2 Oct 2024 13:58:13 -0400 Subject: [PATCH 38/92] cleaning up seqfu dockerfile --- seqfu/1.20.3/Dockerfile | 2 -- 1 file changed, 2 deletions(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index c2a597be1..5fd1080a6 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -64,8 +64,6 @@ RUN apt-get update && apt-get install -y --no-install-recommends \ wget && \ rm -rf /var/lib/apt/lists/* - - # Verify installation RUN ls -l /usr/local/bin && \ From 1b1972df5d08d6c1112704785f94aee68a0de0bf Mon Sep 17 00:00:00 2001 From: Young Date: Wed, 2 Oct 2024 13:24:20 -0600 Subject: [PATCH 39/92] adding pbptyper version 2.0.0 (#1064) * adding pbptyper version 2.0.0 * fixed labels * force clean micromamba layer and move --help to test --- README.md | 2 +- pbptyper/2.0.0/Dockerfile | 104 ++++++++++++++++++++++++++++++++++++++ pbptyper/2.0.0/README.md | 31 ++++++++++++ 3 files changed, 136 insertions(+), 1 deletion(-) create mode 100644 pbptyper/2.0.0/Dockerfile create mode 100644 pbptyper/2.0.0/README.md diff --git a/README.md b/README.md index 1a93a29de..44c13ca56 100644 --- a/README.md +++ b/README.md @@ -232,7 +232,7 @@ To learn more about the docker pull rate limits and the open source software pro | [pasty](https://hub.docker.com/r/staphb/pasty)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pasty)](https://hub.docker.com/r/staphb/pasty) |
  • 1.0.2
  • [1.0.3](pasty/1.0.3/)
  • [2.2.1](./pasty/2.2.1/)
| https://github.com/rpetit3/pasty | | [pbmm2](https://hub.docker.com/r/staphb/pbmm2)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pbmm2)](https://hub.docker.com/r/staphb/pbmm2) |
  • [1.13.1](./pbmm2/1.13.1/)
| https://github.com/PacificBiosciences/pbmm2 | | [Pavian](https://hub.docker.com/r/staphb/pavian)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pavian)](https://hub.docker.com/r/staphb/pavian) |
  • [1.2.1](pavian/1.2.1/)
| https://github.com/fbreitwieser/pavian | -| [pbptyper](https://hub.docker.com/r/staphb/pbptyper)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pbptyper)](https://hub.docker.com/r/staphb/pbptyper) |
  • 1.0.0
  • 1.0.1
  • 1.0.4
| https://github.com/rpetit3/pbptyper | +| [pbptyper](https://hub.docker.com/r/staphb/pbptyper)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pbptyper)](https://hub.docker.com/r/staphb/pbptyper) |
  • [1.0.0](./pbptyper/1.0.0/)
  • [1.0.1](./pbptyper/1.0.0/)
  • [1.0.4](./pbptyper/1.0.4/)
  • [2.0.0](./pbptyper/2.0.0/)
| https://github.com/rpetit3/pbptyper | | [pbtk](https://hub.docker.com/r/staphb/pbtk)
[![docker pulls](https://badgen.net/docker/pulls/staphb/pbtk)](https://hub.docker.com/r/staphb/pbtk) |
  • [3.1.1](./pbtk/3.1.1/)
| https://github.com/PacificBiosciences/pbtk | | [Phyml](https://hub.docker.com/r/staphb/phyml)
[![docker pulls](https://badgen.net/docker/pulls/staphb/phyml)](https://hub.docker.com/r/staphb/phyml) |
  • 3.3.20220408
| https://github.com/stephaneguindon/phyml | | [phyTreeViz](https://hub.docker.com/r/staphb/phytreeviz)
[![docker pulls](https://badgen.net/docker/pulls/staphb/phytreeviz)](https://hub.docker.com/r/staphb/phytreeviz) |
  • [0.1.0](./phytreeviz/0.1.0/)
  • [0.2.0](./phytreeviz/0.2.0/)
| https://github.com/moshi4/phyTreeViz/ | diff --git a/pbptyper/2.0.0/Dockerfile b/pbptyper/2.0.0/Dockerfile new file mode 100644 index 000000000..1915213c3 --- /dev/null +++ b/pbptyper/2.0.0/Dockerfile @@ -0,0 +1,104 @@ +ARG PBPTYPER_VERSION="2.0.0" + +FROM mambaorg/micromamba:1.5.8 as app + +# Version arguments +# ARG variables only persist during build time +ARG PBPTYPER_VERSION + +# build and run as root users since micromamba image has 'mambauser' set as the $USER +USER root +# set workdir to default for building; set to /data at the end +WORKDIR / + +LABEL base.image="mambaorg/micromamba:1.5.8" +LABEL dockerfile.version="1" +LABEL software="pbptyper" +LABEL software.version="${PBPTYPER_VERSION}" +LABEL description="In silico Penicillin Binding Protein (PBP) typer for Streptococcus pneumoniae assemblies" +LABEL website="https://github.com/rpetit3/pbptyper" +LABEL license="https://github.com/rpetit3/pbptyper/blob/main/LICENSE" +LABEL maintainer="Curtis Kapsak" +LABEL maintainer.email="curtis.kapsak@theiagen.com" + +# install dependencies; cleanup apt garbage +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + procps && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# Install pbptyper into the base conda/micromamba environment, pinning the version +# clean up conda garbage +RUN micromamba install --name base -c conda-forge -c bioconda -c defaults pbptyper=${PBPTYPER_VERSION} && \ + micromamba clean -a -f -y + +# set the environment, add base conda/micromamba bin directory into path +# set locale settings to UTF-8 +ENV PATH="/opt/conda/bin/:${PATH}" \ + LC_ALL=C.UTF-8 + +# set final working directory to /data +WORKDIR /data + +CMD pbptyper --help + +# new base for testing +FROM app as test + +ARG PBPTYPER_VERSION + +RUN pbptyper --help && \ + pbptyper --version + +# so that all test inputs & outputs are kept in /test +WORKDIR /test + +# download test data from pbptyper repo +RUN wget -q https://github.com/rpetit3/pbptyper/archive/refs/tags/v${PBPTYPER_VERSION}.tar.gz && \ + tar -vxf v${PBPTYPER_VERSION}.tar.gz + +# shamelessly stolen and modified from https://github.com/rpetit3/pbptyper/blob/main/.github/workflows/test-pbptyper.yml (again) +RUN cd pbptyper-${PBPTYPER_VERSION} && \ + echo "ERR1065617" && \ + pbptyper --yaml data/pbptyper.yaml --targets data/pbptyper.fasta --input test/ERR1065617.fna.gz --prefix ERR1065617 && \ + cat ERR1065617.tsv && \ + head ERR1065617.tblastn.tsv && \ + echo "SRR2912551" && \ + pbptyper --yaml data/pbptyper.yaml --targets data/pbptyper.fasta --input test/SRR2912551.fna.gz --prefix SRR2912551 && \ + cat SRR2912551.tsv && \ + head SRR2912551.tblastn.tsv && \ + echo "SRR8654742" && \ + pbptyper --yaml data/pbptyper.yaml --targets data/pbptyper.fasta --input test/SRR8654742.fna --prefix SRR8654742 --outdir SRR8654742 && \ + cat SRR8654742/SRR8654742.tsv && \ + head SRR8654742/SRR8654742.tblastn.tsv && \ + echo "S. pseudopneumoniae" && \ + pbptyper --yaml data/pbptyper.yaml --targets data/pbptyper.fasta --input test/spseudopneumoniae.fna.gz --prefix spseudopneumoniae --outdir spseudopneumoniae && \ + cat spseudopneumoniae/spseudopneumoniae.tsv && \ + head spseudopneumoniae/spseudopneumoniae.tblastn.tsv && \ + echo "S. mitis" && \ + pbptyper --yaml data/pbptyper.yaml --targets data/pbptyper.fasta --input test/smitis.fna.gz --prefix smitis --outdir smitis && \ + cat smitis/smitis.tsv && \ + head smitis/smitis.tblastn.tsv && \ + echo "S. suis" && \ + pbptyper --yaml data/pbptyper.yaml --targets data/pbptyper.fasta --input test/ssuis.fna.gz --prefix ssuis --outdir ssuis && \ + cat ssuis/ssuis.tsv && \ + head ssuis/ssuis.tblastn.tsv && \ + echo "not-spn" && \ + pbptyper --yaml data/pbptyper.yaml --targets data/pbptyper.fasta --input test/not-spn.fna.gz --prefix not-spn && \ + cat not-spn.tsv && \ + head not-spn.tblastn.tsv && \ + echo "not-a-fasta" && \ + pbptyper --yaml data/pbptyper.yaml --targets data/pbptyper.fasta --input test/not-a-fasta.fasta --prefix not-a-fasta && \ + cat not-a-fasta.tsv && \ + head not-a-fasta.tblastn.tsv && \ + echo "poor" && \ + pbptyper --yaml data/pbptyper.yaml --targets data/pbptyper.fasta --input test/poor.fasta --prefix poor --outdir poor && \ + cat poor/poor.tsv && \ + head poor/poor.tblastn.tsv + +RUN cd pbptyper-${PBPTYPER_VERSION} && \ + echo "ERR1065617 again" && \ + pbptyper --input test/ERR1065617.fna.gz --prefix ERR1065617_2 && \ + cat ERR1065617_2.tsv && \ + head ERR1065617_2.tblastn.tsv diff --git a/pbptyper/2.0.0/README.md b/pbptyper/2.0.0/README.md new file mode 100644 index 000000000..95e8506cd --- /dev/null +++ b/pbptyper/2.0.0/README.md @@ -0,0 +1,31 @@ +# pbptyper container + +Main tool : [pbptyper](https://github.com/rpetit3/pbptyper) + +Full documentation: [https://github.com/rpetit3/pbptyper](https://github.com/rpetit3/pbptyper) + +In silico Penicillin Binding Protein (PBP) typer for Streptococcus pneumoniae assemblies + +## Example Usage + +```bash +# run pbptyper on an test S. pneumo assembly included with pbptyper +# WARNING: test data no longer included in docker image, visit here to get test data: https://github.com/rpetit3/pbptyper/tree/main/test +$ pbptyper --input SRR2912551.fna.gz --prefix SRR2912551 --db /pbptyper-*/db/ --outdir /SRR2912551-pbptyper-test +Running TBLASTN for 1A... +TBLASTN results written to /SRR2912551-pbptyper-test/SRR2912551-1A.tblastn.tsv + +Running TBLASTN for 2B... +TBLASTN results written to /SRR2912551-pbptyper-test/SRR2912551-2B.tblastn.tsv + +Running TBLASTN for 2X... +TBLASTN results written to /SRR2912551-pbptyper-test/SRR2912551-2X.tblastn.tsv + + Predicted PBP Type +┏━━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━┓ +┃ sample ┃ pbptype ┃ 1A_coverage ┃ 1A_pident ┃ 2B_coverage ┃ 2B_pident ┃ 2X_coverage ┃ 2X_pident ┃ +┡━━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━┩ +│ SRR2912551 │ 23:0:2 │ 100 │ 100.000 │ 100 │ 100.000 │ 100 │ 100.000 │ +└────────────┴─────────┴─────────────┴───────────┴─────────────┴───────────┴─────────────┴───────────┘ +Predicted pbp type result written to /SRR2912551-pbptyper-test/SRR2912551.tsv +``` From 010a27498f176241570534005e9156d9ffd3912b Mon Sep 17 00:00:00 2001 From: Young Date: Thu, 3 Oct 2024 07:35:30 -0600 Subject: [PATCH 40/92] Update medaka to version 2.0.0 (#1053) * adding medaka verison 2.0.0 * adding cpu version of 2.0.0 * Update Dockerfile * Adding MEDAKA_VER and PYABPOA_VER to pip install lines * Added pyabpoa --- README.md | 2 +- medaka/2.0.0/Dockerfile | 158 ++++++++++++++++++++++++++++++++++++++++ medaka/2.0.0/README.md | 35 +++++++++ 3 files changed, 194 insertions(+), 1 deletion(-) create mode 100644 medaka/2.0.0/Dockerfile create mode 100644 medaka/2.0.0/README.md diff --git a/README.md b/README.md index 44c13ca56..aa523c911 100644 --- a/README.md +++ b/README.md @@ -206,7 +206,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Mash](https://hub.docker.com/r/staphb/mash/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/mash)](https://hub.docker.com/r/staphb/mash) |
  • 2.1
  • 2.2
  • 2.3
| https://github.com/marbl/Mash | | [mashtree](https://hub.docker.com/r/staphb/mashtree)
[![docker pulls](https://badgen.net/docker/pulls/staphb/mashtree)](https://hub.docker.com/r/staphb/mashtree) |
  • [0.52.0](./mashtree/0.52.0/)
  • [0.57.0](./mashtree/0.57.0/)
  • [1.0.4](./mashtree/1.0.4/)
  • [1.2.0](./mashtree/1.2.0/)
  • [1.4.6](./mashtree/1.4.6/)
| https://github.com/lskatz/mashtree | | [MaSuRCA](https://hub.docker.com/r/staphb/masurca)
[![docker pulls](https://badgen.net/docker/pulls/staphb/masurca)](https://hub.docker.com/r/staphb/masurca) |
  • 4.0.8
  • 4.0.9
  • 4.1.0
| https://github.com/alekseyzimin/masurca | -| [medaka](https://hub.docker.com/r/staphb/medaka)
[![docker pulls](https://badgen.net/docker/pulls/staphb/medaka)](https://hub.docker.com/r/staphb/medaka) |
  • 0.8.1
  • 1.0.1
  • 1.2.0
| https://github.com/nanoporetech/medaka | +| [medaka](https://hub.docker.com/r/staphb/medaka)
[![docker pulls](https://badgen.net/docker/pulls/staphb/medaka)](https://hub.docker.com/r/staphb/medaka) |
  • [0.8.1](./medaka/0.8.1/)
  • [1.0.1](./medaka/1.0.1/)
  • [1.2.0](./medaka/1.2.0/)
  • [2.0.0](./medaka/2.0.0/)
| https://github.com/nanoporetech/medaka | | [metaphlan](https://hub.docker.com/r/staphb/metaphlan)
[![docker pulls](https://badgen.net/docker/pulls/staphb/metaphlan)](https://hub.docker.com/r/staphb/metaphlan) |
  • [3.0.3-no-db (no database)](./metaphlan/3.0.3-no-db/)
  • [3.0.3 (~3GB db)](./metaphlan/3.0.3/)
  • [4.1.0](./metaphlan/4.1.0/) (no database)
  • [4.1.1](./metaphlan/4.1.1/) (no database)
| https://github.com/biobakery/MetaPhlAn | | [MIDAS](https://hub.docker.com/r/staphb/midas)
[![docker pulls](https://badgen.net/docker/pulls/staphb/midas)](https://hub.docker.com/r/staphb/midas) |
  • 1.3.2 (no database)
    • | https://github.com/snayfach/MIDAS | | [minimap2](https://hub.docker.com/r/staphb/minimap2)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/minimap2)](https://hub.docker.com/r/staphb/minimap2) |
    • 2.17
    • 2.18
    • 2.21
    • 2.22
    • 2.23
    • 2.24
    • 2.25
    • [2.26](./minimap2/2.26)
    • [2.27](./minimap2/2.27/)
      • li>[2.28](./minimap2/2.28/)
    | https://github.com/lh3/minimap2 | diff --git a/medaka/2.0.0/Dockerfile b/medaka/2.0.0/Dockerfile new file mode 100644 index 000000000..e874fa23e --- /dev/null +++ b/medaka/2.0.0/Dockerfile @@ -0,0 +1,158 @@ +ARG MEDAKA_VER="2.0.0" +ARG PYABPOA_VER="1.5.3" +ARG SAMTOOLS_VER="1.21" +ARG BCFTOOLS_VER=${SAMTOOLS_VER} +ARG HTSLIB_VER=${SAMTOOLS_VER} +ARG MINIMAP2_VER="2.28" + +FROM ubuntu:jammy as builder + +ARG SAMTOOLS_VER +ARG BCFTOOLS_VER +ARG HTSLIB_VER +ARG MINIMAP2_VER + +# install dependencies required for compiling samtools +ARG DEBIAN_FRONTEND=noninteractive + +RUN apt-get update && apt-get install --no-install-recommends -y \ + libncurses5-dev \ + libbz2-dev \ + liblzma-dev \ + libcurl4-gnutls-dev \ + zlib1g-dev \ + libssl-dev \ + gcc \ + wget \ + make \ + perl \ + bzip2 \ + gnuplot \ + ca-certificates \ + curl \ + perl \ + bzip2 \ + autoconf \ + automake \ + make \ + gcc \ + libdeflate-dev \ + zlib1g-dev \ + libbz2-dev \ + liblzma-dev \ + libcurl4-gnutls-dev \ + libssl-dev \ + libperl-dev \ + libgsl0-dev \ + libdeflate-dev \ + procps && \ + rm -rf /var/lib/apt/lists/* && apt-get autoclean + +# download, compile, and install bcftools +RUN wget -q https://github.com/samtools/bcftools/releases/download/${BCFTOOLS_VER}/bcftools-${BCFTOOLS_VER}.tar.bz2 && \ + tar -xjf bcftools-${BCFTOOLS_VER}.tar.bz2 && \ + rm -v bcftools-${BCFTOOLS_VER}.tar.bz2 && \ + cd bcftools-${BCFTOOLS_VER} && \ + ./configure --enable-libgsl --enable-perl-filters &&\ + make && \ + make install + +# download, compile, and install samtools +RUN wget -q https://github.com/samtools/samtools/releases/download/${SAMTOOLS_VER}/samtools-${SAMTOOLS_VER}.tar.bz2 && \ + tar -xjf samtools-${SAMTOOLS_VER}.tar.bz2 && \ + cd samtools-${SAMTOOLS_VER} && \ + ./configure && \ + make && \ + make install + +RUN wget -q https://github.com/samtools/htslib/releases/download/${HTSLIB_VER}/htslib-${HTSLIB_VER}.tar.bz2 && \ + tar -vxjf htslib-${HTSLIB_VER}.tar.bz2 && \ + rm -v htslib-${HTSLIB_VER}.tar.bz2 && \ + cd htslib-${HTSLIB_VER} && \ + ./configure && \ + make && \ + make install + +RUN curl -L https://github.com/lh3/minimap2/releases/download/v${MINIMAP2_VER}/minimap2-${MINIMAP2_VER}_x64-linux.tar.bz2 | tar -jxvf - --no-same-owner && \ + ls && \ + mv minimap2-${MINIMAP2_VER}_x64-linux/minimap2 /usr/local/bin + +### start of app stage ### +FROM ubuntu:jammy as app + +ARG MEDAKA_VER +ARG PYABPOA_VER + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version=1 +LABEL container.version="1" +LABEL software="Medaka" +LABEL software.version="${MEDAKA_VER}" +LABEL description="Consensus sequence correction provided by ONT Research" +LABEL website="https://github.com/nanoporetech/medaka" +LABEL license="https://github.com/nanoporetech/medaka/blob/master/LICENSE.md" +LABEL maintainer="Curtis Kapsak" +LABEL maintainer.email="pjx8@cdc.gov" +LABEL maintainer1="Erin Young" +LABEL maintainer1.email="eriny@utah.gov" + +ARG DEBIAN_FRONTEND=noninteractive + +# install dependencies required for running samtools +RUN apt-get update && apt-get install --no-install-recommends -y \ + perl \ + zlib1g \ + libncurses5 \ + bzip2 \ + libdeflate-dev \ + liblzma-dev \ + libcurl4-gnutls-dev \ + python3 \ + python3-pip \ + python-is-python3 \ + python3-dev \ + build-essential \ + libssl-dev \ + libffi-dev \ + libxml2-dev \ + libxslt1-dev \ + zlib1g-dev \ + libgsl-dev \ + && apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# copy in samtools, htslib, and minimap2 executables from builder stage +COPY --from=builder /usr/local/bin/* /usr/local/bin/ + +# install medaka via pip +RUN pip install medaka-cpu==${MEDAKA_VER} --extra-index-url https://download.pytorch.org/whl/cpu -vv --no-cache-dir && \ + pip install pyabpoa==${PYABPOA_VER} -vv --no-cache-dir + +ENV LC_ALL=C + +# final working directory is /data +WORKDIR /data + +# default command is to pull up help options +CMD medaka --help + +### start of test stage ### +FROM app as test + +RUN apt-get update && apt-get install --no-install-recommends -y wget + +# making sure dependencies are in path +RUN samtools --help && minimap2 --help && tabix --help && bgzip --help + +RUN medaka --help && \ + medaka --version + +# set working directory so that all test inputs & outputs are kept in /test +WORKDIR /test + +# using on real data (CRPA isolate) +RUN wget -q https://www.ebi.ac.uk/ena/browser/api/fasta/GCA_021601745.3 -O GCA_021601745.3.fasta && \ + wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR234/068/SRR23473168/SRR23473168_1.fastq.gz && \ + medaka_consensus -i SRR23473168_1.fastq.gz -d GCA_021601745.3.fasta -o testing -t 4 + +# listing available models +RUN medaka tools list\_models diff --git a/medaka/2.0.0/README.md b/medaka/2.0.0/README.md new file mode 100644 index 000000000..78b25c98c --- /dev/null +++ b/medaka/2.0.0/README.md @@ -0,0 +1,35 @@ +# medaka container + +Main tool : [medaka](https://github.com/nanoporetech/medaka) + +Additional tools: +- bcftools version 1.21 +- samtools version 1.21 +- htslib version 1.21 +- minimap2 version 2.28 +- pyabpoa verson 1.5.3 + +Full documentation: [https://github.com/nanoporetech/medaka](https://github.com/nanoporetech/medaka) + +> medaka is a tool to create consensus sequences and variant calls from nanopore sequencing data. This task is performed using neural networks applied a pileup of individual sequencing reads against a draft assembly. It provides state-of-the-art results outperforming sequence-graph based methods and signal-based methods, whilst also being faster. + +## Example Usage + +```bash + +# listing models +medaka tools list\_models + +# polishing +medaka_consensus -i sample.fastq.gz -d sample.fasta -o medaka/sample -t 4 + +``` + +## Medaka models + +Medaka updates frequently. These are the medaka models in this image: +``` +Available: r103_fast_g507, r103_fast_snp_g507, r103_fast_variant_g507, r103_hac_g507, r103_hac_snp_g507, r103_hac_variant_g507, r103_sup_g507, r103_sup_snp_g507, r103_sup_variant_g507, r1041_e82_260bps_fast_g632, r1041_e82_260bps_fast_variant_g632, r1041_e82_260bps_hac_g632, r1041_e82_260bps_hac_v4.0.0, r1041_e82_260bps_hac_v4.1.0, r1041_e82_260bps_hac_variant_g632, r1041_e82_260bps_hac_variant_v4.1.0, r1041_e82_260bps_joint_apk_ulk_v5.0.0, r1041_e82_260bps_sup_g632, r1041_e82_260bps_sup_v4.0.0, r1041_e82_260bps_sup_v4.1.0, r1041_e82_260bps_sup_variant_g632, r1041_e82_260bps_sup_variant_v4.1.0, r1041_e82_400bps_bacterial_methylation, r1041_e82_400bps_fast_g615, r1041_e82_400bps_fast_g632, r1041_e82_400bps_fast_variant_g615, r1041_e82_400bps_fast_variant_g632, r1041_e82_400bps_hac_g615, r1041_e82_400bps_hac_g632, r1041_e82_400bps_hac_v4.0.0, r1041_e82_400bps_hac_v4.1.0, r1041_e82_400bps_hac_v4.2.0, r1041_e82_400bps_hac_v4.3.0, r1041_e82_400bps_hac_v5.0.0, r1041_e82_400bps_hac_variant_g615, r1041_e82_400bps_hac_variant_g632, r1041_e82_400bps_hac_variant_v4.1.0, r1041_e82_400bps_hac_variant_v4.2.0, r1041_e82_400bps_hac_variant_v4.3.0, r1041_e82_400bps_hac_variant_v5.0.0, r1041_e82_400bps_sup_g615, r1041_e82_400bps_sup_v4.0.0, r1041_e82_400bps_sup_v4.1.0, r1041_e82_400bps_sup_v4.2.0, r1041_e82_400bps_sup_v4.3.0, r1041_e82_400bps_sup_v5.0.0, r1041_e82_400bps_sup_variant_g615, r1041_e82_400bps_sup_variant_v4.1.0, r1041_e82_400bps_sup_variant_v4.2.0, r1041_e82_400bps_sup_variant_v4.3.0, r1041_e82_400bps_sup_variant_v5.0.0, r104_e81_fast_g5015, r104_e81_fast_variant_g5015, r104_e81_hac_g5015, r104_e81_hac_variant_g5015, r104_e81_sup_g5015, r104_e81_sup_g610, r104_e81_sup_variant_g610, r941_e81_fast_g514, r941_e81_fast_variant_g514, r941_e81_hac_g514, r941_e81_hac_variant_g514, r941_e81_sup_g514, r941_e81_sup_variant_g514, r941_min_fast_g507, r941_min_fast_snp_g507, r941_min_fast_variant_g507, r941_min_hac_g507, r941_min_hac_snp_g507, r941_min_hac_variant_g507, r941_min_sup_g507, r941_min_sup_snp_g507, r941_min_sup_variant_g507, r941_prom_fast_g507, r941_prom_fast_snp_g507, r941_prom_fast_variant_g507, r941_prom_hac_g507, r941_prom_hac_snp_g507, r941_prom_hac_variant_g507, r941_prom_sup_g507, r941_prom_sup_snp_g507, r941_prom_sup_variant_g507, r941_sup_plant_g610, r941_sup_plant_variant_g610 +Default consensus: r1041_e82_400bps_sup_v5.0.0 +Default variant: r1041_e82_400bps_sup_variant_v5.0.0 +``` From 746f2b30f0b171e0666f904d8fe777303f55ba2a Mon Sep 17 00:00:00 2001 From: Young Date: Thu, 3 Oct 2024 08:00:45 -0600 Subject: [PATCH 41/92] update tbprofiler to version 6.3.0 (#1070) * update tbprofiler to version 6.3.0 * Added '-f' to micromamba clean --- README.md | 2 +- tbprofiler/6.3.0/Dockerfile | 65 +++++++++++++++++++++++++++++++++++++ tbprofiler/6.3.0/README.md | 58 +++++++++++++++++++++++++++++++++ 3 files changed, 124 insertions(+), 1 deletion(-) create mode 100644 tbprofiler/6.3.0/Dockerfile create mode 100644 tbprofiler/6.3.0/README.md diff --git a/README.md b/README.md index aa523c911..a06d376e8 100644 --- a/README.md +++ b/README.md @@ -294,7 +294,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Staramr](https://hub.docker.com/r/staphb/staramr/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/staramr)](https://hub.docker.com/r/staphb/staramr) |
    • [0.5.1](./staramr/0.5.1/)
    • [0.7.1](./staramr/0.7.1/)
    • [0.8.0](./staramr/0.8.0/)
    • [0.10.0](./staramr/0.10.0/)
    | https://github.com/phac-nml/staramr | | [stxtyper](https://hub.docker.com/r/staphb/stxtyper)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/stxtyper)](https://hub.docker.com/r/staphb/stxtyper) |
    • [1.0.24](stxtyper/1.0.24)
    | https://github.com/ncbi/stxtyper | | [sylph](https://hub.docker.com/r/staphb/sylph)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/sylph)](https://hub.docker.com/r/staphb/sylph) |
    • [0.4.1](./sylph/0.4.1)
    • [0.5.1](./sylph/0.5.1)
    • [0.6.0](./sylph/0.6.0)
    • [0.6.1](./sylph/0.6.1)
    | https://github.com/bluenote-1577/sylph | -| [TBProfiler](https://hub.docker.com/r/staphb/tbprofiler/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/tbprofiler)](https://hub.docker.com/r/staphb/tbprofiler) |
    • [4.3.0](./tbprofiler/4.3.0/)
    • [4.4.0](./tbprofiler/4.4.0/)
    • [4.4.2](./tbprofiler/4.4.2/)
    • [5.0.1](tbprofiler/5.0.1/)
    • [6.2.0](tbprofiler/6.2.0/)
    • [6.2.1](tbprofiler/6.2.1/)
    | https://github.com/jodyphelan/TBProfiler | +| [TBProfiler](https://hub.docker.com/r/staphb/tbprofiler/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/tbprofiler)](https://hub.docker.com/r/staphb/tbprofiler) |
    • [4.3.0](./tbprofiler/4.3.0/)
    • [4.4.0](./tbprofiler/4.4.0/)
    • [4.4.2](./tbprofiler/4.4.2/)
    • [5.0.1](tbprofiler/5.0.1/)
    • [6.2.0](tbprofiler/6.2.0/)
    • [6.2.1](tbprofiler/6.2.1/)
    • [6.3.0](tbprofiler/6.3.0/)
    | https://github.com/jodyphelan/TBProfiler | | [TipToft](https://hub.docker.com/r/staphb/tiptoft/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/tiptoft)](https://hub.docker.com/r/staphb/tiptoft) |
    • 1.0.0
    • 1.0.2
    | https://github.com/andrewjpage/tiptoft | | [Tostadas](https://hub.docker.com/r/staphb/tostadas/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/tostadas)](https://hub.docker.com/r/staphb/tostadas) |
    • [0.2.0-beta](./tostadas/0.2.0-beta/)
    • [3.1.0](./tostadas/3.1.0/)
    | https://github.com/CDCgov/tostadas | | [Treemmer](https://hub.docker.com/r/staphb/treemmer/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/treemmer)](https://hub.docker.com/r/staphb/treemmer) |
    • 0.3
    | https://git.scicore.unibas.ch/TBRU/Treemmer (archived, moved to GitHub)
    https://github.com/fmenardo/Treemmer | diff --git a/tbprofiler/6.3.0/Dockerfile b/tbprofiler/6.3.0/Dockerfile new file mode 100644 index 000000000..d07f9cdfa --- /dev/null +++ b/tbprofiler/6.3.0/Dockerfile @@ -0,0 +1,65 @@ +FROM mambaorg/micromamba:1.5.8 as app + +USER root +WORKDIR / + +ARG TBPROFILER_VER="6.3.0" + +# this version is the shortened commit hash on the `master` branch here https://github.com/jodyphelan/tbdb/ +# commits are found on https://github.com/jodyphelan/tbdb/commits/master +# this was the latest commit as of 2024-08-29 +ARG TBDB_COMMIT="4907915526b52ac2f20f1324613f5d4dc951e0bd" + +# LABEL instructions tag the image with metadata that might be important to the user +LABEL base.image="micromamba:1.5.8" +LABEL dockerfile.version="1" +LABEL software="tbprofiler" +LABEL software.version="${TBPROFILER_VER}" +LABEL description="The pipeline aligns reads to the H37Rv reference using bowtie2, BWA or minimap2 and then calls variants using bcftools. These variants are then compared to a drug-resistance database." +LABEL website="https://github.com/jodyphelan/TBProfiler/" +LABEL license="https://github.com/jodyphelan/TBProfiler/blob/master/LICENSE" +LABEL maintainer="John Arnn" +LABEL maintainer.email="jarnn@utah.gov" +LABEL maintainer2="Curtis Kapsak" +LABEL maintainer2.email="kapsakcj@gmail.com" +LABEL maintainer3="Sage Wright" +LABEL maintainer3.email="sagemwright@gmail.com" + +# Install dependencies via apt-get; cleanup apt garbage +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + procps && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# install tb-profiler via bioconda; install into 'base' conda env +RUN micromamba install --yes --name base --channel conda-forge --channel bioconda \ + tb-profiler=${TBPROFILER_VER} && \ + micromamba clean --all --yes -f + +# hardcode 'base' env bin into PATH, so conda env does not have to be "activated" at run time +ENV PATH="/opt/conda/bin:${PATH}" + +# Version of database can be confirmed at /opt/conda/share/tbprofiler/tbdb.version.json +# can also run 'tb-profiler list_db' to find the same version info + +# https://github.com/jodyphelan/tbdb +RUN tb-profiler update_tbdb --commit ${TBDB_COMMIT} + +WORKDIR /data + +# Added command to bring help menu up upon running container. +CMD tb-profiler + +# test stage +FROM app as test + +# checking if tool is in PATH +RUN tb-profiler && tb-profiler version + +WORKDIR /tests + +# download some TB FASTQs and run through tb-profiler +RUN wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR166/009/ERR1664619/ERR1664619_1.fastq.gz && \ + wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR166/009/ERR1664619/ERR1664619_2.fastq.gz && \ + tb-profiler profile -1 ERR1664619_1.fastq.gz -2 ERR1664619_2.fastq.gz -t 2 -p ERR1664619 --txt diff --git a/tbprofiler/6.3.0/README.md b/tbprofiler/6.3.0/README.md new file mode 100644 index 000000000..ff8fc5938 --- /dev/null +++ b/tbprofiler/6.3.0/README.md @@ -0,0 +1,58 @@ +# TBProfiler Container + +Main tool: [TBProfiler](https://github.com/jodyphelan/TBProfiler) + +The pipeline aligns reads to the H37Rv reference using bowtie2, BWA or minimap2 and then calls variants using bcftools. These variants are then compared to a drug-resistance database. It also predicts the number of reads supporting drug resistance variants as an insight into hetero-resistance. + +## Database + +This tool relies on a database to run. The version (AKA git commit hash) of the database that is included in the docker image is `97b5876`. This is from the GitHub repository https://github.com/jodyphelan/tbdb. This can be confirmed in the json file: `/opt/conda/share/tbprofiler/tbdb.version.json`: + +```bash +$ grep 'commit' /opt/conda/share/tbprofiler/tbdb.version.json +{"name": "tbdb", "commit": "5f3c51e", "Merge": "b1a2549 abddb8e", "Author": "Jody Phelan ", "Date": "Thu Jan 19 10:47:32 2023 +0000"} +``` + +Additionally you can run the command `tb-profiler list_db` to list the same information + +```bash +$ tb-profiler list_db +tbdb 97b5876 Jody Phelan Wed May 8 13:53:15 2024 +0100 /opt/conda/share/tbprofiler/tbdb +``` + +## Additional included tools/dependencies + +- bedtools 2.31.1 +- gatk4 4.5.0.0 +- kmc 3.2.4 +- pathogen-profiler 4.2.0 +- perl 5.32.1 +- python 3.10.14 +- trimmomatic 0.39 +- bwa 0.7.18 +- minimap2 2.28 +- samtools 1.20 +- bcftools 1.20 +- freebayes 1.3.6 +- tqdm 4.66.4 +- parallel 20240522 +- samclip 0.4.0 +- snpeff 5.2 + +## Example Usage + +Run whole pipeline on Illumina paired-end reads: + +```bash +tb-profiler profile -1 ERR1664619_1.fastq.gz -2 ERR1664619_2.fastq.gz -t 4 -p ERR1664619 --txt +``` + +Make alternative database: + +```bash +tb-profiler create_db --prefix +tb-profiler load_library --prefix +``` + +## Updates +Release 5.0.1 implemented sqlite3 database locking with https://py-filelock.readthedocs.io/en/latest/index.html. This should fix issues using it over network filing systems (NFS). For more information, official documentation can be found [here.](https://jodyphelan.gitbook.io/tb-profiler/) From e9253f805c9bd9e92113df13a355a8c48c27d469 Mon Sep 17 00:00:00 2001 From: Kincekara Date: Thu, 3 Oct 2024 16:21:33 +0000 Subject: [PATCH 42/92] add bbtools 39.10 --- README.md | 2 +- bbtools/39.10/Dockerfile | 71 ++++++++++++++++++++++++ bbtools/39.10/README.md | 114 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 186 insertions(+), 1 deletion(-) create mode 100644 bbtools/39.10/Dockerfile create mode 100644 bbtools/39.10/README.md diff --git a/README.md b/README.md index a06d376e8..cefa724b9 100644 --- a/README.md +++ b/README.md @@ -124,7 +124,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Auspice](https://hub.docker.com/r/staphb/auspice)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/auspice)](https://hub.docker.com/r/staphb/auspice) |
    • 2.12.0
    | https://github.com/nextstrain/auspice | | [bakta](https://hub.docker.com/r/staphb/bakta)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bakta)](https://hub.docker.com/r/staphb/bakta) |
    • [1.9.2](./bakta/1.9.2/)
    • [1.9.2-light](./bakta/1.9.2-5.1-light/)
    • [1.9.3](./bakta/1.9.3/)
    • [1.9.3-light](./bakta/1.9.3-5.1-light/)
    • [1.9.4](./bakta/1.9.4/)
    • [1.9.4-5.1-light](./bakta/1.9.4-5.1-light/)
    | https://github.com/oschwengers/bakta | | [bandage](https://hub.docker.com/r/staphb/bandage)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bandage)](https://hub.docker.com/r/staphb/bandage) |
    • [0.8.1](./bandage/0.8.1/)
    | https://rrwick.github.io/Bandage/ | -| [BBTools](https://hub.docker.com/r/staphb/bbtools/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bbtools)](https://hub.docker.com/r/staphb/bbtools) |
    • [38.76](./bbtools/38.76/)
    • [38.86](./bbtools/38.86/)
    • [38.95](./bbtools/38.95/)
    • [38.96](./bbtools/38.96/)
    • [38.97](./bbtools/38.97/)
    • [38.98](./bbtools/38.98/)
    • [38.99](./bbtools/38.99/)
    • [39.00](./bbtools/39.00/)
    • [39.01](./bbtools/39.01/)
    • [39.06](./bbtools/39.06/)
    | https://jgi.doe.gov/data-and-tools/bbtools/ | +| [BBTools](https://hub.docker.com/r/staphb/bbtools/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bbtools)](https://hub.docker.com/r/staphb/bbtools) |
    • [38.76](./bbtools/38.76/)
    • [38.86](./bbtools/38.86/)
    • [38.95](./bbtools/38.95/)
    • [38.96](./bbtools/38.96/)
    • [38.97](./bbtools/38.97/)
    • [38.98](./bbtools/38.98/)
    • [38.99](./bbtools/38.99/)
    • [39.00](./bbtools/39.00/)
    • [39.01](./bbtools/39.01/)
    • [39.06](./bbtools/39.06/)
    • [39.10](./bbtools/39.10/)
    | https://jgi.doe.gov/data-and-tools/bbtools/ | | [bcftools](https://hub.docker.com/r/staphb/bcftools/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bcftools)](https://hub.docker.com/r/staphb/bcftools) |
    • [1.10.2](./bcftools/1.10.2/)
    • [1.11](./bcftools/1.11/)
    • [1.12](./bcftools/1.12/)
    • [1.13](./bcftools/1.13/)
    • [1.14](./bcftools/1.14/)
    • [1.15](./bcftools/1.15/)
    • [1.16](./bcftools/1.16/)
    • [1.17](./bcftools/1.17/)
    • [1.18](bcftools/1.18/)
    • [1.19](./bcftools/1.19/)
    • [1.20](./bcftools/1.20/)
    • [1.20.c](./bcftools/1.20.c/)
    • [1.21](./bcftools/1.21/)
    | https://github.com/samtools/bcftools | | [bedtools](https://hub.docker.com/r/staphb/bedtools/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bedtools)](https://hub.docker.com/r/staphb/bedtools) |
    • 2.29.2
    • 2.30.0
    • [2.31.0](bedtools/2.31.0/)
    • [2.31.1](bedtools/2.31.1/)
    | https://bedtools.readthedocs.io/en/latest/
    https://github.com/arq5x/bedtools2 | | [berrywood-report-env](https://hub.docker.com/r/staphb/berrywood-report-env/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/berrywood-report-env)](https://hub.docker.com/r/staphb/berrywood-report-env) |
    • 1.0
    | none | diff --git a/bbtools/39.10/Dockerfile b/bbtools/39.10/Dockerfile new file mode 100644 index 000000000..4fad5dc11 --- /dev/null +++ b/bbtools/39.10/Dockerfile @@ -0,0 +1,71 @@ +FROM staphb/samtools:1.21 as samtools +FROM staphb/htslib:1.21 as htslib + +# As a reminder +# https://github.com/StaPH-B/docker-builds/pull/925#issuecomment-2010553275 +# bbmap/docs/TableOfContents.txt lists additional dependencies + +FROM ubuntu:jammy as app + +ARG SAMBAMBAVER=1.0.1 +ARG BBTOOLSVER=39.10 + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="BBTools" +LABEL software.version=${BBTOOLSVER} +LABEL description="A set of tools labeled as \"Bestus Bioinformaticus\"" +LABEL website="https://sourceforge.net/projects/bbmap" +LABEL documentation="https://jgi.doe.gov/data-and-tools/bbtools/bb-tools-user-guide/" +LABEL license="https://jgi.doe.gov/disclaimer/" +LABEL maintainer="Abigail Shockey" +LABEL maintainer.email="abigail.shockey@slh.wisc.edu" +LABEL maintainer2="Padraic Fanning" +LABEL maintainer2.email="faninnpm AT miamioh DOT edu" + +RUN apt-get update && \ + apt-get install --no-install-recommends -y \ + openjdk-8-jre-headless \ + pigz \ + pbzip2 \ + lbzip2 \ + bzip2 \ + wget \ + ca-certificates \ + procps && \ + rm -rf /var/lib/apt/lists/* && \ + apt-get autoclean + +# copy samtools to image +COPY --from=samtools /usr/local/bin/* /usr/local/bin/ +COPY --from=htslib /usr/local/bin/* /usr/local/bin/ + +# download and install sambamba +RUN wget -q https://github.com/biod/sambamba/releases/download/v${SAMBAMBAVER}/sambamba-${SAMBAMBAVER}-linux-amd64-static.gz && \ + gzip -d sambamba-${SAMBAMBAVER}-linux-amd64-static.gz && \ + mv sambamba-${SAMBAMBAVER}-linux-amd64-static /usr/local/bin/sambamba && \ + chmod +x /usr/local/bin/sambamba + +# download and install bbtools +RUN wget -q https://sourceforge.net/projects/bbmap/files/BBMap_${BBTOOLSVER}.tar.gz && \ + tar -xzf BBMap_${BBTOOLSVER}.tar.gz && \ + rm BBMap_${BBTOOLSVER}.tar.gz && \ + mkdir /data + +ENV PATH=/bbmap/:$PATH \ + LC_ALL=C + +CMD tail -n 90 /bbmap/docs/TableOfContents.txt + +WORKDIR /data + +# testing +FROM app as test + +# testing that '-h' works for all tools +RUN for tool in $(ls /bbmap/*sh | cut -f 3 -d "/") ; do echo $tool; done + +# get test data and test one thing that uses samtools/sambamba +RUN wget -q https://raw.githubusercontent.com/StaPH-B/docker-builds/master/tests/SARS-CoV-2/SRR13957123.primertrim.sorted.bam && \ + streamsam.sh in='SRR13957123.primertrim.sorted.bam' out='test_SRR13957123.primertrim.sorted.fastq.gz' && \ + test -f test_SRR13957123.primertrim.sorted.fastq.gz diff --git a/bbtools/39.10/README.md b/bbtools/39.10/README.md new file mode 100644 index 000000000..e65829476 --- /dev/null +++ b/bbtools/39.10/README.md @@ -0,0 +1,114 @@ +# BBTools container + +Main tool: [BBTools](https://jgi.doe.gov/data-and-tools/software-tools/bbtools/) + +Code repository: https://sourceforge.net/projects/bbmap/ + +Additional tools: +- samtools: 1.21 +- htslib: 1.21 +- sambamba: 1.0.1 + +Basic information on how to use this tool: +- executable: *.sh +- help: Program descriptions and options are shown when running the shell scripts with no parameters. +- version: --version +- description: +>BBTools is a suite of fast, multithreaded bioinformatics tools designed for analysis of DNA and RNA sequence data. BBTools can handle common sequencing file formats such as fastq, fasta, sam, scarf, fasta+qual, compressed or raw, with autodetection of quality encoding and interleaving. + +Additional information: +| Script | Purpose | Comment | +|-------------------------|----------------------------------------------------------------------------------|------------------------------------------------------------------------| +| bbcms.sh | Performs error correction using a Count-Min Sketch | Intended for metagenome assembly assembly | +| bbcountunique.sh | Counts unique kmers in reads | | +| bbduk.sh | Trims, filters or masks reads using kmers | | +| bbmap.sh | Splice-aware aligner for short reads | | +| bbmapskimmer.sh | BBMap version designed for high levels of multimapping | | +| bbmask.sh | Masks references based on various things, such as sequence complexity | | +| bbmerge.sh | Merges overlapping paired reads | | +| bbmerge-auto.sh | Same as bbmerge, but tries to allocate all memory on the node | Use this version for kmer operations like extend | +| bbnorm.sh | Normalizes reads based on coverage | Mainly for use prior to single-cell assembly | +| bbsplit.sh | BBMap version that maps to multiple references simultaneously | Intended for decontamination; similar to Seal | +| bbversion.sh | Prints the version of BBTools | | +| bbwrap.sh | Wraps BBMap to process many files using same reference | Saves time by loading the index only once | +| calctruequality.sh | Allows recalibration of quality scores from mapped reads | This generates the correction matrix; BBDuk does the recalibration | +| callgenes.sh | Fast prokaryotic gene caller | Integrated into BBSketch | +| callvariants.sh | Fast variant caller | | +| callvariants2.sh | Same as callvariants.sh with the "multisample" flag | | +| clumpify.sh | Shrinks compressed fastq files, and can remove duplicate reads | Also supports error correction | +| comparesketch.sh | Compares sketches locally, without using a sketch server | | +| crossblock.sh | Alias for decontaminate.sh | | +| cutgff.sh | Cuts out features defined by gff file | E.g, generates one fasta entry per gene from a gff and an assembly | +| cutprimers.sh | Cuts out subregions of ribosomes | Mainly for 16S analysis | +| decontaminate.sh | Pool-level decontamination for single-cell MDA-amplified genomes | | +| dedupe.sh | Removes duplicate and fully-contained sequences | Can also be used to cluster 16S sequences | +| dedupe2.sh | Version of dedupe that supports more hash keys for greater sensitivity | | +| dedupebymapping.sh | Deduplicates reads based on mapping coordinates | | +| demuxbyname.sh | Demultiplexes based on sequences headers | | +| filterbyname.sh | Filters based on sequence headers | | +| filterbytaxa.sh | Filters sequences based on taxonomic classification | Used with NCBI datasets | +| filterbytile.sh | Removes reads that are in low quality areas on flowcell | | +| filterqc.sh | Part of JGI's fastq filtering pipeline | | +| filtersam.sh | Filters sam files to remove reads with multiple unsupported mismatches | Designed for NovaSeq | +| gitable.sh | Used to process NCBI taxonomy data | | +| khist.sh | Alias for bbnorm.sh with flags for making a kmer frequency histogram | | +| kmercountexact.sh | Counts kmers and produces a histogram | Uses more memory than BBNorm but allows exact counts | +| kmercountmulti.sh | Cardinality estimation over multiple kmer lengths | Uses LogLog; does not produce a histogram | +| mapPacBio.sh | BBMap version designed for PacBio or Nanopore reads | Reads longer than 5kbp get broken into 5kbp shreds | +| mergesketch.sh | Allows multiple sketches to be combined | | +| msa.sh | Alignment tool | Used with cutprimers.sh to cut subsections out of 16s | +| mutate.sh | Generates synthetic genomes by randomly mutating the input | | +| muxbyname.sh | Multiplex multiple files, renaming sequences based on input file name | Opposite of demuxbyname.sh | +| partition.sh | Splits a sequence file into multiple files | | +| pileup.sh | Calculates coverage from sam files | | +| plotflowcell.sh | Produces statistics about flowcell positions | | +| processhi-c.sh | Custom trimming for hi-C reads | In development | +| randomreads.sh | Generates synthetic data from real genome reference | Highly customizable | +| readqc.sh | Short read quality report | Alternative to fastqc | +| reformat.sh | Converts sequence files to another format | Has many additional options, includes subsampling | +| rename.sh | Renames sequences in various ways, such as adding a prefix | | +| repair.sh | Fixes broken pairing in fastq files | | +| representative.sh | Makes a smaller subset of a reference dataset by eliminating redundancy | Designed for use with BBSketch output | +| rqcfilter2.sh | Filtering pipeline used at JGI | portal.nersc.gov/dna/microbial/assembly/bushnell/RQCFilterData.tar | +| seal.sh | Counts kmer matches between query and reference sequences | | +| sendsketch.sh | Fast taxonomic classifier using webservers at JGI | | +| shred.sh | Breaks sequences into shorter, fixed-length pieces | | +| shuffle.sh | Randomly reorders input file | Crashes if input doesn't fit in memory | +| shuffle2.sh | Randomly reorders input file | Supports larger files, but output might be less random | +| sketch.sh | Makes reference sketches on a per-TaxID basis | | +| sketchblacklist.sh | Makes sketch blacklists of common kmers | | +| sortbyname.sh | Sorts sequences by name, length, quality, taxa, and other things | | +| summarizequast.sh | Generates box plots for multiple quast reports | | +| tadpipe.sh | Preprocessing and assembly pipeline using tadpole | | +| tadpole.sh | Fast short read assembler | | +| tadwrapper.sh | Runs Tadpole with multiple kmer lengths to select the best assembly | | +| taxserver.sh | Starts taxonomy and sketch servers | | +| testformat.sh | Determines if file is fasta, fastq, interleaved, etc. by reading first few lines | | +| testformat2.sh | Generates extensive statistics by reading the full file | | +| translate6frames.sh | Translates nucleotide sequence into amino acid sequence in all frames | | +| vcf2gff.sh | Converts vcf format to gff format | | + +Full documentation: https://jgi.doe.gov/data-and-tools/software-tools/bbtools/bb-tools-user-guide/ + +## Example Usage + +(adapted from `/opt/bbmap/pipelines/covid/processCorona.sh`) + +Interleave a pair of FASTQ files for downstream processing: + +```text +reformat.sh \ + in1=${SAMPLE}_R1.fastq.gz \ + in2=${SAMPLE}_R2.fastq.gz \ + out=${SAMPLE}.fastq.gz +``` +Split into SARS-CoV-2 and non-SARS-CoV-2 reads: + +```text +bbduk.sh ow -Xmx1g \ + in=${SAMPLE}.fq.gz \ + ref=REFERENCE.fasta \ + outm=${SAMPLE}_viral.fq.gz \ + outu=${SAMPLE}_nonviral.fq.gz \ + k=25 +``` From 95645079d5848ff5d0512be55da6ffee3abc5bd5 Mon Sep 17 00:00:00 2001 From: Kincekara Date: Thu, 3 Oct 2024 16:28:18 +0000 Subject: [PATCH 43/92] fix test --- bbtools/39.10/Dockerfile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/bbtools/39.10/Dockerfile b/bbtools/39.10/Dockerfile index 4fad5dc11..039d28ccb 100644 --- a/bbtools/39.10/Dockerfile +++ b/bbtools/39.10/Dockerfile @@ -62,8 +62,8 @@ WORKDIR /data # testing FROM app as test -# testing that '-h' works for all tools -RUN for tool in $(ls /bbmap/*sh | cut -f 3 -d "/") ; do echo $tool; done +# testing all tools +RUN for tool in $(ls /bbmap/*sh | cut -f 3 -d "/") ; do $tool; done # get test data and test one thing that uses samtools/sambamba RUN wget -q https://raw.githubusercontent.com/StaPH-B/docker-builds/master/tests/SARS-CoV-2/SRR13957123.primertrim.sorted.bam && \ From 79c8c57e57bd8bfcc2e3545d5667c429a7d4cb8d Mon Sep 17 00:00:00 2001 From: Kincekara Date: Thu, 3 Oct 2024 18:12:03 +0000 Subject: [PATCH 44/92] adds viridian 1.3.0 --- README.md | 2 +- viridian/1.3.0/Dockerfile | 215 ++++++++++++++++++++++++++++++++++++++ viridian/1.3.0/README.md | 47 +++++++++ 3 files changed, 263 insertions(+), 1 deletion(-) create mode 100644 viridian/1.3.0/Dockerfile create mode 100644 viridian/1.3.0/README.md diff --git a/README.md b/README.md index a06d376e8..c4f35483a 100644 --- a/README.md +++ b/README.md @@ -305,7 +305,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Verkko](https://hub.docker.com/r/staphb/verkko/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/verkko)](https://hub.docker.com/r/staphb/verkko) |
    • [2.0](./verkko/2.0/)
    • [2.1](./verkko/2.1/)
    • [2.2](./verkko/2.2/)
    | https://github.com/marbl/verkko | | [VIBRANT](https://hub.docker.com/r/staphb/vibrant/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/vibrant)](https://hub.docker.com/r/staphb/vibrant) |
    • 1.2.1
    | https://github.com/AnantharamanLab/VIBRANT | | [VIGOR4](https://hub.docker.com/r/staphb/vigor4/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/vigor4)](https://hub.docker.com/r/staphb/vigor4) |
    • [4.1.20190131](./vigor4/4.1.20190131/)
    • [4.1.20200702](./vigor4/4.1.20200702/)
    | https://github.com/JCVenterInstitute/VIGOR4 | -| [Viridian](https://hub.docker.com/r/staphb/viridian/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/viridian)](https://hub.docker.com/r/staphb/viridian) |
    • [1.2.2](./viridian/1.2.2/)
    | https://github.com/iqbal-lab-org/viridian | +| [Viridian](https://hub.docker.com/r/staphb/viridian/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/viridian)](https://hub.docker.com/r/staphb/viridian) |
    • [1.2.2](./viridian/1.2.2/)
    • [1.3.0](./viridian/1.3.0/)
    | https://github.com/iqbal-lab-org/viridian | | [VirSorter2](https://hub.docker.com/r/staphb/virsorter2/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/virsorter2)](https://hub.docker.com/r/staphb/virsorter2/) |
    • 2.1
    | https://github.com/jiarong/VirSorter2 | | [VirulenceFinder](https://hub.docker.com/r/staphb/virulencefinder/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/virulencefinder)](https://hub.docker.com/r/staphb/virulencefinder/) |
    • [2.1.4](virulencefinder/2.0.4/)
    | https://bitbucket.org/genomicepidemiology/virulencefinder/src/master/
    https://bitbucket.org/genomicepidemiology/virulencefinder_db/src/master/ | | [wtdbg2](https://hub.docker.com/r/staphb/wtdbg2/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/wtdbg2)](https://hub.docker.com/r/staphb/wtdbg2) |
    • 2.5
    | https://github.com/ruanjue/wtdbg2 | diff --git a/viridian/1.3.0/Dockerfile b/viridian/1.3.0/Dockerfile new file mode 100644 index 000000000..3d362114b --- /dev/null +++ b/viridian/1.3.0/Dockerfile @@ -0,0 +1,215 @@ +ARG VIRIDIAN_VER="1.3.0" +ARG SAMTOOLS_VER="1.21" +ARG BCFTOOLS_VER=${SAMTOOLS_VER} +ARG HTSLIB_VER=${SAMTOOLS_VER} +ARG ENA_VER="1.7.1" +ARG NGMERGE_VER="0.3" +ARG VT_VER="0.57721" +ARG RACON_VER="1.5.0" +ARG MUMMER_VER="4.0.0rc1" +ARG READITANDKEEP_VER="0.3.0" +ARG CYLON_COMMIT_HASH="57d559a76254b0b95785f7c02fa58ef806713e01" +ARG VARIFIER_COMMIT_HASH="8bc8726ed3cdb337dc47b62515e709759e451137" +ARG MINIMAP2_VER="2.28" + +## Builder ## +FROM ubuntu:jammy as build +ARG SAMTOOLS_VER +ARG BCFTOOLS_VER +ARG HTSLIB_VER +ARG NGMERGE_VER +ARG VT_VER +ARG RACON_VER +ARG READITANDKEEP_VER +ARG MINIMAP2_VER +ARG MUMMER_VER + +ENV DEBIAN_FRONTEND=noninteractive + +RUN apt-get update && apt-get install --no-install-recommends -y \ + wget \ + ca-certificates \ + perl \ + bzip2 \ + cmake \ + git \ + autoconf \ + automake \ + make \ + curl \ + gcc \ + g++ \ + gnuplot \ + zlib1g-dev \ + libbz2-dev \ + liblzma-dev \ + libcurl4-gnutls-dev \ + libncurses5-dev \ + libssl-dev \ + libperl-dev \ + libgsl0-dev \ + procps \ + gawk \ + sed \ + build-essential \ + unzip \ + nasm \ + pkgconf \ + libtool \ + ruby \ + yaggo \ + gcc-11 && \ + rm -rf /var/lib/apt/lists/* && apt-get autoclean + +# compile bcftools +RUN wget -q https://github.com/samtools/bcftools/releases/download/${BCFTOOLS_VER}/bcftools-${BCFTOOLS_VER}.tar.bz2 && \ + tar -xjf bcftools-${BCFTOOLS_VER}.tar.bz2 && \ + rm -v bcftools-${BCFTOOLS_VER}.tar.bz2 && \ + cd bcftools-${BCFTOOLS_VER} && \ + make && \ + make install + +# compile samtools +RUN wget -q https://github.com/samtools/samtools/releases/download/${SAMTOOLS_VER}/samtools-${SAMTOOLS_VER}.tar.bz2 && \ + tar -xjf samtools-${SAMTOOLS_VER}.tar.bz2 && \ + cd samtools-${SAMTOOLS_VER} && \ + ./configure && \ + make && \ + make install + +# compile htslib +RUN wget -q https://github.com/samtools/htslib/releases/download/${HTSLIB_VER}/htslib-${HTSLIB_VER}.tar.bz2 && \ + tar -vxjf htslib-${HTSLIB_VER}.tar.bz2 && \ + rm -v htslib-${HTSLIB_VER}.tar.bz2 && \ + cd htslib-${HTSLIB_VER} && \ + make && \ + make install + +# compile NGmerge +RUN wget -q https://github.com/harvardinformatics/NGmerge/archive/refs/tags/v${NGMERGE_VER}.tar.gz && \ + tar -vxf v${NGMERGE_VER}.tar.gz && \ + cd NGmerge-${NGMERGE_VER} && \ + make && \ + cp NGmerge /usr/local/bin/. + +# compile vt +RUN wget -q https://github.com/atks/vt/archive/refs/tags/${VT_VER}.tar.gz && \ + tar -vxf ${VT_VER}.tar.gz && \ + cd vt-${VT_VER} && \ + make && \ + cp vt /usr/local/bin/. + +# compile racon +RUN wget -q https://github.com/lbcb-sci/racon/archive/refs/tags/${RACON_VER}.tar.gz && \ + tar -xvf ${RACON_VER}.tar.gz && \ + cd racon-${RACON_VER} && \ + mkdir build && \ + cd build && \ + cmake -DCMAKE_BUILD_TYPE=Release .. && \ + make && \ + cp bin/racon /usr/local/bin/. + +# compile read-it-and-keep +RUN wget -q https://github.com/GlobalPathogenAnalysisService/read-it-and-keep/archive/refs/tags/v${READITANDKEEP_VER}.tar.gz && \ + tar -vxf v${READITANDKEEP_VER}.tar.gz && \ + cd read-it-and-keep-${READITANDKEEP_VER}/src && \ + make && \ + cp readItAndKeep /usr/local/bin/. + +# install minimap2 binary +RUN curl -L https://github.com/lh3/minimap2/releases/download/v${MINIMAP2_VER}/minimap2-${MINIMAP2_VER}_x64-linux.tar.bz2 | tar -jxvf - --no-same-owner && \ + cp minimap2-${MINIMAP2_VER}_x64-linux/minimap2 /usr/local/bin + +RUN wget -q https://github.com/mummer4/mummer/archive/refs/tags/v${MUMMER_VER}.tar.gz && \ + tar -xvf v${MUMMER_VER}.tar.gz && \ + cd mummer-${MUMMER_VER} && \ + autoreconf -i && \ + ./configure CXXFLAGS="-std=c++11 -Wno-maybe-uninitialized" LDFLAGS=-static && \ + make && \ + make install && \ + ldconfig + +## App ## +FROM ubuntu:jammy as app + +ARG VIRIDIAN_VER +ARG ENA_VER +ARG CYLON_COMMIT_HASH +ARG VARIFIER_COMMIT_HASH + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="viridian" +LABEL software.version="${VIRIDIAN_VER}" +LABEL description="Ultra-careful amplicon-aware viral assembly for tiled amplicon schemes." +LABEL website="https://github.com/iqbal-lab-org/viridian" +LABEL license="https://github.com/iqbal-lab-org/viridian/blob/master/LICENSE" +LABEL maintainer="Wilson Chan" +LABEL maintainer.email="chan.wilson.wc@gmail.com" +LABEL maintainer2="Kutluhan Incekara" +LABEL maintainer2.email="kutluhan.incekara@ct.gov" +LABEL maintainer3="Erin Young" +LABEL maintainer3.email="eriny@utah.gov" + +RUN apt-get update && apt-get install -y --no-install-recommends \ + python3 \ + python3-pip \ + python3-dev \ + gzip \ + gcc \ + perl \ + zlib1g \ + libncurses5 \ + bzip2 \ + liblzma-dev \ + libcurl4-gnutls-dev \ + wget \ + && apt-get autoclean && rm -rf /var/lib/apt/lists/* + +COPY --from=build /usr/local/bin/* /usr/local/bin/ +COPY --from=build /usr/local/lib/* /usr/local/lib/ + +RUN pip install --no-cache-dir cython + +# ENA tools +RUN wget -q https://github.com/enasequence/enaBrowserTools/archive/refs/tags/v${ENA_VER}.tar.gz && \ + tar -xvf v${ENA_VER}.tar.gz && \ + rm v${ENA_VER}.tar.gz + +RUN wget -q https://github.com/iqbal-lab-org/cylon/archive/${CYLON_COMMIT_HASH}.zip &&\ + pip install --no-cache-dir ${CYLON_COMMIT_HASH}.zip && \ + rm ${CYLON_COMMIT_HASH}.zip + +RUN wget -q https://github.com/iqbal-lab-org/varifier/archive/${VARIFIER_COMMIT_HASH}.zip &&\ + pip install --no-cache-dir ${VARIFIER_COMMIT_HASH}.zip && \ + rm ${VARIFIER_COMMIT_HASH}.zip + +# install viridian +RUN wget -q https://github.com/iqbal-lab-org/viridian/archive/refs/tags/v${VIRIDIAN_VER}.tar.gz && \ + pip install --no-cache-dir v${VIRIDIAN_VER}.tar.gz && \ + mkdir viridian && \ + tar -C viridian --strip-components=1 -xvf v${VIRIDIAN_VER}.tar.gz && \ + rm v${VIRIDIAN_VER}.tar.gz + +WORKDIR /data + +CMD ["viridian", "--help "] + +ENV PATH="/enaBrowserTools-${ENA_VER}/python3:$PATH" LC_ALL=C + +## Test ## +FROM app as test + +WORKDIR /test + +RUN cd /viridian && \ + pip install --no-cache-dir pytest && \ + pytest + +RUN viridian run_one_sample --run_accession SRR29437696 --outdir OUT && \ + wc -l OUT/consensus.fa.gz OUT/log.json.gz OUT/qc.tsv.gz && \ + head OUT/variants.vcf + +RUN viridian run_one_sample --run_accession SRR29437696 --outdir OUT2 --keep_bam && \ + wc -l OUT2/consensus.fa.gz OUT2/log.json.gz OUT2/qc.tsv.gz OUT2/reference_mapped.bam && \ + head OUT2/variants.vcf diff --git a/viridian/1.3.0/README.md b/viridian/1.3.0/README.md new file mode 100644 index 000000000..d56ad17fa --- /dev/null +++ b/viridian/1.3.0/README.md @@ -0,0 +1,47 @@ +# Viridian container + +Main tool: [Viridian](https://github.com/iqbal-lab-org/viridian) + +Code repository: [Viridian](https://github.com/iqbal-lab-org/viridian) + +Additional tools: +- samtools: 1.21 +- bcftools: 1.21 +- htslib: 1.21 +- ENA: 1.7.1 +- ngmerge: 0.3 +- vt: 0.577721 +- racon: 1.5.0 +- mummer: 4.0.0 +- read-it-and-keep: 0.3.0 +- cylon: commit hash 57d559a76254b0b95785f7c02fa58ef806713e01 +- varifier: commit hash 8bc8726ed3cdb337dc47b62515e709759e451137 +- minimap2: 2.28 + +Basic information on how to use this tool: +- executable: viridian +- help: --help +- version: --version +- description: Ultra-careful amplicon-aware viral assembly for tiled amplicon schemes. + +Full documentation: [Viridian wiki](https://github.com/iqbal-lab-org/viridian/wiki) + + +## Example Usage + +To run on paired Illumina reads: + +```bash +viridian run_one_sample \ + --tech illumina \ + --reads1 reads_1.fastq.gz \ + --reads2 reads_2.fastq.gz \ + --outdir OUT +``` + +Download reads with accession SRR12345678 and run: +```bash +viridian run_one_sample --run_accession SRR12345678 --outdir OUT +``` + +The sequencing tech and unpaired/paired is taken from the ENA metadata for each run. From ca1764820a544b1a3a9e113ff0f44f088975991c Mon Sep 17 00:00:00 2001 From: Kincekara Date: Thu, 3 Oct 2024 20:27:44 +0000 Subject: [PATCH 45/92] adds checkv --- Program_Licenses.md | 1 + README.md | 1 + checkv/1.0.3/Dockerfile | 52 +++++++++++++++++++++++++++++++++++++++++ checkv/1.0.3/README.md | 38 ++++++++++++++++++++++++++++++ 4 files changed, 92 insertions(+) create mode 100644 checkv/1.0.3/Dockerfile create mode 100644 checkv/1.0.3/README.md diff --git a/Program_Licenses.md b/Program_Licenses.md index 84442d2d8..8e4b30b13 100644 --- a/Program_Licenses.md +++ b/Program_Licenses.md @@ -31,6 +31,7 @@ The licenses of the open-source software that is contained in these Docker image | CDC-SPN | GitHub No License | https://github.com/BenJamesMetcalf/Spn_Scripts_Reference | | cfsan-snp-pipeline | non-standard license see --> | https://github.com/CFSAN-Biostatistics/snp-pipeline/blob/master/LICENSE.txt | | CheckM | GNU GPLv3 | https://github.com/Ecogenomics/CheckM/blob/master/LICENSE | +| CheckV | MIT | https://bitbucket.org/berkeleylab/checkv/src/master/LICENSE.txt | | Circlator | GNU GPLv3 | https://github.com/sanger-pathogens/circlator/blob/master/LICENSE | | Circos | GNU GPLv3 | https://circos.ca/ | | CirculoCov | GNU GPLv3 | https://github.com/erinyoung/CirculoCov/blob/main/LICENSE | diff --git a/README.md b/README.md index a06d376e8..56d4b5652 100644 --- a/README.md +++ b/README.md @@ -139,6 +139,7 @@ To learn more about the docker pull rate limits and the open source software pro | [CDC-SPN](https://hub.docker.com/r/staphb/cdc-spn/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/cdc-spn)](https://hub.docker.com/r/staphb/cdc-spn) |
    • 0.1 (no version)
    | https://github.com/BenJamesMetcalf/Spn_Scripts_Reference | | [cfsan-snp-pipeline](https://hub.docker.com/r/staphb/cfsan-snp-pipeline)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/cfsan-snp-pipeline)](https://hub.docker.com/r/staphb/cfsan-snp-pipeline) |
    • 2.0.2
    • 2.2.1
    | https://github.com/CFSAN-Biostatistics/snp-pipeline | | [CheckM](https://hub.docker.com/r/staphb/checkm)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/checkm)](https://hub.docker.com/r/staphb/checkm) |
    • [1.2.2](./checkm/1.2.2/)
    • [1.2.3](./checkm/1.2.3/)
    | https://github.com/Ecogenomics/CheckM | +| [CheckV](https://hub.docker.com/r/staphb/checkv)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/checkv)](https://hub.docker.com/r/staphb/checkv) |
    • [1.0.3](./checkv/1.0.3/)
    | https://bitbucket.org/berkeleylab/checkv/ | | [Circlator](https://hub.docker.com/r/staphb/circlator)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/circlator)](https://hub.docker.com/r/staphb/circlator) |
    • 1.5.6
    • 1.5.5
    | https://github.com/sanger-pathogens/circlator | | [Circos](https://hub.docker.com/r/staphb/circos)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/circos)](https://hub.docker.com/r/staphb/circos) |
    • [0.69-9](./circos/0.69.9/)
    | https://circos.ca/ | | [CirculoCov](https://hub.docker.com/r/staphb/circulocov)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/circulocov)](https://hub.docker.com/r/staphb/circulocov) |
    • [0.1.20240104](./circulocov/0.1.20240104/)
    | https://github.com/erinyoung/CirculoCov | diff --git a/checkv/1.0.3/Dockerfile b/checkv/1.0.3/Dockerfile new file mode 100644 index 000000000..cdde46ef8 --- /dev/null +++ b/checkv/1.0.3/Dockerfile @@ -0,0 +1,52 @@ +FROM ubuntu:jammy AS app + +ARG CHECKV_VER="1.0.3" +ARG DIAMOND_VER="2.1.8" +ARG PRODIGALGV_VER="2.11.0" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="CheckV" +LABEL software.version="${CHECKV_VER}" +LABEL description="CheckV is a fully automated command-line pipeline for assessing the quality of single-contig viral genomes" +LABEL website="https://bitbucket.org/berkeleylab/checkv/" +LABEL license="https://bitbucket.org/berkeleylab/checkv/src/master/LICENSE.txt" +LABEL maintainer="Kutluhan Incekara" +LABEL maintainer.email="kutluhan.incekara@ct.gov" + +RUN apt-get update && apt-get install --no-install-recommends -y \ + wget \ + hmmer \ + ncbi-blast+ \ + python3-pip && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# install diamond +RUN wget -q https://github.com/bbuchfink/diamond/releases/download/v${DIAMOND_VER}/diamond-linux64.tar.gz &&\ + tar -C /usr/local/bin/ -xvf diamond-linux64.tar.gz &&\ + rm diamond-linux64.tar.gz +# install prodigal-gv +RUN wget -q https://github.com/apcamargo/prodigal-gv/releases/download/${PRODIGALGV_VER}/prodigal-gv-linux &&\ + chmod +x prodigal-gv-linux &&\ + mv prodigal-gv-linux /usr/local/bin/prodigal-gv +# install checkv +RUN pip3 install --no-cache-dir checkv==${CHECKV_VER} + +ENV LC_ALL=C + +CMD [ "checkv", "--help" ] + +WORKDIR /data + + +## Test ## +FROM app AS test + +# download database (current v1.5) +RUN checkv download_database /db + +# download test fna and run checkv +RUN wget -q https://bitbucket.org/berkeleylab/checkv/raw/51a5293f75da04c5d9a938c9af9e2b879fa47bd8/test/test_sequences.fna &&\ + checkv end_to_end -d /db/checkv-db-v1.5 test_sequences.fna test_out -t 4 + + diff --git a/checkv/1.0.3/README.md b/checkv/1.0.3/README.md new file mode 100644 index 000000000..e628ef7d0 --- /dev/null +++ b/checkv/1.0.3/README.md @@ -0,0 +1,38 @@ +# CheckV container + +Main tool: [checkv](https://jgi.doe.gov/data-and-tools/software-tools/checkv/) + +Code repository: https://bitbucket.org/berkeleylab/checkv/ + +Additional tools: +- diamond: 2.1.8 +- prodigal-gv: 2.11.0 +- hmmer: 3.3.2 +- blast: 2.12.0+ + +Basic information on how to use this tool: +- executable: checkv +- help: -h +- version: +- description: +>CheckV is the first fully automated, command-line tool for assessing the quality of metagenome-assembled viral genomes + +Additional information: + +This container does not include any database. You can use `checkv download_database` command or https://portal.nersc.gov/CheckV/ address to download it manually + +Full documentation: https://bitbucket.org/berkeleylab/checkv/src/master/ + +## Example Usage + +```bash +# Using a single command to run the full pipeline (recommended) +checkv end_to_end input_file.fna output_directory -t 16 + +# Using individual commands for each step in the pipeline +checkv contamination input_file.fna output_directory -t 16 +checkv completeness input_file.fna output_directory -t 16 +checkv complete_genomes input_file.fna output_directory +checkv quality_summary input_file.fna output_directory +``` + From 6f0ef56cf374d1c297245e4cbf0bdbbc589f817e Mon Sep 17 00:00:00 2001 From: Young Date: Fri, 4 Oct 2024 10:24:21 -0600 Subject: [PATCH 46/92] Moving labels to app stage from builder --- seqfu/1.20.3/Dockerfile | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index 5fd1080a6..c5cc51645 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -5,17 +5,6 @@ ARG SEQFU_VER="1.20.3" FROM ubuntu:focal AS builder ARG SEQFU_VER -# Metadata -LABEL base.image="ubuntu:focal" -LABEL dockerfile.version="1" -LABEL software="SeqFu" -LABEL software.version="${SEQFU_VER}" -LABEL description="A general-purpose program to manipulate and parse information from FASTA/FASTQ files, supporting gzipped input files." -LABEL website="https://github.com/telatin/seqfu2" -LABEL license.url="https://github.com/telatin/seqfu2?tab=GPL-3.0-1-ov-file#readme" -LABEL maintainer="Taylor K. Paisie" -LABEL maintainer.email="ltj8@cdc.gov" - # Set non-interactive frontend and update PATH ENV DEBIAN_FRONTEND=noninteractive \ PATH="/root/.nimble/bin:${PATH}" @@ -53,6 +42,18 @@ RUN ls -l /root/seqfu2-${SEQFU_VER}/bin && \ FROM ubuntu:focal AS app ARG SEQFU_VER +# Metadata +LABEL base.image="ubuntu:focal" +LABEL dockerfile.version="1" +LABEL software="SeqFu" +LABEL software.version="${SEQFU_VER}" +LABEL description="A general-purpose program to manipulate and parse information from FASTA/FASTQ files, supporting gzipped input files." +LABEL website="https://github.com/telatin/seqfu2" +LABEL license.url="https://github.com/telatin/seqfu2?tab=GPL-3.0-1-ov-file#readme" +LABEL maintainer="Taylor K. Paisie" +LABEL maintainer.email="ltj8@cdc.gov" + + # Copy the necessary files from the builder COPY --from=builder /usr/local/bin /usr/local/bin From ecd7ea992cf78afd9dee11782140804de7c0cbed Mon Sep 17 00:00:00 2001 From: Young Date: Fri, 4 Oct 2024 11:12:36 -0600 Subject: [PATCH 47/92] Add CMD layer and more tests --- seqfu/1.20.3/Dockerfile | 43 +++++++++++++++++++++++------------------ 1 file changed, 24 insertions(+), 19 deletions(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index c5cc51645..2733bbbf0 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -1,5 +1,6 @@ # Set global variables ARG SEQFU_VER="1.20.3" +ARG NIM_VER="1.22.2" # Stage 1: Build Dockerfile FROM ubuntu:focal AS builder @@ -26,18 +27,15 @@ RUN apt-get update && apt-get install -y --no-install-recommends \ WORKDIR /root # Install Nim and SeqFu -RUN curl https://nim-lang.org/choosenim/init.sh -sSf | sh -s -- -y --ver 1.22.2 && \ - wget https://github.com/telatin/seqfu2/archive/refs/tags/v${SEQFU_VER}.tar.gz && \ +RUN curl https://nim-lang.org/choosenim/init.sh -sSf | sh -s -- -y --ver ${NIM_VER} + +# Install SeqFu +RUN wget https://github.com/telatin/seqfu2/archive/refs/tags/v${SEQFU_VER}.tar.gz && \ tar -xzf v${SEQFU_VER}.tar.gz && \ rm v${SEQFU_VER}.tar.gz && \ cd seqfu2-${SEQFU_VER} && \ make -# Copy the built binary to a location in the PATH -RUN ls -l /root/seqfu2-${SEQFU_VER}/bin && \ - cp -R /root/seqfu2-${SEQFU_VER}/bin/* /usr/local/bin/ && \ - chmod +x /usr/local/bin/seqfu - # Stage 2: Create the final image FROM ubuntu:focal AS app ARG SEQFU_VER @@ -53,31 +51,38 @@ LABEL license.url="https://github.com/telatin/seqfu2?tab=GPL-3.0-1-ov-file#readm LABEL maintainer="Taylor K. Paisie" LABEL maintainer.email="ltj8@cdc.gov" - # Copy the necessary files from the builder -COPY --from=builder /usr/local/bin /usr/local/bin +COPY --from=builder /root/seqfu2-${SEQFU_VER}/bin /usr/local/bin # Install minimal runtime dependencies RUN apt-get update && apt-get install -y --no-install-recommends \ - curl \ - git \ ca-certificates \ wget && \ - rm -rf /var/lib/apt/lists/* + apt-get autoclean && rm -rf /var/lib/apt/lists/* +ENV LC_ALL=C -# Verify installation -RUN ls -l /usr/local/bin && \ -seqfu --version && seqfu --help +CMD seqfu --help -# Running seqfu on test staph-b test dataset +# Stage 3: testing the installation FROM app AS test -WORKDIR /data/test +ARG SEQFU_VER + +# Verify installation +RUN seqfu --version && seqfu --help + +WORKDIR /test +# using dev supplied tests +COPY --from=builder /root/seqfu2-${SEQFU_VER} /test + +# skipping test-check.sh because it through error on dev-supplied fastq files +RUN mv test/test-check.sh test/test-check.sh_skip && \ + bash test/mini.sh + +# testing on user-supplied files RUN wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_1.fastq.gz && \ wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_2.fastq.gz && \ seqfu check SRR13957123_1.fastq.gz SRR13957123_2.fastq.gz > seqfu_check_test.txt && \ seqfu count -f SRR13957123_1.fastq.gz -r SRR13957123_2.fastq.gz > seqfu_count_test.txt - -WORKDIR /data From 62e2ec0b0af64287feb94d5cb6a3ac708269dd3b Mon Sep 17 00:00:00 2001 From: Young Date: Fri, 4 Oct 2024 11:21:46 -0600 Subject: [PATCH 48/92] add curl to apt-get layer --- seqfu/1.20.3/Dockerfile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index 2733bbbf0..56e481e10 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -55,7 +55,9 @@ LABEL maintainer.email="ltj8@cdc.gov" COPY --from=builder /root/seqfu2-${SEQFU_VER}/bin /usr/local/bin # Install minimal runtime dependencies +# curl is used in checking for the versions of dependencies RUN apt-get update && apt-get install -y --no-install-recommends \ + curl \ ca-certificates \ wget && \ apt-get autoclean && rm -rf /var/lib/apt/lists/* From cc9f01ef64e882da5e274553eadac07c8fc6073c Mon Sep 17 00:00:00 2001 From: Young Date: Fri, 4 Oct 2024 11:23:13 -0600 Subject: [PATCH 49/92] Update Dockerfile --- seqfu/1.20.3/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/seqfu/1.20.3/Dockerfile b/seqfu/1.20.3/Dockerfile index 56e481e10..06a56b5d7 100644 --- a/seqfu/1.20.3/Dockerfile +++ b/seqfu/1.20.3/Dockerfile @@ -79,7 +79,7 @@ WORKDIR /test # using dev supplied tests COPY --from=builder /root/seqfu2-${SEQFU_VER} /test -# skipping test-check.sh because it through error on dev-supplied fastq files +# skipping test-check.sh because it throws an error on dev-supplied fastq files RUN mv test/test-check.sh test/test-check.sh_skip && \ bash test/mini.sh From 9fed37d23a4e89b021cd4f6a5ddcc721f205e47a Mon Sep 17 00:00:00 2001 From: Kincekara Date: Fri, 4 Oct 2024 18:08:47 +0000 Subject: [PATCH 50/92] remove loop --- bbtools/39.10/Dockerfile | 3 --- 1 file changed, 3 deletions(-) diff --git a/bbtools/39.10/Dockerfile b/bbtools/39.10/Dockerfile index 039d28ccb..34c3c6218 100644 --- a/bbtools/39.10/Dockerfile +++ b/bbtools/39.10/Dockerfile @@ -62,9 +62,6 @@ WORKDIR /data # testing FROM app as test -# testing all tools -RUN for tool in $(ls /bbmap/*sh | cut -f 3 -d "/") ; do $tool; done - # get test data and test one thing that uses samtools/sambamba RUN wget -q https://raw.githubusercontent.com/StaPH-B/docker-builds/master/tests/SARS-CoV-2/SRR13957123.primertrim.sorted.bam && \ streamsam.sh in='SRR13957123.primertrim.sorted.bam' out='test_SRR13957123.primertrim.sorted.fastq.gz' && \ From 089e54e0594cdd3b8f6397cbd850ae7f409a83ef Mon Sep 17 00:00:00 2001 From: Kincekara Date: Wed, 16 Oct 2024 19:47:02 +0000 Subject: [PATCH 51/92] adds checkm2 --- Program_Licenses.md | 1 + README.md | 1 + checkm2/1.0.2/Dockerfile | 37 +++++++++++++++++++++++++++++++++++++ checkm2/1.0.2/README.md | 28 ++++++++++++++++++++++++++++ 4 files changed, 67 insertions(+) create mode 100644 checkm2/1.0.2/Dockerfile create mode 100644 checkm2/1.0.2/README.md diff --git a/Program_Licenses.md b/Program_Licenses.md index a3d94a8a1..46d7bbe28 100644 --- a/Program_Licenses.md +++ b/Program_Licenses.md @@ -31,6 +31,7 @@ The licenses of the open-source software that is contained in these Docker image | CDC-SPN | GitHub No License | https://github.com/BenJamesMetcalf/Spn_Scripts_Reference | | cfsan-snp-pipeline | non-standard license see --> | https://github.com/CFSAN-Biostatistics/snp-pipeline/blob/master/LICENSE.txt | | CheckM | GNU GPLv3 | https://github.com/Ecogenomics/CheckM/blob/master/LICENSE | +| CheckM2 | GNU GPLv3 | https://github.com/chklovski/CheckM2/blob/main/LICENSE | | CheckV | MIT | https://bitbucket.org/berkeleylab/checkv/src/master/LICENSE.txt | | Circlator | GNU GPLv3 | https://github.com/sanger-pathogens/circlator/blob/master/LICENSE | | Circos | GNU GPLv3 | https://circos.ca/ | diff --git a/README.md b/README.md index 6977eded9..274b351ab 100644 --- a/README.md +++ b/README.md @@ -139,6 +139,7 @@ To learn more about the docker pull rate limits and the open source software pro | [CDC-SPN](https://hub.docker.com/r/staphb/cdc-spn/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/cdc-spn)](https://hub.docker.com/r/staphb/cdc-spn) |
    • 0.1 (no version)
    | https://github.com/BenJamesMetcalf/Spn_Scripts_Reference | | [cfsan-snp-pipeline](https://hub.docker.com/r/staphb/cfsan-snp-pipeline)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/cfsan-snp-pipeline)](https://hub.docker.com/r/staphb/cfsan-snp-pipeline) |
    • 2.0.2
    • 2.2.1
    | https://github.com/CFSAN-Biostatistics/snp-pipeline | | [CheckM](https://hub.docker.com/r/staphb/checkm)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/checkm)](https://hub.docker.com/r/staphb/checkm) |
    • [1.2.2](./checkm/1.2.2/)
    • [1.2.3](./checkm/1.2.3/)
    | https://github.com/Ecogenomics/CheckM | +| [CheckM2](https://hub.docker.com/r/staphb/checkm2)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/checkm2)](https://hub.docker.com/r/staphb/checkm2) |
    • [1.0.2](./checkm2/1.0.2)
    | https://github.com/chklovski/CheckM2 | | [CheckV](https://hub.docker.com/r/staphb/checkv)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/checkv)](https://hub.docker.com/r/staphb/checkv) |
    • [1.0.3](./checkv/1.0.3/)
    | https://bitbucket.org/berkeleylab/checkv/ | | [Circlator](https://hub.docker.com/r/staphb/circlator)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/circlator)](https://hub.docker.com/r/staphb/circlator) |
    • 1.5.6
    • 1.5.5
    | https://github.com/sanger-pathogens/circlator | | [Circos](https://hub.docker.com/r/staphb/circos)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/circos)](https://hub.docker.com/r/staphb/circos) |
    • [0.69-9](./circos/0.69.9/)
    | https://circos.ca/ | diff --git a/checkm2/1.0.2/Dockerfile b/checkm2/1.0.2/Dockerfile new file mode 100644 index 000000000..ad5f42502 --- /dev/null +++ b/checkm2/1.0.2/Dockerfile @@ -0,0 +1,37 @@ +FROM mambaorg/micromamba:1.5.8 AS app + +ARG CHECKM2_VERSION="1.0.2" + +USER root + +WORKDIR / + +LABEL base.image="mambaorg/micromamba:1.5.8" +LABEL dockerfile.version="1" +LABEL software="CHECKM2" +LABEL software.version="${CHECKM2_VERSION}" +LABEL description="Rapid assessment of genome bin quality using machine learning." +LABEL website="https://github.com/chklovski/CheckM2" +LABEL license="https://github.com/chklovski/CheckM2/blob/main/LICENSE" +LABEL maintainer="Kutluhan Incekara" +LABEL maintainer.email="kutluhan.incekara@ct.gov" + +RUN apt-get update && apt-get install -y --no-install-recommends \ + procps && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +RUN micromamba install --name base -c conda-forge -c bioconda checkm2=${CHECKM2_VERSION} && \ + micromamba clean -a -f -y + +ENV PATH="/opt/conda/bin/:${PATH}" \ + LC_ALL=C.UTF-8 + +CMD [ "checkm2", "--help" ] + +WORKDIR /data + +## Test ## +FROM app AS test + +RUN checkm2 database --download &&\ + checkm2 testrun --threads 4 \ No newline at end of file diff --git a/checkm2/1.0.2/README.md b/checkm2/1.0.2/README.md new file mode 100644 index 000000000..af4756b7c --- /dev/null +++ b/checkm2/1.0.2/README.md @@ -0,0 +1,28 @@ +# CheckM2 container + +Main tool: [checkm2](https://github.com/chklovski/CheckM2) + +Code repository: https://github.com/chklovski/CheckM2 + +Additional tools: +- diamond: 2.0.4 +- prodigal 2.6.3 + +Basic information on how to use this tool: +- executable: checkm2 +- help: -h, --help +- version: --version +- description: Rapid assessment of genome bin quality using machine learning. + +Additional information: + +CheckM2 relies on a external diamond database (~1.7 GB) for rapid annotation. the database can be downloaded via `checkm2 database --download` command or obtained directly from: https://zenodo.org/api/records/5571251/files/checkm2_database.tar.gz/content + + +Full documentation: https://github.com/chklovski/CheckM2 + +## Example Usage + +```bash +checkm2 predict --threads 8 fasta --input ./input_folder --output-directory ./output_folder --database_path /path/to/database/CheckM2_database/uniref100.KO.1.dmnd +``` \ No newline at end of file From 1610fdfc2bdbe5024111c025601fd177af22fd94 Mon Sep 17 00:00:00 2001 From: Sage Wright Date: Wed, 23 Oct 2024 12:19:28 -0400 Subject: [PATCH 52/92] adding krakentools version d4a2fbe (#1079) * add genoflu * add readme * add to license * add --force-pkgs-dirs * krakentools add * update readmes * silence warnings about AS casing; fix typo * added comment in dockerfile & added additional dependencies and versions to readme for krakentools * pinning biopython and pandas versions and removing unnecessary jq and gawk * fixed version of python installed listed in krakentools readme --------- Co-authored-by: Curtis Kapsak --- Program_Licenses.md | 1 + README.md | 3 ++- krakentools/d4a2fbe/Dockerfile | 47 ++++++++++++++++++++++++++++++++++ krakentools/d4a2fbe/README.md | 29 +++++++++++++++++++++ 4 files changed, 79 insertions(+), 1 deletion(-) create mode 100644 krakentools/d4a2fbe/Dockerfile create mode 100644 krakentools/d4a2fbe/README.md diff --git a/Program_Licenses.md b/Program_Licenses.md index 46d7bbe28..7e0049c8e 100644 --- a/Program_Licenses.md +++ b/Program_Licenses.md @@ -86,6 +86,7 @@ The licenses of the open-source software that is contained in these Docker image | kma | Apache v2.0 | https://bitbucket.org/genomicepidemiology/kma/src/master/ | | Kraken | GNU GPLv3 | https://github.com/DerrickWood/kraken/blob/master/LICENSE | | Kraken2 | MIT | https://github.com/DerrickWood/kraken2/blob/master/LICENSE | +| KrakenTools | GNU GPLv3 | https://github.com/jenniferlu717/KrakenTools/blob/master/LICENSE | | KrakenUniq | GNU GPLv3 | https://github.com/fbreitwieser/krakenuniq/blob/master/LICENSE | | kSNP3 | BSD | available in zipped kSNP archive on sourceforge or in docker image under `/kSNP3.1_Linux_package/THE BSD OPENSOURCE LICENSE.pdf` | | kSNP4 | BSD | available in zipped kSNP archive on sourceforge or in docker image under `/opt/kSNP4 Linux package/Documentation/THE BSD OPENSOURCE LICENSE.pdf` | diff --git a/README.md b/README.md index 274b351ab..39b0582f9 100644 --- a/README.md +++ b/README.md @@ -194,7 +194,8 @@ To learn more about the docker pull rate limits and the open source software pro | [Kleborate](https://hub.docker.com/r/staphb/kleborate/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kleborate)](https://hub.docker.com/r/staphb/kleborate) |
    • [2.0.4](./kleborate/2.0.4/)
    • [2.1.0](./kleborate/2.1.0/)
    • [2.2.0](./kleborate/2.3.2/)
    • [2.3.2](./kleborate/2.3.2)
    • [2.3.2-2023-05](kleborate/2.3.2-2023-05/)
    • [2.4.1](kleborate/2.4.1/)
    | https://github.com/katholt/Kleborate/
    https://github.com/katholt/Kaptive/ | | [kma](https://hub.docker.com/r/staphb/kma/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kma)](https://hub.docker.com/r/staphb/kma) |
    • 1.2.21
    • 1.4.10 (no database)
    • [1.4.14](./kma/1.4.14/) (no database)
    | https://bitbucket.org/genomicepidemiology/kma/ | | [Kraken](https://hub.docker.com/r/staphb/kraken/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kraken)](https://hub.docker.com/r/staphb/kraken) |
    • 1.0
    • 1.1.1
    • 1.1.1 (no database)
    | https://github.com/DerrickWood/kraken | -| [Kraken2](https://hub.docker.com/r/staphb/kraken2/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kraken2)](https://hub.docker.com/r/staphb/kraken2) |
    • 2.0.8-beta (no database)
    • 2.0.8-beta (MiniKraken2_v1_8GB db)
    • 2.0.8-beta_hv (human + virus db)
    • 2.0.9-beta (no db)
    • 2.0.9-beta (Minikraken v2 RefSeq: bacteria, archaea, viral, and human 8GB db)
    • 2.1.0 (no db)
    • 2.1.1 (no db)
    • 2.1.2 (no db)
    • [2.1.3](kraken2/2.1.3/) (no db)
    | https://github.com/DerrickWood/kraken2 | +| [Kraken2](https://hub.docker.com/r/staphb/kraken2/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kraken2)](https://hub.docker.com/r/staphb/kraken2) |
    • 2.0.8-beta (no database)
    • 2.0.8-beta (MiniKraken2_v1_8GB db)
    • 2.0.8-beta_hv (human + virus db)
    • 2.0.9-beta (no db)
    • 2.0.9-beta (Minikraken v2 RefSeq: bacteria, archaea, viral, and human 8GB db)
    • 2.1.0 (no db)
    • 2.1.1 (no db)
    • 2.1.2 (no db)
    • [2.1.3](kraken2/2.1.3/) (no db)
    | https://github.com/DerrickWood/kraken2 | +| [KrakenTools](https://github.com/jenniferlu717/KrakenTools)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/krakentools)](https://hub.docker.com/r/staphb/krakentools) |
    • [d4a2fbe](./krakentools/d4a2fbe)
    | https://github.com/jenniferlu717/KrakenTools | | [KrakenUniq](https://hub.docker.com/r/staphb/krakenuniq/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/krakenuniq)](https://hub.docker.com/r/staphb/krakenuniq) |
    • [1.0.4](./krakenuniq/1.0.4) (no database)
    | https://github.com/fbreitwieser/krakenuniq | | [kSNP3](https://hub.docker.com/r/staphb/ksnp3/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/ksnp3)](https://hub.docker.com/r/staphb/ksnp3)|
    • 3.1
    | https://sourceforge.net/projects/ksnp/ | | [kSNP4](https://hub.docker.com/r/staphb/ksnp4/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/ksnp4)](https://hub.docker.com/r/staphb/ksnp4)|
    • 4.0
    • [4.1](./ksnp4/4.1/)
    | https://sourceforge.net/projects/ksnp/ | diff --git a/krakentools/d4a2fbe/Dockerfile b/krakentools/d4a2fbe/Dockerfile new file mode 100644 index 000000000..20691e85e --- /dev/null +++ b/krakentools/d4a2fbe/Dockerfile @@ -0,0 +1,47 @@ +FROM ubuntu:jammy AS app + +WORKDIR / + +# using a git commit because the last release was over three years ago, despite recent(ish) activity in the repo's main branch +# this commit is from 2023-11-16: https://github.com/jenniferlu717/KrakenTools/commit/d4a2fbe2833c2392a724697c0c97a3014e748474 +ARG KRAKENTOOLS_VERSION="d4a2fbe2833c2392a724697c0c97a3014e748474" + +# LABEL instructions tag the image with metadata that might be important to the user +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="KrakenTools" +LABEL software.version=${KRAKENTOOLS_VERSION} +LABEL description="KrakenTools is a set of tools for processing Kraken output" +LABEL website="https://github.com/jenniferlu717/KrakenTools" +LABEL documentation="https://github.com/jenniferlu717/KrakenTools" +LABEL license="https://github.com/jenniferlu717/KrakenTools/blob/master/LICENSE" +LABEL maintainer="Sage Wright" +LABEL maintainer.email="sagemwright@gmail.com" + + +# Install dependencies via apt-get; cleanup apt garbage +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + python3 \ + python3-pip \ + python3-setuptools \ + git \ + procps && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +RUN pip install biopython==1.84 \ + pandas==2.2.3 + +RUN git clone https://github.com/jenniferlu717/KrakenTools.git && \ + cd KrakenTools && \ + git checkout ${KRAKENTOOLS_VERSION} && \ + chmod +x * + +ENV PATH=/KrakenTools:${PATH} + +WORKDIR /data + +FROM app AS test + +RUN python3 /KrakenTools/extract_kraken_reads.py --help \ No newline at end of file diff --git a/krakentools/d4a2fbe/README.md b/krakentools/d4a2fbe/README.md new file mode 100644 index 000000000..8794ae695 --- /dev/null +++ b/krakentools/d4a2fbe/README.md @@ -0,0 +1,29 @@ +# KrakenTools container + +Main tool [KrakenTools](https://github.com/jenniferlu717/KrakenTools) + +Code repository: https://github.com/jenniferlu717/KrakenTools + +Additional tools: + +- python 3.10.12 +- biopython 1.84 +- pandas 2.2.3 +- numpy 2.1.2 + +Basic information on how to use this tool: + +- executable: various python scripts +- help: most scripts have -h options +- version: most scripts do not have versioning information +- description: "KrakenTools is a suite of scripts to be used alongside the Kraken, KrakenUniq, Kraken 2, or Bracken programs. These scripts are designed to help Kraken users with downstream analysis of Kraken results." + +Additional information: + +Full documentation: [https://github.com/jenniferlu717/KrakenTools](https://github.com/jenniferlu717/KrakenTools) + +## Example Usage + +```bash +python3 /KrakenTools/extract_kraken_reads.py -h +``` From 52c1c1209d8c84df5b33144f94f950e06b8b7c27 Mon Sep 17 00:00:00 2001 From: Young Date: Tue, 29 Oct 2024 06:21:40 -0600 Subject: [PATCH 53/92] updating freyja to 1.5.2 (#1082) * updating freyja to 1.5.2 * removed -vv --- .github/workflows/update_freyja.yml | 4 +- README.md | 2 +- freyja/1.5.2/Dockerfile | 103 ++++++++++++++++++++++++++++ freyja/1.5.2/README.md | 23 +++++++ 4 files changed, 129 insertions(+), 3 deletions(-) create mode 100644 freyja/1.5.2/Dockerfile create mode 100644 freyja/1.5.2/README.md diff --git a/.github/workflows/update_freyja.yml b/.github/workflows/update_freyja.yml index 054cdd6d4..367599a20 100644 --- a/.github/workflows/update_freyja.yml +++ b/.github/workflows/update_freyja.yml @@ -9,7 +9,7 @@ name: Update Freyja on: workflow_dispatch: schedule: - - cron: '30 7 1 * *' + - cron: '30 7 * * 1' run-name: Updating Freyja @@ -23,7 +23,7 @@ jobs: - name: set freyja version id: latest_version run: | - version=1.5.1 + version=1.5.2 echo "version=$version" >> $GITHUB_OUTPUT file=freyja/$version/Dockerfile diff --git a/README.md b/README.md index 39b0582f9..29604aafc 100644 --- a/README.md +++ b/README.md @@ -170,7 +170,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Filtlong](https://hub.docker.com/r/staphb/filtlong)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/filtlong)](https://hub.docker.com/r/staphb/filtlong) |
    • 0.2.0
    • 0.2.1
    | https://github.com/rrwick/filtlong | | [FLASH](https://hub.docker.com/r/staphb/flash)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/flash)](https://hub.docker.com/r/staphb/flash) |
    • 1.2.11
    | http://ccb.jhu.edu/software/FLASH | | [Flye](https://hub.docker.com/r/staphb/flye)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/flye)](https://hub.docker.com/r/staphb/flye) |
    • [2.5](flye/2.5/)
    • [2.7](flye/2.7/)
    • [2.8](flye/2.8/)
    • [2.9](flye/2.9/)
    • [2.9.1](flye/2.9.1/)
    • [2.9.2](flye/2.9.2/)
    • [2.9.3](flye/2.9.3/)
    • [2.9.4](flye/2.9.4/)
    | https://github.com/fenderglass/Flye | -| [Freyja](https://hub.docker.com/r/staphb/freyja)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/freyja)](https://hub.docker.com/r/staphb/freyja) |
    • [1.2](./freyja/1.2/)
    • [1.2.1](./freyja/1.2.1/)
    • [1.3.1](./freyja/1.3.1/)
    • [1.3.2](./freyja/1.3.2/)
    • [1.3.4](./freyja/1.3.4/)
    • [1.3.7](./freyja/1.3.7/)
    • [1.3.8](./freyja/1.3.8/)
    • [1.3.9](./freyja/1.3.9/)
    • [1.3.10](./freyja/1.3.10/)
    • [1.3.11](./freyja/1.3.11/)
    • [1.3.12](./freyja/1.3.12/)
    • [1.4.2](./freyja/1.4.2/)
    • [1.4.3](freyja/1.4.3/)
    • [1.4.4](freyja/1.4.4/)
    • [1.4.5](freyja/1.4.5/)
    • [1.4.7](freyja/1.4.7/)
    • [1.4.8](freyja/1.4.8/)
    • [1.4.9](freyja/1.4.9/)
    • [1.5.0](freyja/1.5.0/)
    • [1.5.1](freyja/1.5.1/)
    | https://github.com/andersen-lab/Freyja | +| [Freyja](https://hub.docker.com/r/staphb/freyja)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/freyja)](https://hub.docker.com/r/staphb/freyja) |
    • [1.2](./freyja/1.2/)
    • [1.2.1](./freyja/1.2.1/)
    • [1.3.1](./freyja/1.3.1/)
    • [1.3.2](./freyja/1.3.2/)
    • [1.3.4](./freyja/1.3.4/)
    • [1.3.7](./freyja/1.3.7/)
    • [1.3.8](./freyja/1.3.8/)
    • [1.3.9](./freyja/1.3.9/)
    • [1.3.10](./freyja/1.3.10/)
    • [1.3.11](./freyja/1.3.11/)
    • [1.3.12](./freyja/1.3.12/)
    • [1.4.2](./freyja/1.4.2/)
    • [1.4.3](freyja/1.4.3/)
    • [1.4.4](freyja/1.4.4/)
    • [1.4.5](freyja/1.4.5/)
    • [1.4.7](freyja/1.4.7/)
    • [1.4.8](freyja/1.4.8/)
    • [1.4.9](freyja/1.4.9/)
    • [1.5.0](freyja/1.5.0/)
    • [1.5.1](freyja/1.5.1/)
    • [1.5.2](freyja/1.5.2/)
    | https://github.com/andersen-lab/Freyja | | [GAMBIT](https://hub.docker.com/r/staphb/gambit)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/gambit)](https://hub.docker.com/r/staphb/gambit) |
    • 0.3.0
    • 0.4.0
    • 0.5.0
    • 1.0.0
    | https://github.com/jlumpe/gambit | | [GAMMA](https://hub.docker.com/r/staphb/gamma)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/gamma)](https://hub.docker.com/r/staphb/gamma) |
    • 1.4
    • 2.1
    • 2.2
    | https://github.com/rastanton/GAMMA/ | | [GenoFLU](https://hub.docker.com/r/staphb/genoflu)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/genoflu)]() |
    • [1.03](genoflu/1.03/)
    | https://github.com/USDA-VS/GenoFLU | diff --git a/freyja/1.5.2/Dockerfile b/freyja/1.5.2/Dockerfile new file mode 100644 index 000000000..2f94e18e5 --- /dev/null +++ b/freyja/1.5.2/Dockerfile @@ -0,0 +1,103 @@ +FROM mambaorg/micromamba:1.5.8 as app + +# Version arguments +# ARG variables only persist during build time +ARG FREYJA_SOFTWARE_VERSION="1.5.2" +ARG IVAR_VER="1.4.3" +ARG SAMTOOLS_VER="1.21" +ARG USHER_VER="0.6.3" + + +# build and run as root users since micromamba image has 'mambauser' set as the $USER +USER root +# set workdir to default for building; set to /data at the end +WORKDIR / + +LABEL base.image="mambaorg/micromamba:1.5.8" +LABEL dockerfile.version="1" +LABEL software="Freyja" +LABEL software.version=${FREYJA_SOFTWARE_VERSION} +LABEL description="Freyja is a tool to recover relative lineage abundances from mixed SARS-CoV-2 samples from a sequencing dataset (BAM aligned to the Hu-1 reference)" +LABEL website="https://github.com/andersen-lab/Freyja" +LABEL license="https://github.com/andersen-lab/Freyja/blob/main/LICENSE" +LABEL maintainer="Kevin Libuit" +LABEL maintainer.email="kevin.libuit@theiagen.com" +LABEL maintainer2="Curtis Kapsak" +LABEL maintainer2.email="curtis.kapsak@theiagen.com" +LABEL maintainer3="Erin Young" +LABEL maintainer3.email="eriny@utah.gov" + +# install dependencies; cleanup apt garbage +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + procps \ + git && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# Create Freyja conda environment called freyja-env from bioconda recipe +# clean up conda garbage +RUN micromamba create -n freyja-env -c conda-forge -c bioconda -c defaults \ + ivar=${IVAR_VER} \ + usher=${USHER_VER} \ + samtools=${SAMTOOLS_VER} \ + pip \ + biopython \ + click \ + cvxpy \ + epiweeks \ + joblib \ + matplotlib-base \ + numpy \ + pandas \ + plotly \ + pyarrow \ + pysam \ + pyyaml \ + requests \ + seaborn \ + tqdm && \ + micromamba clean -a -y -f + +# set the environment, put new conda env in PATH by default +ENV PATH="/opt/conda/envs/freyja-env/bin:/opt/conda/envs/env/bin:${PATH}" \ + LC_ALL=C.UTF-8 + +RUN wget -q https://github.com/andersen-lab/Freyja/archive/refs/tags/v${FREYJA_SOFTWARE_VERSION}.tar.gz && \ + pip install --no-cache-dir v${FREYJA_SOFTWARE_VERSION}.tar.gz && \ + rm v${FREYJA_SOFTWARE_VERSION}.tar.gz + + +# update barcodes +# NOTE: this will download the latest version of the `freyja/data/usher_barcodes.csv` file from GitHub +RUN freyja update + +# set working directory to /data +WORKDIR /data + +# default command is to pull up help options +CMD [ "freyja", "--help" ] + +# new base for testing +FROM app as test + +RUN freyja --help && freyja --version + +# Grab test data from Freyja version 1.3.4 +RUN wget -O /data/Freyja_WWSC2.bam https://github.com/StaPH-B/docker-builds/blob/master/freyja/1.3.4/tests/Freyja_WWSC2.bam?raw=true && \ + wget -P /data https://raw.githubusercontent.com/StaPH-B/docker-builds/master/freyja/1.3.4/tests/Freyja_depths.tsv && \ + wget -P /data https://raw.githubusercontent.com/StaPH-B/docker-builds/master/freyja/1.3.4/tests/Freyja_variants.tsv && \ + wget -P /data https://raw.githubusercontent.com/StaPH-B/docker-builds/master/freyja/1.3.4/tests/nCoV-2019.reference.fasta + +# Run Freyja +RUN freyja variants /data/Freyja_WWSC2.bam --variants /data/test_variants.tsv --depths /data/test_depths.tsv --ref /data/nCoV-2019.reference.fasta && \ + freyja demix /data/test_variants.tsv /data/test_depths.tsv --output /data/test_demix.tsv + +# Check validity of outputs +RUN head /data/test_variants.tsv && \ + head /data/test_depths.tsv && \ + head /data/test_demix.tsv && \ + grep "Omicron" /data/test_demix.tsv + +# print barcode version and freyja version +RUN freyja demix --version diff --git a/freyja/1.5.2/README.md b/freyja/1.5.2/README.md new file mode 100644 index 000000000..0477ab028 --- /dev/null +++ b/freyja/1.5.2/README.md @@ -0,0 +1,23 @@ +# freyja container + +Main tool & documentation: [freyja](https://github.com/andersen-lab/Freyja) + +Freyja is a tool to recover relative lineage abundances from mixed SARS-CoV-2 samples from a sequencing dataset (BAM aligned to the Hu-1 reference). The method uses lineage-determining mutational "barcodes" derived from the UShER global phylogenetic tree as a basis set to solve the constrained (unit sum, non-negative) de-mixing problem. + +## freyja barcodes + +This docker image was built on **2024-10-28** and the command `freyja update` is run as part of the build to retrieve the most up-to-date database. The barcode version included in this docker image is **`10_27_2024-01-41`** as reported by `freyja demix --version` + +This image is rebuilt every day on Dockerhub and Quay.io with the tag ${freyja version}-${freyja database version}-${data image was deployed}. + +## Example Usage + +```bash +# run freyja variants to call variants from an aligned SC2 bam file +freyja variants [bamfile] --variants [variant outfile name] --depths [depths outfile name] --ref [reference.fa] + +# run freyja demix to identify lineages based on called variants +freyja demix [variants-file] [depth-file] --output [output-file] +``` + +Warning: `freyja update` does not work under all conditions. You may need to specify an output directory (`freyja update --outdir /path/to/outdir`) for which your user has write privileges, such as a mounted volume. From b98256ba6484cef8d9eff0db5c406d8a93240dd2 Mon Sep 17 00:00:00 2001 From: Kincekara Date: Tue, 29 Oct 2024 12:48:38 +0000 Subject: [PATCH 54/92] fix bbtools error --- bbtools/39.10/Dockerfile | 1 + 1 file changed, 1 insertion(+) diff --git a/bbtools/39.10/Dockerfile b/bbtools/39.10/Dockerfile index 34c3c6218..881799bee 100644 --- a/bbtools/39.10/Dockerfile +++ b/bbtools/39.10/Dockerfile @@ -30,6 +30,7 @@ RUN apt-get update && \ pbzip2 \ lbzip2 \ bzip2 \ + libdeflate-dev \ wget \ ca-certificates \ procps && \ From b4cc31438387d613fb6a32849d2a4cda1712de8a Mon Sep 17 00:00:00 2001 From: Young Date: Tue, 29 Oct 2024 12:40:25 -0600 Subject: [PATCH 55/92] adding rasusa version 2.1.0 (#1067) * adding rasusa version 2.1.0 * gnu --- README.md | 2 +- rasusa/2.1.0/Dockerfile | 54 +++++++++++++++++++++++++++++++++++++++++ rasusa/2.1.0/README.md | 32 ++++++++++++++++++++++++ 3 files changed, 87 insertions(+), 1 deletion(-) create mode 100644 rasusa/2.1.0/Dockerfile create mode 100644 rasusa/2.1.0/README.md diff --git a/README.md b/README.md index 29604aafc..66943bd3b 100644 --- a/README.md +++ b/README.md @@ -258,7 +258,7 @@ To learn more about the docker pull rate limits and the open source software pro | [QUAST](https://hub.docker.com/r/staphb/quast/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/quast)](https://hub.docker.com/r/staphb/quast) |
    • 5.0.0
    • 5.0.2
    • [5.2.0](./quast/5.2.0)
    • [5.2.0-slim](./quast/5.2.0-slim)
    | https://github.com/ablab/quast | | [QuickSNP](https://hub.docker.com/r/staphb/quicksnp/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/quicksnp)](https://hub.docker.com/r/staphb/quicksnp) |
    • 1.0.1
    | https://github.com/k-florek/QuickSNP | | [racon](https://hub.docker.com/r/staphb/racon)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/racon)](https://hub.docker.com/r/staphb/racon)|
    • [1.4.3](./racon/1.4.3/)
    • [1.4.20](./racon/1.4.20/)
    • [1.5.0](./racon/1.5.0/)
    |
  • https://github.com/lbcb-sci/racon
  • https://github.com/isovic/racon (ARCHIVED)
    • | -| [rasusa](https://hub.docker.com/r/staphb/rasusa/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/rasusa)](https://hub.docker.com/r/staphb/rasusa) |
    • [0.1.0](./rasusa/0.1.0/)
    • [0.2.0](./rasusa/0.2.0/)
    • [0.3.0](./rasusa/0.3.0/)
    • [0.6.0](./rasusa/0.6.0/)
    • [0.7.0](./rasusa/0.7.0/)
    • [0.8.0](./rasusa/0.8.0/)
    • [2.0.0](./rasusa/2.0.0/)
    | https://github.com/mbhall88/rasusa | +| [rasusa](https://hub.docker.com/r/staphb/rasusa/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/rasusa)](https://hub.docker.com/r/staphb/rasusa) |
    • [0.1.0](./rasusa/0.1.0/)
    • [0.2.0](./rasusa/0.2.0/)
    • [0.3.0](./rasusa/0.3.0/)
    • [0.6.0](./rasusa/0.6.0/)
    • [0.7.0](./rasusa/0.7.0/)
    • [0.8.0](./rasusa/0.8.0/)
    • [2.0.0](./rasusa/2.0.0/)
    • [2.1.0](./rasusa/2.1.0/)
    | https://github.com/mbhall88/rasusa | | [raven](https://hub.docker.com/r/staphb/raven/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/raven)](https://hub.docker.com/r/staphb/raven) |
    • 1.5.1
    • 1.8.1
    • [1.8.3](./raven/1.8.3)
    | https://github.com/lbcb-sci/raven | | [RAxML](https://hub.docker.com/r/staphb/raxml/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/raxml)](https://hub.docker.com/r/staphb/raxml) |
    • 8.2.12
    • [8.2.13](./raxml/8.2.13/)
    | https://github.com/stamatak/standard-RAxML | | [RAxML-NG](https://hub.docker.com/r/staphb/raxml-ng/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/raxml-ng)](https://hub.docker.com/r/staphb/raxml-ng) |
    • [1.2.2](./raxml-ng/1.2.2/)
    | https://github.com/amkozlov/raxml-ng | diff --git a/rasusa/2.1.0/Dockerfile b/rasusa/2.1.0/Dockerfile new file mode 100644 index 000000000..7c8b0ce7c --- /dev/null +++ b/rasusa/2.1.0/Dockerfile @@ -0,0 +1,54 @@ +FROM ubuntu:jammy as app + +ARG RASUSA_VER="2.1.0" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="rasusa" +LABEL software.version="${RASUSA_VER}" +LABEL description="Randomly subsample sequencing reads to a specified coverage." +LABEL website="https://github.com/mbhall88/rasusa" +LABEL license="https://github.com/mbhall88/rasusa/blob/master/LICENSE" +LABEL maintainer="Jake Garfin" +LABEL maintainer.email="jake.garfin@state.mn.us" +LABEL maintainer2="Curtis Kapsak" +LABEL maintainer2.email="kapsakcj@gmail.com" +LABEL maintainer3="Erin Young" +LABEL maintainer3.email="eriny@utah.gov" + +# install wget and cleanup apt garbage +RUN apt-get update && apt-get -y install --no-install-recommends \ + wget \ + ca-certificates \ + procps && \ + apt-get autoclean && \ + rm -rf /var/lib/apt/lists/* + +# install rasusa +RUN wget -q https://github.com/mbhall88/rasusa/releases/download/${RASUSA_VER}/rasusa-${RASUSA_VER}-x86_64-unknown-linux-gnu.tar.gz && \ + tar -xvf rasusa-${RASUSA_VER}-x86_64-unknown-linux-gnu.tar.gz && \ + rm -rf rasusa-${RASUSA_VER}-x86_64-unknown-linux-gnu.tar.gz && \ + mkdir /data + +# set PATH and perl locale settings +ENV PATH="${PATH}:/rasusa-${RASUSA_VER}-x86_64-unknown-linux-gnu/" \ + LC_ALL=C + +WORKDIR /data + +CMD rasusa --help + +FROM app as test + +# print version and help options +RUN rasusa --version && rasusa --help + +# cannot run rust-based test, since rust isn't installed, but just testing basic command on SC2 reads in our repo +# inputs FASTQs each have 80867 reads +# output FASTQs should have 40434 reads in each (about 1/2 of input) +# -s 1 is for setting a specific seed +# -O is for gzip compression on output FASTQs +RUN wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_1.fastq.gz && \ + wget -q https://github.com/StaPH-B/docker-builds/raw/master/tests/SARS-CoV-2/SRR13957123_2.fastq.gz && \ + rasusa reads --num 40434 -s 1 -O g -o SRR13957123_downsampled_1.fastq.gz -o SRR13957123_downsampled_2.fastq.gz SRR13957123_1.fastq.gz SRR13957123_2.fastq.gz && \ + ls -lh diff --git a/rasusa/2.1.0/README.md b/rasusa/2.1.0/README.md new file mode 100644 index 000000000..ffa71ab15 --- /dev/null +++ b/rasusa/2.1.0/README.md @@ -0,0 +1,32 @@ +# Rasusa container + +Main tool : [Rasusa](https://github.com/mbhall88/rasusa) + +Additional tools: + +- none + +Full documentation: https://github.com/mbhall88/rasusa + +Randomly subsample sequencing reads to a specified coverage + +## Example Usage + +```bash +# sars-cov-2 example, paired-end illumina +rasusa reads \ + -n 40434 \ # downsample to specific number of reads per FASTQ file + -s 1 \ # set seed + -O g \ # set output file compression format as gzip + -o SRR13957123_downsampled_1.fastq.gz -o SRR13957123_downsampled_2.fastq.gz \ + SRR13957123_1.fastq.gz SRR13957123_2.fastq.gz + +# Salmonella enterica example, paired-end illumina +rasusa reads \ + --coverage 100 \ # use 100X coverage for downsampling + --genome-size 5M \ # downsample to specific coverage based on genome size (5 million bases) + -s 1 \ # set seed + -O g \ # set output file compression format as gzip + -o SRR10992628_downsampled_1.fastq.gz -o SRR10992628_downsampled_2.fastq.gz \ + SRR10992628_1.fastq.gz SRR10992628_2.fastq.gz +``` From ab858d18ce38a20ac2256583ecd8adc8dbb7caa6 Mon Sep 17 00:00:00 2001 From: Young Date: Tue, 29 Oct 2024 13:43:30 -0600 Subject: [PATCH 56/92] adding flye version 2.9.5 (#1058) * adding flye version 2.9.5 * added builder stage --- README.md | 2 +- flye/2.9.5/Dockerfile | 72 +++++++++++++++++++++++++++++++++++++++++++ flye/2.9.5/README.md | 14 +++++++++ 3 files changed, 87 insertions(+), 1 deletion(-) create mode 100644 flye/2.9.5/Dockerfile create mode 100644 flye/2.9.5/README.md diff --git a/README.md b/README.md index 66943bd3b..90ea43a87 100644 --- a/README.md +++ b/README.md @@ -169,7 +169,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Freebayes](https://hub.docker.com/r/staphb/freebayes)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/freebayes)](https://hub.docker.com/r/staphb/freebayes) |
    • 1.3.6
    • 1.3.7
    • 1.3.7
    • 1.3.7
    | https://github.com/freebayes/freebayes | | [Filtlong](https://hub.docker.com/r/staphb/filtlong)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/filtlong)](https://hub.docker.com/r/staphb/filtlong) |
    • 0.2.0
    • 0.2.1
    | https://github.com/rrwick/filtlong | | [FLASH](https://hub.docker.com/r/staphb/flash)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/flash)](https://hub.docker.com/r/staphb/flash) |
    • 1.2.11
    | http://ccb.jhu.edu/software/FLASH | -| [Flye](https://hub.docker.com/r/staphb/flye)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/flye)](https://hub.docker.com/r/staphb/flye) |
    • [2.5](flye/2.5/)
    • [2.7](flye/2.7/)
    • [2.8](flye/2.8/)
    • [2.9](flye/2.9/)
    • [2.9.1](flye/2.9.1/)
    • [2.9.2](flye/2.9.2/)
    • [2.9.3](flye/2.9.3/)
    • [2.9.4](flye/2.9.4/)
    | https://github.com/fenderglass/Flye | +| [Flye](https://hub.docker.com/r/staphb/flye)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/flye)](https://hub.docker.com/r/staphb/flye) |
    • [2.5](flye/2.5/)
    • [2.7](flye/2.7/)
    • [2.8](flye/2.8/)
    • [2.9](flye/2.9/)
    • [2.9.1](flye/2.9.1/)
    • [2.9.2](flye/2.9.2/)
    • [2.9.3](flye/2.9.3/)
    • [2.9.4](flye/2.9.4/)
    • [2.9.5](./flye/2.9.5/)
    | https://github.com/fenderglass/Flye | | [Freyja](https://hub.docker.com/r/staphb/freyja)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/freyja)](https://hub.docker.com/r/staphb/freyja) |
    • [1.2](./freyja/1.2/)
    • [1.2.1](./freyja/1.2.1/)
    • [1.3.1](./freyja/1.3.1/)
    • [1.3.2](./freyja/1.3.2/)
    • [1.3.4](./freyja/1.3.4/)
    • [1.3.7](./freyja/1.3.7/)
    • [1.3.8](./freyja/1.3.8/)
    • [1.3.9](./freyja/1.3.9/)
    • [1.3.10](./freyja/1.3.10/)
    • [1.3.11](./freyja/1.3.11/)
    • [1.3.12](./freyja/1.3.12/)
    • [1.4.2](./freyja/1.4.2/)
    • [1.4.3](freyja/1.4.3/)
    • [1.4.4](freyja/1.4.4/)
    • [1.4.5](freyja/1.4.5/)
    • [1.4.7](freyja/1.4.7/)
    • [1.4.8](freyja/1.4.8/)
    • [1.4.9](freyja/1.4.9/)
    • [1.5.0](freyja/1.5.0/)
    • [1.5.1](freyja/1.5.1/)
    • [1.5.2](freyja/1.5.2/)
    | https://github.com/andersen-lab/Freyja | | [GAMBIT](https://hub.docker.com/r/staphb/gambit)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/gambit)](https://hub.docker.com/r/staphb/gambit) |
    • 0.3.0
    • 0.4.0
    • 0.5.0
    • 1.0.0
    | https://github.com/jlumpe/gambit | | [GAMMA](https://hub.docker.com/r/staphb/gamma)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/gamma)](https://hub.docker.com/r/staphb/gamma) |
    • 1.4
    • 2.1
    • 2.2
    | https://github.com/rastanton/GAMMA/ | diff --git a/flye/2.9.5/Dockerfile b/flye/2.9.5/Dockerfile new file mode 100644 index 000000000..cdba1cd6b --- /dev/null +++ b/flye/2.9.5/Dockerfile @@ -0,0 +1,72 @@ +ARG FLYE_VER="2.9.5" + +FROM ubuntu:jammy as builder + +ARG FLYE_VER + +RUN apt-get update && apt-get install --no-install-recommends -y \ + make \ + gcc \ + g++ \ + python3 \ + python3-pip \ + python3-setuptools \ + zlib1g-dev \ + wget \ + ca-certificates \ + procps && \ + rm -rf /var/lib/apt/lists/* && apt-get autoclean + +RUN wget -q https://github.com/fenderglass/Flye/archive/${FLYE_VER}.tar.gz && \ + tar -xf ${FLYE_VER}.tar.gz && \ + cd Flye-${FLYE_VER} && \ + python3 setup.py install + +FROM ubuntu:jammy as app + +ARG FLYE_VER + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="Flye" +LABEL software.version="${FLYE_VER}" +LABEL description="Fast and accurate de novo assembler for single molecule sequencing reads" +LABEL website="https://github.com/fenderglass/Flye" +LABEL license="https://github.com/fenderglass/Flye/blob/flye/LICENSE" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" +LABEL maintainer2="Curtis Kapsak" +LABEL maintainer2.email="kapsakcj@gmail.com" + +# Minimal requirements to run Flye in final image +# python3-distutils is required for test_toy.py , but might not be needed at runtime +RUN apt-get update && apt-get install --no-install-recommends -y \ + python3 \ + python3-distutils \ + procps && \ + rm -rf /var/lib/apt/lists/* && apt-get autoclean + +COPY --from=builder /usr/local/lib/python3.10/dist-packages /usr/local/lib/python3.10/dist-packages +COPY --from=builder /usr/local/bin /usr/local/bin + +WORKDIR /data +CMD ["flye", "--help"] + +# For Singularity compatibility +ENV LC_ALL=C + +FROM app as test + +# Run Flye version and help for quick validation +RUN flye --version && flye --help + +# Copy Flye source files from builder for running tests +COPY --from=builder /Flye-${FLYE_VER} /Flye-${FLYE_VER} + +# Run Flye's built-in toy dataset test +RUN python3 /Flye-${FLYE_VER}/flye/tests/test_toy.py + +# Download test data and perform an assembly +RUN apt-get update && apt-get install --no-install-recommends -y wget ca-certificates && \ + wget -q https://raw.githubusercontent.com/bactopia/bactopia-tests/main/data/species/portiera/nanopore/ERR3772599.fastq.gz && \ + flye --nano-raw ERR3772599.fastq.gz -o flye-test-portiera -t 2 diff --git a/flye/2.9.5/README.md b/flye/2.9.5/README.md new file mode 100644 index 000000000..daefd49eb --- /dev/null +++ b/flye/2.9.5/README.md @@ -0,0 +1,14 @@ +# Flye container + +Main tool : [flye](https://github.com/fenderglass/Flye) + +Full documentation: [https://github.com/fenderglass/Flye/blob/flye/docs/USAGE.md](https://github.com/fenderglass/Flye/blob/flye/docs/USAGE.md) + +> Flye is a de novo assembler for single-molecule sequencing reads, such as those produced by PacBio and Oxford Nanopore Technologies. + +## Example Usage + +```bash +# sample.fastq.gz is compressed with bgzip +flye --nano-raw sample.fastq.gz --threads 12 --out-dir flye/sample +``` From 92aaa5be0f4b83796c8b252433375f4944eebf8a Mon Sep 17 00:00:00 2001 From: Young Date: Thu, 31 Oct 2024 07:06:46 -0600 Subject: [PATCH 57/92] adding elgato version 1.20.1 (#1088) --- README.md | 2 +- elgato/1.20.1/Dockerfile | 55 ++++++++++++++++++++++++++++++++++++++++ elgato/1.20.1/README.md | 33 ++++++++++++++++++++++++ 3 files changed, 89 insertions(+), 1 deletion(-) create mode 100644 elgato/1.20.1/Dockerfile create mode 100644 elgato/1.20.1/README.md diff --git a/README.md b/README.md index 90ea43a87..f1f724db8 100644 --- a/README.md +++ b/README.md @@ -155,7 +155,7 @@ To learn more about the docker pull rate limits and the open source software pro | [dragonflye](https://hub.docker.com/r/staphb/dragonflye)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/dragonflye)](https://hub.docker.com/r/staphb/dragonflye) |
    • [1.0.14](./dragonflye/1.0.14/)
    • [1.1.1](./dragonflye/1.1.1/)
    • [1.1.2](./dragonflye/1.1.2/)
    • [1.2.0](./dragonflye/1.2.0/)
    • [1.2.1](./dragonflye/1.2.1/)
    | https://github.com/rpetit3/dragonflye | | [Dr. PRG ](https://hub.docker.com/r/staphb/drprg)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/drprg)](https://hub.docker.com/r/staphb/drprg) |
    • [0.1.1](drprg/0.1.1/)
    | https://mbh.sh/drprg/ | | [DSK](https://hub.docker.com/r/staphb/dsk)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/dsk)](https://hub.docker.com/r/staphb/dsk) |
    • [0.0.100](./dsk/0.0.100/)
    • [2.3.3](./dsk/2.3.3/)
    | https://gatb.inria.fr/software/dsk/ | -| [el_gato](https://hub.docker.com/r/staphb/elgato)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/elgato)](https://hub.docker.com/r/staphb/elgato) |
    • [1.15.2](./elgato/1.15.2)
    • [1.18.2](./elgato/1.18.2)
    • [1.19.0](./elgato/1.19.0)
      • [1.20.0](./elgato/1.20.0)
    | https://github.com/appliedbinf/el_gato | +| [el_gato](https://hub.docker.com/r/staphb/elgato)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/elgato)](https://hub.docker.com/r/staphb/elgato) |
    • [1.15.2](./elgato/1.15.2)
    • [1.18.2](./elgato/1.18.2)
    • [1.19.0](./elgato/1.19.0)
    • [1.20.0](./elgato/1.20.0)
    • [1.20.1](./elgato/1.20.1)
    | https://github.com/appliedbinf/el_gato | | [emboss](https://hub.docker.com/r/staphb/emboss)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/emboss)](https://hub.docker.com/r/staphb/emboss) |
    • 6.6.0 (no version)
    | http://emboss.sourceforge.net | | [emmtyper](https://hub.docker.com/r/staphb/emmtyper)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/emmtyper)](https://hub.docker.com/r/staphb/emmtyper) |
    • 0.2.0
    | https://github.com/MDU-PHL/emmtyper | | [emm-typing-tool](https://hub.docker.com/r/staphb/emm-typing-tool)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/emm-typing-tool)](https://hub.docker.com/r/staphb/emm-typing-tool) |
    • 0.0.1 (no version)
    | https://github.com/phe-bioinformatics/emm-typing-tool | diff --git a/elgato/1.20.1/Dockerfile b/elgato/1.20.1/Dockerfile new file mode 100644 index 000000000..c675a4b43 --- /dev/null +++ b/elgato/1.20.1/Dockerfile @@ -0,0 +1,55 @@ +FROM staphb/ispcr:33 as app + +ARG ELGATO_VER="1.20.1" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="el_gato" +LABEL software.version="${ELGATO_VER}" +LABEL description="Epidemiology of Legionella : Genome-bAsed Typing" +LABEL website="https://github.com/appliedbinf/el_gato" +LABEL license="https://github.com/appliedbinf/el_gato/blob/main/LICENSE" +LABEL maintainer="Kutluhan Incekara" +LABEL maintainer.email="kutluhan.incekara@ct.gov" + +WORKDIR / + +# dependencies +RUN apt-get update && apt-get install --no-install-recommends -y \ + wget \ + python3-pip \ + minimap2 \ + samtools \ + ncbi-blast+ && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# install el_gato +RUN wget --no-check-certificate https://github.com/appliedbinf/el_gato/archive/refs/tags/${ELGATO_VER}.tar.gz &&\ + tar -xvf ${ELGATO_VER}.tar.gz && rm ${ELGATO_VER}.tar.gz &&\ + cd el_gato-${ELGATO_VER} &&\ + python3 -m pip install . -vv --no-cache-dir &&\ + mv ./el_gato/db/ /usr/local/bin/db/ + +# install fpd2 for pdf reports +RUN pip install --no-cache-dir fpdf2 packaging + +ENV LC_ALL=C + +CMD el_gato.py -h + +WORKDIR /data + +## Test ## +FROM app as test + +RUN apt-get update && apt-get install unzip + +# download Legionella pneumophila ST62 genome +RUN wget -P /usr/local/bin/ https://ftp.ncbi.nlm.nih.gov/pub/datasets/command-line/v2/linux-amd64/datasets &&\ + chmod 755 /usr/local/bin/datasets &&\ + datasets download genome accession GCF_900119765.1 --include genome &&\ + unzip -j ncbi_dataset.zip ncbi_dataset/data/GCF_900119765.1/GCF_900119765.1_2532STDY5467631_genomic.fna -d . + +# test el_gato +RUN el_gato.py --assembly GCF_900119765.1_2532STDY5467631_genomic.fna --out test/ &&\ + cat test/run.log diff --git a/elgato/1.20.1/README.md b/elgato/1.20.1/README.md new file mode 100644 index 000000000..8a83429f7 --- /dev/null +++ b/elgato/1.20.1/README.md @@ -0,0 +1,33 @@ +# el_gato container + +Main tool: [el_gato](https://github.com/appliedbinf/el_gato) + +Code repository: https://github.com/appliedbinf/el_gato + +Additional tools: +- minimap2: 2.24-r1122 +- samtools: 1.13 +- ncbi-blast+: 2.12.0+ +- isPCR: v33x2 + +Basic information on how to use this tool: +- executable: el_gato.py +- help: -h +- version: -v +- description: Epidemiology of Legionella : Genome-bAsed Typing + +Additional information: + +Container contains necessary database of Legionella sequence types + +Full documentation: https://github.com/appliedbinf/el_gato + +## Example Usage + +```bash +# Paired-end: +el_gato.py --read1 read1.fastq.gz --read2 read2.fastq.gz --out output_folder/ + +# Assembly: +el_gato.py --assembly assembly_file.fna --out output_folder/ +``` \ No newline at end of file From 717c4a6601483c6e538d5e73e30adb6af4844c4c Mon Sep 17 00:00:00 2001 From: Young Date: Thu, 31 Oct 2024 07:13:02 -0600 Subject: [PATCH 58/92] adding diamond version 2.1.10 (#1089) --- README.md | 2 +- diamond/2.1.10/Dockerfile | 38 ++++++++++++++++++++++++++++++++++++++ diamond/2.1.10/README.md | 32 ++++++++++++++++++++++++++++++++ 3 files changed, 71 insertions(+), 1 deletion(-) create mode 100644 diamond/2.1.10/Dockerfile create mode 100644 diamond/2.1.10/README.md diff --git a/README.md b/README.md index f1f724db8..0e838120e 100644 --- a/README.md +++ b/README.md @@ -149,7 +149,7 @@ To learn more about the docker pull rate limits and the open source software pro | [colorid](https://hub.docker.com/r/staphb/colorid)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/colorid)](https://hub.docker.com/r/staphb/colorid) |
    • 0.1.4.3
    | https://github.com/hcdenbakker/colorid | | [cutshaw-report-env](https://hub.docker.com/r/staphb/cutshaw-report-env)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/cutshaw-report-env)](https://hub.docker.com/r/staphb/cutshaw-report-env) |
    • 1.0.0
    | https://github.com/VADGS/CutShaw | | [datasets-sars-cov-2](https://github.com/CDCgov/datasets-sars-cov-2)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/datasets-sars-cov-2)](https://hub.docker.com/r/staphb/datasets-sars-cov-2) |
    • 0.6.2
    • 0.6.3
    • 0.7.2
    | https://github.com/CDCgov/datasets-sars-cov-2 | -| [diamond](https://github.com/bbuchfink/diamond)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/diamond)](https://hub.docker.com/r/staphb/diamond) |
    • [2.1.9](./diamond/2.1.9)
    | https://github.com/bbuchfink/diamond| +| [diamond](https://github.com/bbuchfink/diamond)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/diamond)](https://hub.docker.com/r/staphb/diamond) |
    • [2.1.9](./diamond/2.1.9)
    • [2.1.10](./diamond/2.1.10)
    | https://github.com/bbuchfink/diamond| | [dnaapler](https://hub.docker.com/r/staphb/dnaapler)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/dnaapler)](https://hub.docker.com/r/staphb/dnaapler) |
    • [0.1.0](dnaapler/0.1.0/)
    • [0.4.0](dnaapler/0.4.0/)
    • [0.5.0](./dnaapler/0.5.0/)
    • [0.5.1](./dnaapler/0.5.1/)
    • [0.7.0](./dnaapler/0.7.0/)
    • [0.8.0](./dnaapler/0.8.0/)
    • [0.8.1](./dnaapler/0.8.1/)
    | https://github.com/gbouras13/dnaapler | | [dorado](https://hub.docker.com/r/staphb/dorado)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/dorado)](https://hub.docker.com/r/staphb/dorado) |
    • [0.8.0](dorado/0.8.0/)
    | [https://github.com/nanoporetech/dorado](https://github.com/nanoporetech/dorado) | | [dragonflye](https://hub.docker.com/r/staphb/dragonflye)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/dragonflye)](https://hub.docker.com/r/staphb/dragonflye) |
    • [1.0.14](./dragonflye/1.0.14/)
    • [1.1.1](./dragonflye/1.1.1/)
    • [1.1.2](./dragonflye/1.1.2/)
    • [1.2.0](./dragonflye/1.2.0/)
    • [1.2.1](./dragonflye/1.2.1/)
    | https://github.com/rpetit3/dragonflye | diff --git a/diamond/2.1.10/Dockerfile b/diamond/2.1.10/Dockerfile new file mode 100644 index 000000000..465a674b2 --- /dev/null +++ b/diamond/2.1.10/Dockerfile @@ -0,0 +1,38 @@ +FROM ubuntu:jammy as app + +ARG DIAMOND_VER="2.1.10" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="DIAMOND" +LABEL software.version="${DIAMOND_VER}" +LABEL description="Accelerated BLAST compatible local sequence aligner." +LABEL website="https://github.com/bbuchfink/diamond" +LABEL license="https://github.com/bbuchfink/diamond/blob/master/LICENSE" +LABEL maintainer="Kutluhan Incekara" +LABEL maintainer.email="kutluhan.incekara@ct.gov" + +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ncbi-blast+ &&\ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +RUN wget --no-check-certificate https://github.com/bbuchfink/diamond/releases/download/v${DIAMOND_VER}/diamond-linux64.tar.gz &&\ + tar -C /usr/local/bin -xvf diamond-linux64.tar.gz && \ + rm diamond-linux64.tar.gz + +ENV LC_ALL=C + +CMD [ "diamond", "help" ] + +WORKDIR /data + +## Test ## +FROM app as test + +RUN diamond test + +RUN wget --no-check-certificate https://scop.berkeley.edu/downloads/scopeseq-2.07/astral-scopedom-seqres-gd-sel-gs-bib-40-2.07.fa &&\ + diamond makedb --in astral-scopedom-seqres-gd-sel-gs-bib-40-2.07.fa -d astral40 &&\ + diamond blastp -q astral-scopedom-seqres-gd-sel-gs-bib-40-2.07.fa -d astral40 -o out.tsv --very-sensitive &&\ + head out.tsv diff --git a/diamond/2.1.10/README.md b/diamond/2.1.10/README.md new file mode 100644 index 000000000..58db64ff3 --- /dev/null +++ b/diamond/2.1.10/README.md @@ -0,0 +1,32 @@ +# diamond container + +Main tool: [diamond](https://github.com/bbuchfink/diamond) + +Code repository: https://github.com/bbuchfink/diamond + +Additional tools: +- ncbi-blast+ : 2.12.0 + +Basic information on how to use this tool: +- executable: diamond +- help: help +- version: version +- description: DIAMOND is a sequence aligner for protein and translated DNA searches, designed for high performance analysis of big sequence data. The key features are: + + - Pairwise alignment of proteins and translated DNA at 100x-10,000x speed of BLAST. + - Protein clustering of up to tens of billions of proteins + - Frameshift alignments for long read analysis. + - Low resource requirements and suitable for running on standard desktops or laptops. + - Various output formats, including BLAST pairwise, tabular and XML, as well as taxonomic classification. + +Full documentation: https://github.com/bbuchfink/diamond/wiki + +## Example Usage + +```bash +# Protein alignment +diamond makedb --in proteins.fa -d db +diamond blastp -q query.fa -d db -o out.tsv --very-sensitive +# Protein clustering +diamond cluster -d proteins.fa -o clusters.tsv --approx-id 40 -M 12G --header +``` \ No newline at end of file From 684500b64a92129ea88f714d865e1ccf39e80f2f Mon Sep 17 00:00:00 2001 From: Young Date: Thu, 31 Oct 2024 07:22:20 -0600 Subject: [PATCH 59/92] adding genomad version 1.8.1 (#1090) --- README.md | 2 +- genomad/1.8.1/Dockerfile | 84 ++++++++++++++++++++++++++++++++++++++++ genomad/1.8.1/README.md | 40 +++++++++++++++++++ 3 files changed, 125 insertions(+), 1 deletion(-) create mode 100644 genomad/1.8.1/Dockerfile create mode 100644 genomad/1.8.1/README.md diff --git a/README.md b/README.md index 0e838120e..6e35472c4 100644 --- a/README.md +++ b/README.md @@ -174,7 +174,7 @@ To learn more about the docker pull rate limits and the open source software pro | [GAMBIT](https://hub.docker.com/r/staphb/gambit)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/gambit)](https://hub.docker.com/r/staphb/gambit) |
    • 0.3.0
    • 0.4.0
    • 0.5.0
    • 1.0.0
    | https://github.com/jlumpe/gambit | | [GAMMA](https://hub.docker.com/r/staphb/gamma)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/gamma)](https://hub.docker.com/r/staphb/gamma) |
    • 1.4
    • 2.1
    • 2.2
    | https://github.com/rastanton/GAMMA/ | | [GenoFLU](https://hub.docker.com/r/staphb/genoflu)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/genoflu)]() |
    • [1.03](genoflu/1.03/)
    | https://github.com/USDA-VS/GenoFLU | -| [geNomad](https://hub.docker.com/r/staphb/genomad)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/genomad)](https://hub.docker.com/r/staphb/genomad) |
    • [1.7.4](./genomad/1.7.4/)
    • [1.8.0](./genomad/1.8.0/)
    | https://github.com/apcamargo/genomad | +| [geNomad](https://hub.docker.com/r/staphb/genomad)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/genomad)](https://hub.docker.com/r/staphb/genomad) |
    • [1.7.4](./genomad/1.7.4/)
    • [1.8.0](./genomad/1.8.0/)
    • [1.8.1](./genomad/1.8.1/)
    | https://github.com/apcamargo/genomad | | [GenoVi](https://hub.docker.com/r/staphb/genovi)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/genovi)](https://hub.docker.com/r/staphb/genovi) |
    • [0.2.16](./genovi/0.2.16/)
    | https://github.com/robotoD/GenoVi | | [gfastats](https://hub.docker.com/r/staphb/gfastats)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/gfastats)](https://hub.docker.com/r/staphb/gfastats) |
    • [1.3.6](./gfastats/1.3.6/)
    • [1.3.7](./gfastats/1.3.7/)
    | https://github.com/vgl-hub/gfastats | | [Gubbins](https://hub.docker.com/r/staphb/gubbins)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/gubbins)](https://hub.docker.com/r/staphb/gubbins) |
    • [3.3.3](./gubbins/3.3.3/)
    • [3.3.4](./gubbins/3.3.4/)
    • [3.3.5](./gubbins/3.3.5/)
    | https://github.com/nickjcroucher/gubbins | diff --git a/genomad/1.8.1/Dockerfile b/genomad/1.8.1/Dockerfile new file mode 100644 index 000000000..b765aedbb --- /dev/null +++ b/genomad/1.8.1/Dockerfile @@ -0,0 +1,84 @@ + +ARG GENOMAD_VER="1.8.1" +ARG ARAGORN_VER="1.2.41" +ARG MMSEQS2_VER="15-6f452" + +FROM ubuntu:jammy as builder + +ARG ARAGORN_VER + +RUN apt-get update && apt-get install -y --no-install-recommends \ + ca-certificates \ + libc6-dev \ + make \ + gcc \ + wget + +# get ARAGORN +RUN wget -q https://www.trna.se/ARAGORN/Downloads/aragorn${ARAGORN_VER}.c && \ + gcc -O3 -ffast-math -finline-functions -o aragorn aragorn${ARAGORN_VER}.c && \ + /aragorn -h + +FROM ubuntu:jammy as app + +ARG GENOMAD_VER +ARG MMSEQS2_VER + +# 'LABEL' instructions tag the image with metadata that might be important to the user +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="geNomad" +LABEL software.version="${GENOMAD_VER}" +LABEL description="Identification of mobile genetic elements" +LABEL website="https://github.com/apcamargo/genomad" +LABEL license="https://github.com/apcamargo/genomad/blob/main/LICENSE" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" + +COPY --from=builder /aragorn /usr/local/bin/ + +RUN apt-get update && apt-get install -y --no-install-recommends \ + ca-certificates \ + procps \ + python3 \ + python3-pip \ + wget && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# get MMSEQS2 +RUN wget -q https://github.com/soedinglab/MMseqs2/releases/download/${MMSEQS2_VER}/mmseqs-linux-avx2.tar.gz && \ + tar -xvf mmseqs-linux-avx2.tar.gz && \ + rm mmseqs-linux-avx2.tar.gz + +# get genomad +RUN wget -q https://github.com/apcamargo/genomad/archive/refs/tags/v${GENOMAD_VER}.tar.gz && \ + python3 -m pip install --no-cache-dir v${GENOMAD_VER}.tar.gz && \ + rm -rf v${GENOMAD_VER}.tar.gz && \ + mkdir /data + +ENV PATH="/mmseqs/bin:$PATH" LC_ALL=C + +# downloads latest database, which is version 1.7 and about ~1.6 G in size +RUN genomad download-database . + +# 'CMD' instructions set a default command when the container is run. This is typically 'tool --help.' +CMD genomad --help + +# 'WORKDIR' sets working directory +WORKDIR /data + +FROM app as test + +# set working directory so that all test inputs & outputs are kept in /test +WORKDIR /test + +RUN genomad --help && \ + genomad --version && \ + aragorn -h && \ + mmseqs -h + +# downloads genome from NCBI and runs end-to-end (which looks like all steps) on the downloaded fasta +RUN pip list && \ + wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/025/259/185/GCA_025259185.1_ASM2525918v1/GCA_025259185.1_ASM2525918v1_genomic.fna.gz && \ + gunzip GCA_025259185.1_ASM2525918v1_genomic.fna.gz && \ + genomad end-to-end GCA_025259185.1_ASM2525918v1_genomic.fna test /genomad_db --splits 16 diff --git a/genomad/1.8.1/README.md b/genomad/1.8.1/README.md new file mode 100644 index 000000000..06ba24758 --- /dev/null +++ b/genomad/1.8.1/README.md @@ -0,0 +1,40 @@ +g# geNomad container + +Main tool: [geNomad](https://github.com/apcamargo/genomad/) + +Code repository: https://github.com/apcamargo/genomad/ + +Additional tools: +- aragorn: 1.2.41 +- mmseq2: 15-6f452 + +Basic information on how to use this tool: +- executable: genomad +- help: --help +- version: --version +- description: Identification of mobile genetic elements + +Additional information: + +The geNomad database version 1.7 is downloaded in /genomad_db. + +Full documentation: https://portal.nersc.gov/genomad/ + +## Example Usage + +```bash +# to download the database (database is already downloaded at /genomad_db) +genomad download-database . + +# recommended usage +genomad end-to-end input.fna output /genomad_db + +# subsections of genomad +genomad annotate metagenome.fna genomad_output /genomad_db +genomad find-proviruses metagenome.fna genomad_output /genomad_db +genomad marker-classification metagenome.fna genomad_output /genomad_db +genomad nn-classification metagenome.fna /genomad_output +genomad aggregated-classification metagenome.fna /genomad_output +genomad score-calibration metagenome.fna /genomad_output +genomad summary metagenome.fna /genomad_output +``` From 3d052f83f769b264933766d529912505ad9d2f4a Mon Sep 17 00:00:00 2001 From: Sage Wright Date: Fri, 1 Nov 2024 11:48:07 -0400 Subject: [PATCH 60/92] update tbprofiler v6.4.0 (#1094) * add genoflu * add readme * add to license * add --force-pkgs-dirs * krakentools add * update readmes * silence warnings about AS casing; fix typo * added comment in dockerfile & added additional dependencies and versions to readme for krakentools * pinning biopython and pandas versions and removing unnecessary jq and gawk * fixed version of python installed listed in krakentools readme * add tbprofiler 6.4.0 * update readme * add list_db * exec format, capitalize AS * update versions * pinning delly version due to conflict resolution with usher 0.6.3 which is required by tb-profiler * added delly to list of deps for tb-profiler. Plus link to GH issue describing troubles w delly --------- Co-authored-by: Curtis Kapsak --- README.md | 2 +- tbprofiler/6.4.0/Dockerfile | 66 +++++++++++++++++++++++++++++++++++++ tbprofiler/6.4.0/README.md | 60 +++++++++++++++++++++++++++++++++ 3 files changed, 127 insertions(+), 1 deletion(-) create mode 100644 tbprofiler/6.4.0/Dockerfile create mode 100644 tbprofiler/6.4.0/README.md diff --git a/README.md b/README.md index 6e35472c4..3c97d8fff 100644 --- a/README.md +++ b/README.md @@ -298,7 +298,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Staramr](https://hub.docker.com/r/staphb/staramr/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/staramr)](https://hub.docker.com/r/staphb/staramr) |
    • [0.5.1](./staramr/0.5.1/)
    • [0.7.1](./staramr/0.7.1/)
    • [0.8.0](./staramr/0.8.0/)
    • [0.10.0](./staramr/0.10.0/)
    | https://github.com/phac-nml/staramr | | [stxtyper](https://hub.docker.com/r/staphb/stxtyper)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/stxtyper)](https://hub.docker.com/r/staphb/stxtyper) |
    • [1.0.24](stxtyper/1.0.24)
    | https://github.com/ncbi/stxtyper | | [sylph](https://hub.docker.com/r/staphb/sylph)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/sylph)](https://hub.docker.com/r/staphb/sylph) |
    • [0.4.1](./sylph/0.4.1)
    • [0.5.1](./sylph/0.5.1)
    • [0.6.0](./sylph/0.6.0)
    • [0.6.1](./sylph/0.6.1)
    | https://github.com/bluenote-1577/sylph | -| [TBProfiler](https://hub.docker.com/r/staphb/tbprofiler/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/tbprofiler)](https://hub.docker.com/r/staphb/tbprofiler) |
    • [4.3.0](./tbprofiler/4.3.0/)
    • [4.4.0](./tbprofiler/4.4.0/)
    • [4.4.2](./tbprofiler/4.4.2/)
    • [5.0.1](tbprofiler/5.0.1/)
    • [6.2.0](tbprofiler/6.2.0/)
    • [6.2.1](tbprofiler/6.2.1/)
    • [6.3.0](tbprofiler/6.3.0/)
    | https://github.com/jodyphelan/TBProfiler | +| [TBProfiler](https://hub.docker.com/r/staphb/tbprofiler/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/tbprofiler)](https://hub.docker.com/r/staphb/tbprofiler) |
    • [4.3.0](./tbprofiler/4.3.0/)
    • [4.4.0](./tbprofiler/4.4.0/)
    • [4.4.2](./tbprofiler/4.4.2/)
    • [5.0.1](tbprofiler/5.0.1/)
    • [6.2.0](tbprofiler/6.2.0/)
    • [6.2.1](tbprofiler/6.2.1/)
    • [6.3.0](tbprofiler/6.3.0/)
    • [6.4.0](tbprofiler/6.4.0/)
    | https://github.com/jodyphelan/TBProfiler | | [TipToft](https://hub.docker.com/r/staphb/tiptoft/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/tiptoft)](https://hub.docker.com/r/staphb/tiptoft) |
    • 1.0.0
    • 1.0.2
    | https://github.com/andrewjpage/tiptoft | | [Tostadas](https://hub.docker.com/r/staphb/tostadas/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/tostadas)](https://hub.docker.com/r/staphb/tostadas) |
    • [0.2.0-beta](./tostadas/0.2.0-beta/)
    • [3.1.0](./tostadas/3.1.0/)
    | https://github.com/CDCgov/tostadas | | [Treemmer](https://hub.docker.com/r/staphb/treemmer/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/treemmer)](https://hub.docker.com/r/staphb/treemmer) |
    • 0.3
    | https://git.scicore.unibas.ch/TBRU/Treemmer (archived, moved to GitHub)
    https://github.com/fmenardo/Treemmer | diff --git a/tbprofiler/6.4.0/Dockerfile b/tbprofiler/6.4.0/Dockerfile new file mode 100644 index 000000000..4eb676d4d --- /dev/null +++ b/tbprofiler/6.4.0/Dockerfile @@ -0,0 +1,66 @@ +FROM mambaorg/micromamba:1.5.8 AS app + +USER root +WORKDIR / + +ARG TBPROFILER_VER="6.4.0" + +# this version is the shortened commit hash on the `master` branch here https://github.com/jodyphelan/tbdb/ +# commits are found on https://github.com/jodyphelan/tbdb/commits/master +# this was the latest commit as of 2024-10-31 +ARG TBDB_COMMIT="2c92475219416a449e89782f2b768149d26f7979" + +# LABEL instructions tag the image with metadata that might be important to the user +LABEL base.image="micromamba:1.5.8" +LABEL dockerfile.version="1" +LABEL software="tbprofiler" +LABEL software.version="${TBPROFILER_VER}" +LABEL description="The pipeline aligns reads to the H37Rv reference using bowtie2, BWA or minimap2 and then calls variants using bcftools. These variants are then compared to a drug-resistance database." +LABEL website="https://github.com/jodyphelan/TBProfiler/" +LABEL license="https://github.com/jodyphelan/TBProfiler/blob/master/LICENSE" +LABEL maintainer="John Arnn" +LABEL maintainer.email="jarnn@utah.gov" +LABEL maintainer2="Curtis Kapsak" +LABEL maintainer2.email="kapsakcj@gmail.com" +LABEL maintainer3="Sage Wright" +LABEL maintainer3.email="sagemwright@gmail.com" + +# Install dependencies via apt-get; cleanup apt garbage +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + procps && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# install tb-profiler via bioconda; install into 'base' conda env +RUN micromamba install --yes --name base --channel conda-forge --channel bioconda \ + tb-profiler=${TBPROFILER_VER} delly=1.2.6 && \ + micromamba clean --all --yes -f && micromamba list + +# hardcode 'base' env bin into PATH, so conda env does not have to be "activated" at run time +ENV PATH="/opt/conda/bin:${PATH}" + +# Version of database can be confirmed at /opt/conda/share/tbprofiler/tbdb.version.json +# can also run 'tb-profiler list_db' to find the same version info + +# https://github.com/jodyphelan/tbdb +RUN tb-profiler update_tbdb --commit ${TBDB_COMMIT} && \ + tb-profiler list_db + +WORKDIR /data + +# Added command to bring help menu up upon running container. +CMD ["tb-profiler"] + +# test stage +FROM app AS test + +# checking if tool is in PATH +RUN tb-profiler && tb-profiler version + +WORKDIR /tests + +# download some TB FASTQs and run through tb-profiler +RUN wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR166/009/ERR1664619/ERR1664619_1.fastq.gz && \ + wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR166/009/ERR1664619/ERR1664619_2.fastq.gz && \ + tb-profiler profile -1 ERR1664619_1.fastq.gz -2 ERR1664619_2.fastq.gz -t 2 -p ERR1664619 --txt diff --git a/tbprofiler/6.4.0/README.md b/tbprofiler/6.4.0/README.md new file mode 100644 index 000000000..2460db6fa --- /dev/null +++ b/tbprofiler/6.4.0/README.md @@ -0,0 +1,60 @@ +# TBProfiler Container + +Main tool: [TBProfiler](https://github.com/jodyphelan/TBProfiler) + +The pipeline aligns reads to the H37Rv reference using bowtie2, BWA or minimap2 and then calls variants using bcftools. These variants are then compared to a drug-resistance database. It also predicts the number of reads supporting drug resistance variants as an insight into hetero-resistance. + +## Database + +This tool relies on a database to run. The version (AKA git commit hash) of the database that is included in the docker image is `2c92475`. This is from the GitHub repository https://github.com/jodyphelan/tbdb. This can be confirmed in the json file: `/opt/conda/share/tbprofiler/tbdb.variables.json`: + +```bash +$ grep 'commit' /opt/conda/share/tbprofiler/tbdb.variables.json +{"db-schema-version": "1.0.0", "snpEff_db": "Mycobacterium_tuberculosis_h37rv", "drugs": ["rifampicin", "isoniazid", "ethambutol", "pyrazinamide", "moxifloxacin", "levofloxacin", "bedaquiline", "delamanid", "pretomanid", "linezolid", "streptomycin", "amikacin", "kanamycin", "capreomycin", "clofazimine", "ethionamide", "para-aminosalicylic_acid", "cycloserine"], "tb-profiler-version": ">=6.0.0,<7.0.0", "version": {"name": "tbdb", "commit": "2c92475", "Merge": "8918884 2a51937", "Author": "Jody Phelan ", "Date": "Mon Oct 7 17:06:42 2024 +0100", "db-schema-version": "1.0.0"}, "amplicon": false, "files": {"ref": "tbdb.fasta", "gff": "tbdb.gff", "bed": "tbdb.bed", "json_db": "tbdb.dr.json", "variables": "tbdb.variables.json", "spoligotype_spacers": "tbdb.spoligotype_spacers.txt", "spoligotype_annotations": "tbdb.spoligotype_list.csv", "bedmask": "tbdb.mask.bed", "barcode": "tbdb.barcode.bed", "rules": "tbdb.rules.txt"}} +``` + +Additionally you can run the command `tb-profiler list_db` to list the same information + +```bash +$ tb-profiler list_db +tbdb 2c92475 Jody Phelan Mon Oct 7 17:06:42 2024 +0100 /opt/conda/share/tbprofiler/tbdb +``` + +## Additional included tools/dependencies + +- bedtools 2.31.1 +- gatk4 4.6.1.0 +- kmc 3.2.4 +- pathogen-profiler 4.5.0 +- perl 5.32.1 +- python 3.12.3 +- trimmomatic 0.39 +- bwa 0.7.18 +- minimap2 2.28 +- samtools 1.21 +- bcftools 1.21 +- freebayes 1.3.6 +- tqdm 4.66.6 +- parallel 20240922 +- samclip 0.4.0 +- snpeff 5.2 +- delly 1.2.6 (the more recent version 1.3.1 did not allow for the conda environment to resolve. More info here: https://github.com/jodyphelan/TBProfiler/issues/393#issuecomment-2452076859) + +## Example Usage + +Run whole pipeline on Illumina paired-end reads: + +```bash +tb-profiler profile -1 ERR1664619_1.fastq.gz -2 ERR1664619_2.fastq.gz -t 4 -p ERR1664619 --txt +``` + +Make alternative database: + +```bash +tb-profiler create_db --prefix +tb-profiler load_library --prefix +``` + +## Updates + +Release 5.0.1 implemented sqlite3 database locking with https://py-filelock.readthedocs.io/en/latest/index.html. This should fix issues using it over network filing systems (NFS). For more information, official documentation can be found [here.](https://jodyphelan.gitbook.io/tb-profiler/) From 418b043d1179eefc53f596102264f9104a422ce4 Mon Sep 17 00:00:00 2001 From: Kincekara Date: Mon, 4 Nov 2024 19:44:01 +0000 Subject: [PATCH 61/92] adds busco 5.8.0 --- README.md | 2 +- busco/5.8.0/Dockerfile | 103 +++++++++++++++++++++++++++++++++++++++++ busco/5.8.0/README.md | 95 +++++++++++++++++++++++++++++++++++++ 3 files changed, 199 insertions(+), 1 deletion(-) create mode 100644 busco/5.8.0/Dockerfile create mode 100644 busco/5.8.0/README.md diff --git a/README.md b/README.md index 3c97d8fff..b72fade90 100644 --- a/README.md +++ b/README.md @@ -131,7 +131,7 @@ To learn more about the docker pull rate limits and the open source software pro | [blast+](https://hub.docker.com/r/staphb/blast/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/blast)](https://hub.docker.com/r/staphb/blast) |
    • [2.13.0](blast/2.13.0/)
    • [2.14.0](blast/2.14.0/)
    • [2.14.1](blast/2.14.1/)
    • [2.15.0](blast/2.15.0/)
    • [2.16.0](./blast/2.16.0/)
    | https://www.ncbi.nlm.nih.gov/books/NBK279690/ | | [bowtie2](https://hub.docker.com/r/staphb/bowtie2/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bowtie2)](https://hub.docker.com/r/staphb/bowtie2) |
    • [2.4.4](./bowtie2/2.4.4/)
    • [2.4.5](./bowtie2/2.4.5/)
    • [2.5.1](./bowtie2/2.5.1/)
    • [2.5.3](./bowtie2/2.5.3/)
    • [2.5.4](./bowtie2/2.5.4/)
    | http://bowtie-bio.sourceforge.net/bowtie2/manual.shtml
    https://github.com/BenLangmead/bowtie2 | | [Bracken](https://hub.docker.com/r/staphb/bracken/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bracken)](https://hub.docker.com/r/staphb/bracken) |
    • [2.9](./bracken/2.9)
    | https://ccb.jhu.edu/software/bracken/index.shtml?t=manual
    https://github.com/jenniferlu717/Bracken | -| [BUSCO](https://hub.docker.com/r/staphb/busco/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/busco)](https://hub.docker.com/r/staphb/busco) |
    • [5.4.7](./busco/5.4.7/)
    • [5.6.1](./busco/5.6.1/)
    • [5.6.1-prok-bacteria_odb10_2024-01-08](./busco/5.6.1-prok-bacteria_odb10_2024-01-08/)
    • [5.7.1](./busco/5.7.1/)
    • [5.7.1-prok-bacteria_odb10_2024-01-08](./busco/5.7.1-prok-bacteria_odb10_2024-01-08/)
    | https://busco.ezlab.org/busco_userguide.html
    https://gitlab.com/ezlab/busco | +| [BUSCO](https://hub.docker.com/r/staphb/busco/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/busco)](https://hub.docker.com/r/staphb/busco) |
    • [5.4.7](./busco/5.4.7/)
    • [5.6.1](./busco/5.6.1/)
    • [5.6.1-prok-bacteria_odb10_2024-01-08](./busco/5.6.1-prok-bacteria_odb10_2024-01-08/)
    • [5.7.1](./busco/5.7.1/)
    • [5.7.1-prok-bacteria_odb10_2024-01-08](./busco/5.7.1-prok-bacteria_odb10_2024-01-08/)
    • [5.8.0](./busco/5.8.0/)
    | https://busco.ezlab.org/busco_userguide.html
    https://gitlab.com/ezlab/busco | | [BWA](https://hub.docker.com/r/staphb/bwa)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bwa)](https://hub.docker.com/r/staphb/bwa) |
    • 0.7.17
    • [0.7.18](./bwa/0.7.18/)
    | https://github.com/lh3/bwa | | [Canu](https://hub.docker.com/r/staphb/canu)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/canu?)](https://hub.docker.com/r/staphb/canu)|
    • 2.0
    • 2.1.1
    • 2.2
    | https://canu.readthedocs.io/en/latest/
    https://github.com/marbl/canu | | [Canu-Racon](https://hub.docker.com/r/staphb/canu-racon/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/canu-racon)](https://hub.docker.com/r/staphb/canu-racon) |
    • 1.7.1 (Canu), 1.3.1 (Racon), 2.13 (minimap2)
    • 1.9 (Canu), 1.4.3 (Racon), 2.17 (minimap2)
    • 1.9i (Canu), 1.4.3 (Racon), 2.17 (minimap2), (+racon_preprocess.py)
    • 2.0 (Canu), 1.4.3 (Racon), 2.17 (minimap2)
    | https://canu.readthedocs.io/en/latest/
    https://github.com/lbcb-sci/racon
    https://github.com/isovic/racon (ARCHIVED)
    https://lh3.github.io/minimap2/ | diff --git a/busco/5.8.0/Dockerfile b/busco/5.8.0/Dockerfile new file mode 100644 index 000000000..d79328e21 --- /dev/null +++ b/busco/5.8.0/Dockerfile @@ -0,0 +1,103 @@ +ARG BUSCO_VER="5.8.0" + +FROM ubuntu:focal AS app + +ARG BUSCO_VER +ARG BBMAP_VER="39.10" +ARG BLAST_VER="2.16.0" +ARG MINIPROT_VER="0.13" +ARG SEPP_VER="4.5.5" +ARG METAEUK_VER="7-bba0d80" +ARG DEBIAN_FRONTEND=noninteractive + +LABEL base.image="ubuntu:focal" +LABEL dockerfile.version="1" +LABEL software="BUSCO" +LABEL software.version="${BUSCO_VER}" +LABEL description="Assessing genome assembly and annotation completeness with Benchmarking Universal Single-Copy Orthologs" +LABEL website="https://busco.ezlab.org/" +LABEL license="https://gitlab.com/ezlab/busco/-/raw/master/LICENSE" +LABEL maintainer="Kutluhan Incekara" +LABEL maintainer.email="kutluhan.incekara@ct.gov" + +# install dependencies +RUN apt-get update && apt-get install --no-install-recommends -y \ + wget \ + python3-pip \ + python3-pandas \ + python3-setuptools\ + python3-requests \ + hmmer \ + prodigal \ + augustus \ + r-cran-ggplot2 \ + gcc-x86-64-linux-gnu \ + openjdk-8-jre-headless \ + libjenkins-json-java \ + libgoogle-gson-java \ + libjson-java \ + lbzip2 \ + && rm -rf /var/lib/apt/lists/* && apt-get autoclean \ + && ln -s /usr/bin/python3 /usr/bin/python + +# install other necessary tools +# BioPython (python3-biopython installs 1.73. It causes python error in this version) +RUN pip install --no-cache-dir biopython +# blast +RUN wget https://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/${BLAST_VER}/ncbi-blast-${BLAST_VER}+-x64-linux.tar.gz &&\ + tar -xvf ncbi-blast-${BLAST_VER}+-x64-linux.tar.gz && rm ncbi-blast-${BLAST_VER}+-x64-linux.tar.gz +# sepp +RUN wget https://github.com/smirarab/sepp/archive/refs/tags/v4.5.5.tar.gz &&\ + tar -xvf v${SEPP_VER}.tar.gz && rm v${SEPP_VER}.tar.gz &&\ + cd sepp-${SEPP_VER} &&\ + python setup.py config -c && python setup.py install +# bbtools +RUN wget https://sourceforge.net/projects/bbmap/files/BBMap_${BBMAP_VER}.tar.gz &&\ + tar -xvf BBMap_${BBMAP_VER}.tar.gz && rm BBMap_${BBMAP_VER}.tar.gz &&\ + mv /bbmap/* /usr/local/bin/ +# metaeuk +RUN wget https://github.com/soedinglab/metaeuk/releases/download/${METAEUK_VER}/metaeuk-linux-sse41.tar.gz &&\ + tar -xvf metaeuk-linux-sse41.tar.gz && rm metaeuk-linux-sse41.tar.gz &&\ + mv /metaeuk/bin/* /usr/local/bin/ +# miniprot +RUN wget https://github.com/lh3/miniprot/releases/download/v${MINIPROT_VER}/miniprot-${MINIPROT_VER}_x64-linux.tar.bz2 &&\ + tar -C /usr/local/bin/ --strip-components=1 --no-same-owner -xvf miniprot-${MINIPROT_VER}_x64-linux.tar.bz2 miniprot-${MINIPROT_VER}_x64-linux/miniprot &&\ + rm miniprot-${MINIPROT_VER}_x64-linux.tar.bz2 + +# and finally busco +RUN wget https://gitlab.com/ezlab/busco/-/archive/${BUSCO_VER}/busco-${BUSCO_VER}.tar.gz &&\ + tar -xvf busco-${BUSCO_VER}.tar.gz && \ + rm busco-${BUSCO_VER}.tar.gz &&\ + cd busco-${BUSCO_VER} && \ + python3 setup.py install + +ENV AUGUSTUS_CONFIG_PATH="/usr/share/augustus/config/" \ + PATH="${PATH}:/ncbi-blast-${BLAST_VER}+/bin:/usr/share/augustus/scripts:/busco-${BUSCO_VER}/scripts" \ + LC_ALL=C + +WORKDIR /data + +CMD busco -h && generate_plot.py -h + +## Tests ## +FROM app AS test + +ARG BUSCO_VER + +RUN busco -h && generate_plot.py -h + +# run tests for bacteria and eukaryota +RUN busco -i /busco-${BUSCO_VER}/test_data/bacteria/genome.fna -c 8 -m geno -f --out test_bacteria +RUN busco -i /busco-${BUSCO_VER}/test_data/eukaryota/genome.fna -c 8 -m geno -f --out test_eukaryota +RUN busco -i /busco-${BUSCO_VER}/test_data/eukaryota/genome.fna -l eukaryota_odb10 -c 8 -m geno -f --out test_eukaryota_augustus --augustus + +# generate plot +RUN mkdir my_summaries &&\ + find . -name "short_summary.*.txt" -exec cp {} my_summaries \; &&\ + generate_plot.py -wd my_summaries + +# using actual data (Salmonella genome) +RUN wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/010/941/835/GCA_010941835.1_PDT000052640.3/GCA_010941835.1_PDT000052640.3_genomic.fna.gz && \ + gzip -d GCA_010941835.1_PDT000052640.3_genomic.fna.gz && \ + busco -m genome -i GCA_010941835.1_PDT000052640.3_genomic.fna -o busco_GCA_010941835.1 --cpu 4 --auto-lineage-prok && \ + head busco_GCA_010941835.1/short_summary*.txt diff --git a/busco/5.8.0/README.md b/busco/5.8.0/README.md new file mode 100644 index 000000000..4533d99a9 --- /dev/null +++ b/busco/5.8.0/README.md @@ -0,0 +1,95 @@ +# Assessing genome assembly and annotation completeness with Benchmarking Universal Single-Copy Orthologs (BUSCO) container + +Main tool : [BUSCO](https://gitlab.com/ezlab/busco/) + +Additional tools: +- BBTools 39.10 +- HMMER 3.3 +- Prodigal 2.6.3 +- BLAST+ 2.16.0 +- AUGUSTUS 3.3.3 +- MetaEuk (Release 7-bba0d80) +- SEPP 4.5.5 +- Python 3.8.10 +- BioPython 1.83 +- R 3.6.3 +- Perl 5.30.0 +- OpenJDK 1.8.0_392 +- Miniprot 0.13 + +Full documentation: https://busco.ezlab.org/busco_userguide.html + +This fully functional BUSCO docker image allows you to use all the program options. All additional tools were added to satisfy the requirements of those functions. This image does not contain any lineage dataset. BUSCO downloads the passed dataset name automatically while running. If a full path is given as lineage, this automated management will be disabled. The usage options are given below. Please refer to the BUSCO manual for further information. +## Example Usage +### Specific lineage +```bash +busco -i assembly.fasta -l bacteria_odb10 -o output -m genome +``` +or +```bash +busco -i assembly.fasta -l /path/to/folder/bacteria_odb10 -o output -m genome +``` +### Auto lineage selection: +```bash +busco -i assembly.fasta -o output -m genome --auto-lineage-prok +``` +### Additional options: +```bash + -i FASTA FILE, --in FASTA FILE + Input sequence file in FASTA format. Can be an assembled genome or transcriptome (DNA), or protein sequences from an annotated gene set. + -o OUTPUT, --out OUTPUT + Give your analysis run a recognisable short name. Output folders and files will be labelled with this name. WARNING: do not provide a path + -m MODE, --mode MODE Specify which BUSCO analysis mode to run. + There are three valid modes: + - geno or genome, for genome assemblies (DNA) + - tran or transcriptome, for transcriptome assemblies (DNA) + - prot or proteins, for annotated gene sets (protein) + -l LINEAGE, --lineage_dataset LINEAGE + Specify the name of the BUSCO lineage to be used. + --auto-lineage Run auto-lineage to find optimum lineage path + --auto-lineage-prok Run auto-lineage just on non-eukaryote trees to find optimum lineage path + --auto-lineage-euk Run auto-placement just on eukaryote tree to find optimum lineage path + -c N, --cpu N Specify the number (N=integer) of threads/cores to use. + -f, --force Force rewriting of existing files. Must be used when output files with the provided name already exist. + -r, --restart Continue a run that had already partially completed. + -q, --quiet Disable the info logs, displays only errors + --out_path OUTPUT_PATH + Optional location for results folder, excluding results folder name. Default is current working directory. + --download_path DOWNLOAD_PATH + Specify local filepath for storing BUSCO dataset downloads + --datasets_version DATASETS_VERSION + Specify the version of BUSCO datasets, e.g. odb10 + --download_base_url DOWNLOAD_BASE_URL + Set the url to the remote BUSCO dataset location + --update-data Download and replace with last versions all lineages datasets and files necessary to their automated selection + --offline To indicate that BUSCO cannot attempt to download files + --metaeuk_parameters METAEUK_PARAMETERS + Pass additional arguments to Metaeuk for the first run. All arguments should be contained within a single pair of quotation marks, separated by commas. E.g. "--param1=1,--param2=2" + --metaeuk_rerun_parameters METAEUK_RERUN_PARAMETERS + Pass additional arguments to Metaeuk for the second run. All arguments should be contained within a single pair of quotation marks, separated by commas. E.g. "--param1=1,--param2=2" + -e N, --evalue N E-value cutoff for BLAST searches. Allowed formats, 0.001 or 1e-03 (Default: 1e-03) + --limit REGION_LIMIT How many candidate regions (contig or transcript) to consider per BUSCO (default: 3) + --augustus Use augustus gene predictor for eukaryote runs + --augustus_parameters AUGUSTUS_PARAMETERS + Pass additional arguments to Augustus. All arguments should be contained within a single pair of quotation marks, separated by commas. E.g. "--param1=1,--param2=2" + --augustus_species AUGUSTUS_SPECIES + Specify a species for Augustus training. + --long Optimization Augustus self-training mode (Default: Off); adds considerably to the run time, but can improve results for some non-model organisms + --config CONFIG_FILE Provide a config file + -v, --version Show this version and exit + -h, --help Show this help message and exit + --list-datasets Print the list of available BUSCO datasets +``` +### Plot +Example usage of plotting script: +```bash +# collect short summaries +mkdir my_summaries +cp SPEC1/short_summary.generic.lineage1_odb10.SPEC1.txt my_summaries/. +cp SPEC2/short_summary.generic.lineage2_odb10.SPEC2.txt my_summaries/. +cp SPEC3/short_summary.specific.lineage2_odb10.SPEC3.txt my_summaries/. +cp SPEC4/short_summary.generic.lineage3_odb10.SPEC4.txt my_summaries/. +cp SPEC5/short_summary.generic.lineage4_odb10.SPEC5.txt my_summaries/. +# plot via script +python3 generate_plot.py –wd my_summaries +``` From a0a974d2f0ff188cb2f34360c0b6e1966d815846 Mon Sep 17 00:00:00 2001 From: Kincekara Date: Mon, 4 Nov 2024 19:49:48 +0000 Subject: [PATCH 62/92] fix sepp link --- busco/5.8.0/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/busco/5.8.0/Dockerfile b/busco/5.8.0/Dockerfile index d79328e21..4f72c946a 100644 --- a/busco/5.8.0/Dockerfile +++ b/busco/5.8.0/Dockerfile @@ -47,7 +47,7 @@ RUN pip install --no-cache-dir biopython RUN wget https://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/${BLAST_VER}/ncbi-blast-${BLAST_VER}+-x64-linux.tar.gz &&\ tar -xvf ncbi-blast-${BLAST_VER}+-x64-linux.tar.gz && rm ncbi-blast-${BLAST_VER}+-x64-linux.tar.gz # sepp -RUN wget https://github.com/smirarab/sepp/archive/refs/tags/v4.5.5.tar.gz &&\ +RUN wget https://github.com/smirarab/sepp/archive/refs/tags/v${SEPP_VER}.tar.gz &&\ tar -xvf v${SEPP_VER}.tar.gz && rm v${SEPP_VER}.tar.gz &&\ cd sepp-${SEPP_VER} &&\ python setup.py config -c && python setup.py install From d617d2509dbb2bb4f999c51e016a7a594e2e5802 Mon Sep 17 00:00:00 2001 From: Kincekara Date: Mon, 4 Nov 2024 20:18:57 +0000 Subject: [PATCH 63/92] add busco 5.8.0-prok-bacteria_odb10_2024-01_08 --- README.md | 2 +- .../Dockerfile | 77 +++++++++++++++++++ .../README.md | 24 ++++++ 3 files changed, 102 insertions(+), 1 deletion(-) create mode 100644 busco/5.8.0-prok-bacteria_odb10_2024-01-08/Dockerfile create mode 100644 busco/5.8.0-prok-bacteria_odb10_2024-01-08/README.md diff --git a/README.md b/README.md index b72fade90..60e939df0 100644 --- a/README.md +++ b/README.md @@ -131,7 +131,7 @@ To learn more about the docker pull rate limits and the open source software pro | [blast+](https://hub.docker.com/r/staphb/blast/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/blast)](https://hub.docker.com/r/staphb/blast) |
    • [2.13.0](blast/2.13.0/)
    • [2.14.0](blast/2.14.0/)
    • [2.14.1](blast/2.14.1/)
    • [2.15.0](blast/2.15.0/)
    • [2.16.0](./blast/2.16.0/)
    | https://www.ncbi.nlm.nih.gov/books/NBK279690/ | | [bowtie2](https://hub.docker.com/r/staphb/bowtie2/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bowtie2)](https://hub.docker.com/r/staphb/bowtie2) |
    • [2.4.4](./bowtie2/2.4.4/)
    • [2.4.5](./bowtie2/2.4.5/)
    • [2.5.1](./bowtie2/2.5.1/)
    • [2.5.3](./bowtie2/2.5.3/)
    • [2.5.4](./bowtie2/2.5.4/)
    | http://bowtie-bio.sourceforge.net/bowtie2/manual.shtml
    https://github.com/BenLangmead/bowtie2 | | [Bracken](https://hub.docker.com/r/staphb/bracken/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bracken)](https://hub.docker.com/r/staphb/bracken) |
    • [2.9](./bracken/2.9)
    | https://ccb.jhu.edu/software/bracken/index.shtml?t=manual
    https://github.com/jenniferlu717/Bracken | -| [BUSCO](https://hub.docker.com/r/staphb/busco/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/busco)](https://hub.docker.com/r/staphb/busco) |
    • [5.4.7](./busco/5.4.7/)
    • [5.6.1](./busco/5.6.1/)
    • [5.6.1-prok-bacteria_odb10_2024-01-08](./busco/5.6.1-prok-bacteria_odb10_2024-01-08/)
    • [5.7.1](./busco/5.7.1/)
    • [5.7.1-prok-bacteria_odb10_2024-01-08](./busco/5.7.1-prok-bacteria_odb10_2024-01-08/)
    • [5.8.0](./busco/5.8.0/)
    | https://busco.ezlab.org/busco_userguide.html
    https://gitlab.com/ezlab/busco | +| [BUSCO](https://hub.docker.com/r/staphb/busco/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/busco)](https://hub.docker.com/r/staphb/busco) |
    • [5.4.7](./busco/5.4.7/)
    • [5.6.1](./busco/5.6.1/)
    • [5.6.1-prok-bacteria_odb10_2024-01-08](./busco/5.6.1-prok-bacteria_odb10_2024-01-08/)
    • [5.7.1](./busco/5.7.1/)
    • [5.7.1-prok-bacteria_odb10_2024-01-08](./busco/5.7.1-prok-bacteria_odb10_2024-01-08/)
    • [5.8.0](./busco/5.8.0/)
    • [5.8.0-prok-bacteria_odb10_2024-01-08](./busco/5.8.0-prok-bacteria_odb10_2024-01-08/)
    | https://busco.ezlab.org/busco_userguide.html
    https://gitlab.com/ezlab/busco | | [BWA](https://hub.docker.com/r/staphb/bwa)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bwa)](https://hub.docker.com/r/staphb/bwa) |
    • 0.7.17
    • [0.7.18](./bwa/0.7.18/)
    | https://github.com/lh3/bwa | | [Canu](https://hub.docker.com/r/staphb/canu)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/canu?)](https://hub.docker.com/r/staphb/canu)|
    • 2.0
    • 2.1.1
    • 2.2
    | https://canu.readthedocs.io/en/latest/
    https://github.com/marbl/canu | | [Canu-Racon](https://hub.docker.com/r/staphb/canu-racon/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/canu-racon)](https://hub.docker.com/r/staphb/canu-racon) |
    • 1.7.1 (Canu), 1.3.1 (Racon), 2.13 (minimap2)
    • 1.9 (Canu), 1.4.3 (Racon), 2.17 (minimap2)
    • 1.9i (Canu), 1.4.3 (Racon), 2.17 (minimap2), (+racon_preprocess.py)
    • 2.0 (Canu), 1.4.3 (Racon), 2.17 (minimap2)
    | https://canu.readthedocs.io/en/latest/
    https://github.com/lbcb-sci/racon
    https://github.com/isovic/racon (ARCHIVED)
    https://lh3.github.io/minimap2/ | diff --git a/busco/5.8.0-prok-bacteria_odb10_2024-01-08/Dockerfile b/busco/5.8.0-prok-bacteria_odb10_2024-01-08/Dockerfile new file mode 100644 index 000000000..825335212 --- /dev/null +++ b/busco/5.8.0-prok-bacteria_odb10_2024-01-08/Dockerfile @@ -0,0 +1,77 @@ +ARG BUSCO_VER="5.8.0" + +FROM ubuntu:jammy AS app + +ARG BUSCO_VER +ARG BBMAP_VER="39.10" +ARG SEPP_VER="4.5.5" +ARG DEBIAN_FRONTEND=noninteractive + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="BUSCO" +LABEL software.version="${BUSCO_VER}" +LABEL description="Slim version of BUSCO for prokaryotes only" +LABEL website="https://busco.ezlab.org/" +LABEL license="https://gitlab.com/ezlab/busco/-/raw/master/LICENSE" +LABEL maintainer="Kutluhan Incekara" +LABEL maintainer.email="kutluhan.incekara@ct.gov" + +# install dependencies +RUN apt-get update && apt-get install --no-install-recommends -y \ + wget \ + python3-pip \ + python3-setuptools \ + python3-requests \ + python3-pandas \ + hmmer \ + prodigal \ + lbzip2 \ + openjdk-8-jre-headless \ + && rm -rf /var/lib/apt/lists/* && apt-get autoclean \ + && ln -s /usr/bin/python3 /usr/bin/python + +# BioPython (python3-biopython installs 1.73. It causes python error in this version) +RUN pip install --no-cache-dir biopython + +# bbtools +RUN wget -q https://sourceforge.net/projects/bbmap/files/BBMap_${BBMAP_VER}.tar.gz &&\ + tar -xvf BBMap_${BBMAP_VER}.tar.gz && rm BBMap_${BBMAP_VER}.tar.gz &&\ + mv /bbmap/* /usr/local/bin/ + +# sepp +RUN wget https://github.com/smirarab/sepp/archive/refs/tags/v${SEPP_VER}.tar.gz &&\ + tar -xvf v${SEPP_VER}.tar.gz && rm v${SEPP_VER}.tar.gz &&\ + cd sepp-${SEPP_VER} &&\ + python setup.py config -c && python setup.py install + +# busco +RUN wget -q https://gitlab.com/ezlab/busco/-/archive/${BUSCO_VER}/busco-${BUSCO_VER}.tar.gz &&\ + tar -xvf busco-${BUSCO_VER}.tar.gz && \ + rm busco-${BUSCO_VER}.tar.gz &&\ + cd busco-${BUSCO_VER} && \ + python3 setup.py install + +# download bacteria_odb10 +RUN busco --download bacteria_odb10 + +ENV LC_ALL=C + +WORKDIR /data + +CMD busco -h + +## Tests ## +FROM app AS test + +RUN busco -h + +# offline test +RUN wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/010/941/835/GCA_010941835.1_PDT000052640.3/GCA_010941835.1_PDT000052640.3_genomic.fna.gz && \ + gzip -d GCA_010941835.1_PDT000052640.3_genomic.fna.gz && \ + busco --offline -l /busco_downloads/lineages/bacteria_odb10 -m genome -i GCA_010941835.1_PDT000052640.3_genomic.fna -o offline --cpu 4 && \ + head offline/short_summary*.txt + +# auto-lineage-prok +RUN busco -m genome -i GCA_010941835.1_PDT000052640.3_genomic.fna -o auto --cpu 4 --auto-lineage-prok && \ + head auto/short_summary*.txt diff --git a/busco/5.8.0-prok-bacteria_odb10_2024-01-08/README.md b/busco/5.8.0-prok-bacteria_odb10_2024-01-08/README.md new file mode 100644 index 000000000..cbe922d1e --- /dev/null +++ b/busco/5.8.0-prok-bacteria_odb10_2024-01-08/README.md @@ -0,0 +1,24 @@ +# Assessing genome assembly and annotation completeness with Benchmarking Universal Single-Copy Orthologs (BUSCO) container + +Main tool : [BUSCO](https://gitlab.com/ezlab/busco/) + +Additional tools: +- BBTools 39.10 +- HMMER 3.3.2 +- Prodigal 2.6.3 +- SEPP 4.5.5 +- Python 3.10.12 +- BioPython 1.83 +- Perl 5.34.0 +- OpenJDK 1.8.0_422 + +Full documentation: https://busco.ezlab.org/busco_userguide.html + +This is a BUSCO docker image which has basic functions for prokaryotes only. This image contains bacteria_odb10 lineage dataset for offline use. +## Example Usage +```bash +# offline usage with bacteria lineage +busco --offline -i assembly.fasta -l /busco_downloads/lineages/bacteria_odb10 -o output -m genome +# auto lineage selection +busco -i assembly.fasta -o output -m genome --auto-lineage-prok +``` From beb5349b5c0d857b9f868274f502c14e9a1ffdcd Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Thu, 7 Nov 2024 16:42:39 +0000 Subject: [PATCH 64/92] added dockerfile for amrfinderplus 4.0.3 and db 2024-10-22.1. also added readme --- .../4.0.3-2024-10-22.1/Dockerfile | 100 ++++++++++++++++++ .../4.0.3-2024-10-22.1/README.md | 69 ++++++++++++ 2 files changed, 169 insertions(+) create mode 100755 ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile create mode 100755 ncbi-amrfinderplus/4.0.3-2024-10-22.1/README.md diff --git a/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile b/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile new file mode 100755 index 000000000..49e9facfb --- /dev/null +++ b/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile @@ -0,0 +1,100 @@ +FROM ubuntu:jammy AS app + +ARG AMRFINDER_VER="4.0.3" +ARG AMRFINDER_DB_VER="2024-10-22.1" +ARG BLAST_VER="2.16.0" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="NCBI AMRFinderPlus" +LABEL software.version="${AMRFINDER_VER}" +LABEL description="NCBI resistance gene detection tool" +LABEL website="https://github.com/ncbi/amr" +LABEL license="https://github.com/ncbi/amr/blob/master/LICENSE" +LABEL maintainer="Kelsey Florek" +LABEL maintainer.email="kelsey.florek@slh.wisc.edu" +LABEL maintainer2="Curtis Kapsak" +LABEL maintainer2.email="kapsakcj@gmail.com" +LABEL maintainer3="Anders Goncalves da Silva" +LABEL maintainer3.email="andersgs@gmail.com" +LABEL maintainer4="Erin Young" +LABEL maintainer4.email="eriny@utah.gov" +LABEL maintainer5="Holly McQueary" +LABEL maintainer5.email="holly.c.mcqueary@mass.gov" + +# ncbi-blast+ installed via apt is v2.12.0 - DISABLING so that we can manually install a more recent version +# see here for reason why I'm manualy installing 2.14.0 instead of using apt-get: https://github.com/ncbi/amr/releases/tag/amrfinder_v3.11.8 + +# hmmer installed via apt is v3.3.2 +# removed because likely unnecessary since we are not compiling from source: make g++ +# libgomp1 required for makeblastdb +RUN apt-get update && apt-get install -y --no-install-recommends \ + ca-certificates \ + wget \ + curl \ + libgomp1 \ + hmmer \ + procps \ + gzip && \ + apt-get autoclean && \ + rm -rf /var/lib/apt/lists/* + +# download and install amrfinderplus pre-compiled binaries; make /data +RUN mkdir amrfinder && cd /amrfinder && \ + echo "downloading amrfinderplus v${AMRFINDER_VER} pre-compiled binaries from GitHub..." && \ + wget -q https://github.com/ncbi/amr/releases/download/amrfinder_v${AMRFINDER_VER}/amrfinder_binaries_v${AMRFINDER_VER}.tar.gz && \ + tar zxf amrfinder_binaries_v${AMRFINDER_VER}.tar.gz && \ + rm -v amrfinder_binaries_v${AMRFINDER_VER}.tar.gz && \ + mkdir -v /data + +# install ncbi-blast linux binaries +RUN echo "downloading ncbi-blast-${BLAST_VER}+ linux binaries from NCBI FTP..." && \ + wget -q https://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/${BLAST_VER}/ncbi-blast-${BLAST_VER}+-x64-linux.tar.gz && \ + tar -xzf ncbi-blast-${BLAST_VER}+-x64-linux.tar.gz && \ + rm -v ncbi-blast-${BLAST_VER}+-x64-linux.tar.gz + +# set PATH and locale settings for singularity compatibiliity, set amrfinder and manually-installed blast as higher priority in PATH +ENV PATH="/amrfinder:/ncbi-blast-${BLAST_VER}+/bin:$PATH" \ + LC_ALL=C + +# download databases and index them +# done in this manner to pin the database version instead of pulling the latest version with `amrfinder -u` +# softlink is required for `amrfinder -l` and typical `amrfinder` use cases to work properly +RUN mkdir -p /amrfinder/data/${AMRFINDER_DB_VER} && \ + echo "Downloading amrfinder databases and indexing them now..." && \ + wget -q -P /amrfinder/data/${AMRFINDER_DB_VER} ftp://ftp.ncbi.nlm.nih.gov/pathogen/Antimicrobial_resistance/AMRFinderPlus/database/4.0/${AMRFINDER_DB_VER}/* && \ + amrfinder_index /amrfinder/data/${AMRFINDER_DB_VER} && \ + ln -s /amrfinder/data/${AMRFINDER_DB_VER} /amrfinder/data/latest + +# set final working directory +WORKDIR /data + +# default command is to print help options +CMD [ "amrfinder", "--help" ] + +## Test stage +FROM app AS test + +# list database version and available --organism options +RUN amrfinder -l + +# run recommended tests from amrfinder; check that stx2a_operon is detected in outputs, meaning stxtyper ran correctly +RUN cd /amrfinder && \ + bash test_amrfinder.sh . && \ + echo && echo "Checking for stx2a_operon string in test outputs..." && \ + grep 'stx2a_operon' test_both.got + +# run amrfinder on Salmonella, without and with --organism option +RUN echo "Downloading Salmeonlla genome (GCA_010941835.1_PDT000052640.3) for testing now..." && \ + wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/010/941/835/GCA_010941835.1_PDT000052640.3/GCA_010941835.1_PDT000052640.3_genomic.fna.gz && \ + amrfinder --threads 4 --plus --nucleotide GCA_010941835.1_PDT000052640.3_genomic.fna.gz --output test1.txt && \ + amrfinder --threads 4 --plus --nucleotide GCA_010941835.1_PDT000052640.3_genomic.fna.gz --organism Salmonella --output test2.txt && \ + cat test1.txt test2.txt + +# run amrfinder on Klebesiella oxytoca using --organism/-O flag +RUN echo "Downloading Klembsiella oxytoca genome (GCA_003812925.1_ASM381292v1) for testing now..." && \ + wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/812/925/GCA_003812925.1_ASM381292v1/GCA_003812925.1_ASM381292v1_genomic.fna.gz && \ + amrfinder --threads 4 --plus --name GCA_003812925.1 -n GCA_003812925.1_ASM381292v1_genomic.fna.gz -O Klebsiella_oxytoca -o GCA_003812925.1-amrfinder.tsv + +# test that gunzip is installed +RUN gunzip --help diff --git a/ncbi-amrfinderplus/4.0.3-2024-10-22.1/README.md b/ncbi-amrfinderplus/4.0.3-2024-10-22.1/README.md new file mode 100755 index 000000000..dec2e5422 --- /dev/null +++ b/ncbi-amrfinderplus/4.0.3-2024-10-22.1/README.md @@ -0,0 +1,69 @@ +# NCBI AMRFinderPlus docker image + +Main tool : [NCBI AMRFinderPlus](https://github.com/ncbi/amr) + +Additional tools: + +- hmmer v3.3.2 +- ncbi-blast+ v2.16.0 +- [stxtyper](https://github.com/ncbi/stxtyper/) v1.0.27 (Shiga toxin subtyping tool, added in AMRFinderPlus v4.0.3) + +## Database information + +The database included at time of docker image build is **`2024-10-22.1`**. More information can be found in the [changelog.txt on NCBI's FTP](https://ftp.ncbi.nlm.nih.gov/pathogen/Antimicrobial_resistance/AMRFinderPlus/database/4.0/2024-10-22.1/changes.txt). + +Full documentation: [https://github.com/ncbi/amr/wiki](https://github.com/ncbi/amr/wiki) + +## Docker Image Tags + +Beginning with AMRFinderPlus v3.11.2, we will include the version of AMRFinderPlus followed by the database version in the docker image tag so that it is more informative to users. The format is as follows: + +```bash +# general format +staphb/ncbi-amrfinderplus:- + +# example +staphb/ncbi-amrfinderplus:3.11.14-2023-04-17.1 +``` + +You can view all available docker images on [dockerhub](https://hub.docker.com/r/staphb/ncbi-amrfinderplus/tags) and [quay.io](https://quay.io/repository/staphb/ncbi-amrfinderplus?tab=tags) + +## Example Usage + +```bash +# list out the available organisms for the -O/--organism flag +$ amrfinder -l +Running: amrfinder -l +Software directory: '/amrfinder/' +Software version: 3.12.8 +Database directory: '/amrfinder/data/2024-01-31.1' +Database version: 2024-01-31.1 + +Available --organism options: Acinetobacter_baumannii, Burkholderia_cepacia, Burkholderia_pseudomallei, Campylobacter, +Citrobacter_freundii, Clostridioides_difficile, Enterobacter_asburiae, Enterobacter_cloacae, Enterococcus_faecalis, +Enterococcus_faecium, Escherichia, Klebsiella_oxytoca, Klebsiella_pneumoniae, Neisseria_gonorrhoeae, +Neisseria_meningitidis, Pseudomonas_aeruginosa, Salmonella, Serratia_marcescens, Staphylococcus_aureus, +Staphylococcus_pseudintermedius, Streptococcus_agalactiae, Streptococcus_pneumoniae, Streptococcus_pyogenes, +Vibrio_cholerae, Vibrio_parahaemolyticus, Vibrio_vulnificus + +# download Klebsiella oxytoca genome FASTA/FNA to use as a test +$ wget "https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/812/925/GCA_003812925.1_ASM381292v1/GCA_003812925.1_ASM381292v1_genomic.fna.gz" + +# uncompress the FNA file +$ gzip -d GCA_003812925.1_ASM381292v1_genomic.fna.gz + +# run amrfinder (nucleotide mode) on the uncompressed FNA file +$ amrfinder --plus --name GCA_003812925.1 -n GCA_003812925.1_ASM381292v1_genomic.fna -O Klebsiella_oxytoca -o GCA_003812925.1-amrfinder.tsv + +# view output TSV +$ column -t -s $'\t' -n GCA_003812925.1-amrfinder.tsv +Name Protein identifier Contig id Start Stop Strand Gene symbol Sequence name Scope Element type Element subtype Class Subclass Method Target length Reference sequence length % Coverage of reference sequence % Identity to reference sequence Alignment length Accession of closest sequence Name of closest sequence HMM id HMM description +GCA_003812925.1 NA CP033844.1 369234 370406 + oqxA multidrug efflux RND transporter periplasmic adaptor subunit OqxA core AMR AMR PHENICOL/QUINOLONE PHENICOL/QUINOLONE BLASTX 391 391 100.00 90.79 391 WP_002914189.1 multidrug efflux RND transporter periplasmic adaptor subunit OqxA NA NA +GCA_003812925.1 NA CP033844.1 370433 373582 + oqxB multidrug efflux RND transporter permease subunit OqxB core AMR AMR PHENICOL/QUINOLONE PHENICOL/QUINOLONE BLASTX 1050 1050 100.00 96.86 1050 WP_023323140.1 multidrug efflux RND transporter permease subunit OqxB15 NA NA +GCA_003812925.1 NA CP033844.1 636118 637917 - ybtQ yersiniabactin ABC transporter ATP-binding/permease protein YbtQ plus VIRULENCE VIRULENCE NA NA BLASTX 600 600 100.00 89.17 600 AAC69584.1 yersiniabactin ABC transporter ATP-binding/permease protein YbtQ NA NA +GCA_003812925.1 NA CP033844.1 637913 639706 - ybtP yersiniabactin ABC transporter ATP-binding/permease protein YbtP plus VIRULENCE VIRULENCE NA NA BLASTX 598 600 99.67 89.30 598 CAA21388.1 yersiniabactin ABC transporter ATP-binding/permease protein YbtP NA NA +GCA_003812925.1 NA CP033844.1 3473617 3474798 + emrD multidrug efflux MFS transporter EmrD plus AMR AMR EFFLUX EFFLUX BLASTX 394 394 100.00 94.16 394 ACN65732.1 multidrug efflux MFS transporter EmrD NA NA +GCA_003812925.1 NA CP033844.1 5085488 5086357 - blaOXY-2-1 extended-spectrum class A beta-lactamase OXY-2-1 core AMR AMR BETA-LACTAM CEPHALOSPORIN ALLELEX 290 290 100.00 100.00 290 WP_032727905.1 extended-spectrum class A beta-lactamase OXY-2-1 NA NA +GCA_003812925.1 NA CP033845.1 5102 5632 - ant(2'')-Ia aminoglycoside nucleotidyltransferase ANT(2'')-Ia core AMR AMR AMINOGLYCOSIDE GENTAMICIN/KANAMYCIN/TOBRAMYCIN BLASTX 177 177 100.00 98.31 177 WP_000381803.1 aminoglycoside nucleotidyltransferase ANT(2'')-Ia NA NA +GCA_003812925.1 NA CP033846.1 748 1932 - tet(39) tetracycline efflux MFS transporter Tet(39) core AMR AMR TETRACYCLINE TETRACYCLINE EXACTX 395 395 100.00 100.00 395 WP_004856455.1 tetracycline efflux MFS transporter Tet(39) +``` From a2de1b1a60d64c7c5e784b25a058584df7537445 Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Thu, 7 Nov 2024 16:44:17 +0000 Subject: [PATCH 65/92] update main readme --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 60e939df0..1d9235beb 100644 --- a/README.md +++ b/README.md @@ -222,7 +222,7 @@ To learn more about the docker pull rate limits and the open source software pro | [NanoPlot](https://hub.docker.com/r/staphb/nanoplot)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/nanoplot)](https://hub.docker.com/r/staphb/nanoplot) |
    • [1.27.0](./nanoplot/1.27.0/)
    • [1.29.0](./nanoplot/1.29.0/)
    • [1.30.1](./nanoplot/1.30.1/)
    • [1.32.0](./nanoplot/1.32.0/)
    • [1.33.0](./nanoplot/1.33.0/)
    • [1.40.0](./nanoplot/1.40.0/)
    • [1.41.6](./nanoplot/1.41.6/)
    • [1.42.0](./nanoplot/1.42.0/)
    | https://github.com/wdecoster/NanoPlot | | [ngmaster](https://hub.docker.com/r/staphb/ngmaster)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/ngmaster)](https://hub.docker.com/r/staphb/ngmaster) |
    • 0.5.8
    • 1.0.0
    | https://github.com/MDU-PHL/ngmaster | | [NCBI Datasets](https://hub.docker.com/r/staphb/ncbi-datasets)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/ncbi-datasets)](https://hub.docker.com/r/staphb/ncbi-datasets) |
    Click to see all datasets versions **datasets versions**
    • [13.31.0](./ncbi-datasets/13.31.0/)
    • [13.35.0](./ncbi-datasets/13.35.0/)
    • [13.43.2](./ncbi-datasets/13.43.2/)
    • [14.0.0](./ncbi-datasets/14.0.0/)
    • [14.3.0](./ncbi-datasets/14.3.0/)
    • [14.7.0](./ncbi-datasets/14.7.0/)
    • [14.13.2](./ncbi-datasets/14.13.2/)
    • [14.20.0](./ncbi-datasets/14.20.0/)
    • [14.27.0](ncbi-datasets/14.27.0/)
    • [15.1.0](ncbi-datasets/15.1.0/)
    • [15.2.0](ncbi-datasets/15.2.0/)
    • [15.11.0](ncbi-datasets/15.11.0/)
    • [15.27.1](ncbi-datasets/15.27.1/)
    • [15.31.0](ncbi-datasets/15.31.1/)
    • [16.2.0](ncbi-datasets/16.2.0/)
    • [16.8.1](./ncbi-datasets/16.8.1/)
    • [16.10.3](./ncbi-datasets/16.10.3/)
    • [16.15.0](./ncbi-datasets/16.15.0/)
    • [16.22.1](./ncbi-datasets/16.22.1/)
    • [16.30.0](./ncbi-datasets/16.30.0/)
    | [https://github.com/ncbi/datasets](https://github.com/ncbi/datasets)
    [https://www.ncbi.nlm.nih.gov/datasets/docs/v1/](https://www.ncbi.nlm.nih.gov/datasets/docs/v1/) | -| [NCBI AMRFinderPlus](https://hub.docker.com/r/staphb/ncbi-amrfinderplus)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/ncbi-amrfinderplus)](https://hub.docker.com/r/staphb/ncbi-amrfinderplus) | **AMRFinderPlus & database verion**
    Click to see AMRFinderplus v3.11.4 and older versions!
    • 3.1.1b
    • 3.8.4
    • 3.8.28
    • 3.9.3
    • 3.9.8
    • 3.10.1
    • 3.10.5
    • 3.10.16
    • 3.10.20
    • 3.10.24
    • 3.10.30
    • 3.10.36
    • 3.10.42
    • 3.11.2 & 2022-12-19.1
    • [3.11.2 & 2023-02-23.1](ncbi-amrfinderplus/3.11.2-2023-02-23.1/)
    • [3.11.4 & 2023-02-23.1](ncbi-amrfinderplus/3.11.4-2023-02-23.1/)
    • [3.11.8 & 2023-02-23.1](ncbi-amrfinderplus/3.11.8-2023-02-23.1/)
    • [3.11.11 & 2023-04-17.1](ncbi-amrfinderplus/3.11.11-2023-04-17.1)
    • [3.11.14 & 2023-04-17.1](ncbi-amrfinderplus/3.11.14-2023-04-17.1/)
    • [3.11.17 & 2023-07-13.2](ncbi-amrfinderplus/3.11.17-2023-07-13.2/)
    • [3.11.18 & 2023-08-08.2](ncbi-amrfinderplus/3.11.18-2023-08-08.2/)
    • [3.11.20 & 2023-09-26.1](ncbi-amrfinderplus/3.11.20-2023-09-26.1/)
    • [3.11.26 & 2023-11-15.1](ncbi-amrfinderplus/3.11.26-2023-11-15.1/)
    • [3.12.8 & 2024-01-31.1](ncbi-amrfinderplus/3.12.8-2024-01-31.1/)
    • [3.12.8 & 2024-05-02.2](./ncbi-amrfinderplus/3.12.8-2024-05-02.2/)
    • [3.12.8 & 2024-07-22.1](./ncbi-amrfinderplus/3.12.8-2024-07-22.1/)
    | [https://github.com/ncbi/amr](https://github.com/ncbi/amr) | +| [NCBI AMRFinderPlus](https://hub.docker.com/r/staphb/ncbi-amrfinderplus)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/ncbi-amrfinderplus)](https://hub.docker.com/r/staphb/ncbi-amrfinderplus) | **AMRFinderPlus & database verion**
    Click to see AMRFinderplus v3.11.4 and older versions!
    • 3.1.1b
    • 3.8.4
    • 3.8.28
    • 3.9.3
    • 3.9.8
    • 3.10.1
    • 3.10.5
    • 3.10.16
    • 3.10.20
    • 3.10.24
    • 3.10.30
    • 3.10.36
    • 3.10.42
    • 3.11.2 & 2022-12-19.1
    • [3.11.2 & 2023-02-23.1](ncbi-amrfinderplus/3.11.2-2023-02-23.1/)
    • [3.11.4 & 2023-02-23.1](ncbi-amrfinderplus/3.11.4-2023-02-23.1/)
    • [3.11.8 & 2023-02-23.1](ncbi-amrfinderplus/3.11.8-2023-02-23.1/)
    • [3.11.11 & 2023-04-17.1](ncbi-amrfinderplus/3.11.11-2023-04-17.1)
    • [3.11.14 & 2023-04-17.1](ncbi-amrfinderplus/3.11.14-2023-04-17.1/)
    • [3.11.17 & 2023-07-13.2](ncbi-amrfinderplus/3.11.17-2023-07-13.2/)
    • [3.11.18 & 2023-08-08.2](ncbi-amrfinderplus/3.11.18-2023-08-08.2/)
    • [3.11.20 & 2023-09-26.1](ncbi-amrfinderplus/3.11.20-2023-09-26.1/)
    • [3.11.26 & 2023-11-15.1](ncbi-amrfinderplus/3.11.26-2023-11-15.1/)
    • [3.12.8 & 2024-01-31.1](ncbi-amrfinderplus/3.12.8-2024-01-31.1/)
    • [3.12.8 & 2024-05-02.2](./ncbi-amrfinderplus/3.12.8-2024-05-02.2/)
    • [3.12.8 & 2024-07-22.1](./ncbi-amrfinderplus/3.12.8-2024-07-22.1/)
    • [4.0.3 & 2024-10-22.1 (includes stxtyper)](./ncbi-amrfinderplus/4.0.3-2024-10-22.1/)
    | [https://github.com/ncbi/amr](https://github.com/ncbi/amr) | | [NCBI table2asn](https://hub.docker.com/r/staphb/ncbi-table2asn)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/ncbi-table2asn)](https://hub.docker.com/r/staphb/ncbi-table2asn) |
    • [1.26.678](./ncbi-table2asn/1.26.678/)
    • [1.28.943](./ncbi-table2asn/1.28.943/)
    • [1.28.1021](./ncbi-table2asn/1021/)
    | [https://www.ncbi.nlm.nih.gov/genbank/table2asn/](https://www.ncbi.nlm.nih.gov/genbank/table2asn/)
    [https://ftp.ncbi.nlm.nih.gov/asn1-converters/versions/2022-06-14/by_program/table2asn/](https://ftp.ncbi.nlm.nih.gov/asn1-converters/versions/2022-06-14/by_program/table2asn/) | | [ONTime](https://hub.docker.com/r/staphb/ontime)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/ontime)](https://hub.docker.com/r/staphb/ontime) |
    • [0.2.3](ontime/0.2.3/)
    • [0.3.1](ontime/0.3.1/)
    | https://github.com/mbhall88/ontime | | [OrthoFinder](https://hub.docker.com/r/staphb/orthofinder)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/orthofinder)](https://hub.docker.com/r/staphb/orthofinder) |
    • 2.17
    | https://github.com/davidemms/OrthoFinder | From 2c4468fe6329026bc95c7d5ab428c71fb759ab0e Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Thu, 7 Nov 2024 16:49:07 +0000 Subject: [PATCH 66/92] fix typos --- ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile b/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile index 49e9facfb..4e63aa914 100755 --- a/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile +++ b/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile @@ -85,14 +85,14 @@ RUN cd /amrfinder && \ grep 'stx2a_operon' test_both.got # run amrfinder on Salmonella, without and with --organism option -RUN echo "Downloading Salmeonlla genome (GCA_010941835.1_PDT000052640.3) for testing now..." && \ +RUN echo "Downloading Salmonella genome (GCA_010941835.1_PDT000052640.3) for testing now..." && \ wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/010/941/835/GCA_010941835.1_PDT000052640.3/GCA_010941835.1_PDT000052640.3_genomic.fna.gz && \ amrfinder --threads 4 --plus --nucleotide GCA_010941835.1_PDT000052640.3_genomic.fna.gz --output test1.txt && \ amrfinder --threads 4 --plus --nucleotide GCA_010941835.1_PDT000052640.3_genomic.fna.gz --organism Salmonella --output test2.txt && \ cat test1.txt test2.txt # run amrfinder on Klebesiella oxytoca using --organism/-O flag -RUN echo "Downloading Klembsiella oxytoca genome (GCA_003812925.1_ASM381292v1) for testing now..." && \ +RUN echo "Downloading Klebsiella oxytoca genome (GCA_003812925.1_ASM381292v1) for testing now..." && \ wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/812/925/GCA_003812925.1_ASM381292v1/GCA_003812925.1_ASM381292v1_genomic.fna.gz && \ amrfinder --threads 4 --plus --name GCA_003812925.1 -n GCA_003812925.1_ASM381292v1_genomic.fna.gz -O Klebsiella_oxytoca -o GCA_003812925.1-amrfinder.tsv From ee662289b38ed29349cc06dfbe32e1e21ae5d7fa Mon Sep 17 00:00:00 2001 From: Young Date: Thu, 7 Nov 2024 12:26:45 -0700 Subject: [PATCH 67/92] Changed cat to head for better result deliniation --- ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile b/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile index 4e63aa914..5604c3ea4 100755 --- a/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile +++ b/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile @@ -89,12 +89,13 @@ RUN echo "Downloading Salmonella genome (GCA_010941835.1_PDT000052640.3) for tes wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/010/941/835/GCA_010941835.1_PDT000052640.3/GCA_010941835.1_PDT000052640.3_genomic.fna.gz && \ amrfinder --threads 4 --plus --nucleotide GCA_010941835.1_PDT000052640.3_genomic.fna.gz --output test1.txt && \ amrfinder --threads 4 --plus --nucleotide GCA_010941835.1_PDT000052640.3_genomic.fna.gz --organism Salmonella --output test2.txt && \ - cat test1.txt test2.txt + head test1.txt test2.txt # run amrfinder on Klebesiella oxytoca using --organism/-O flag RUN echo "Downloading Klebsiella oxytoca genome (GCA_003812925.1_ASM381292v1) for testing now..." && \ wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/812/925/GCA_003812925.1_ASM381292v1/GCA_003812925.1_ASM381292v1_genomic.fna.gz && \ - amrfinder --threads 4 --plus --name GCA_003812925.1 -n GCA_003812925.1_ASM381292v1_genomic.fna.gz -O Klebsiella_oxytoca -o GCA_003812925.1-amrfinder.tsv + amrfinder --threads 4 --plus --name GCA_003812925.1 -n GCA_003812925.1_ASM381292v1_genomic.fna.gz -O Klebsiella_oxytoca -o GCA_003812925.1-amrfinder.tsv & \ + head GCA_003812925.1-amrfinder.tsv # test that gunzip is installed RUN gunzip --help From fda6f99c61351a55b7538efa905ef668b846cd60 Mon Sep 17 00:00:00 2001 From: Young Date: Thu, 7 Nov 2024 12:33:33 -0700 Subject: [PATCH 68/92] fixed typo --- ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile b/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile index 5604c3ea4..33b978e10 100755 --- a/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile +++ b/ncbi-amrfinderplus/4.0.3-2024-10-22.1/Dockerfile @@ -94,7 +94,7 @@ RUN echo "Downloading Salmonella genome (GCA_010941835.1_PDT000052640.3) for tes # run amrfinder on Klebesiella oxytoca using --organism/-O flag RUN echo "Downloading Klebsiella oxytoca genome (GCA_003812925.1_ASM381292v1) for testing now..." && \ wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/812/925/GCA_003812925.1_ASM381292v1/GCA_003812925.1_ASM381292v1_genomic.fna.gz && \ - amrfinder --threads 4 --plus --name GCA_003812925.1 -n GCA_003812925.1_ASM381292v1_genomic.fna.gz -O Klebsiella_oxytoca -o GCA_003812925.1-amrfinder.tsv & \ + amrfinder --threads 4 --plus --name GCA_003812925.1 -n GCA_003812925.1_ASM381292v1_genomic.fna.gz -O Klebsiella_oxytoca -o GCA_003812925.1-amrfinder.tsv && \ head GCA_003812925.1-amrfinder.tsv # test that gunzip is installed From f0a1c6c7236be99ec8ad79ceb7e33937560b7e62 Mon Sep 17 00:00:00 2001 From: Young Date: Sat, 9 Nov 2024 08:42:46 -0700 Subject: [PATCH 69/92] adding virulencefinder version 3.0.0 (#927) * adding virulencefinder version 2.0.5 * updated versions * updated db commit * adding virulencefinder version 3.0.0 * as -> AS in FROM lines want to silence warning and trigger automation to build * added mentions of Enterococcus, S. aureus, and Listeria to virulencefinder readme * updated CMD to recommended JSON argument syntax * Update virulencefinder 3.0.0 readme with updated dependency versions * removed unnecessary and confusing pip3 install line from virulencefinder 3.0.0 dockerfile * updated comments w correct blast and python versions. also forced bash shell so alias is set properly (I was getting a weird error when running the virulencefinder.py command manually * update virulencefinder readme with updated help message and example usage commands * correct version of numpy in readme --------- Co-authored-by: Curtis Kapsak --- README.md | 2 +- virulencefinder/3.0.0/Dockerfile | 129 ++++++++++++++++++++++++++++++ virulencefinder/3.0.0/README.md | 130 +++++++++++++++++++++++++++++++ 3 files changed, 260 insertions(+), 1 deletion(-) create mode 100644 virulencefinder/3.0.0/Dockerfile create mode 100644 virulencefinder/3.0.0/README.md diff --git a/README.md b/README.md index 1d9235beb..ac6306bd5 100644 --- a/README.md +++ b/README.md @@ -311,7 +311,7 @@ To learn more about the docker pull rate limits and the open source software pro | [VIGOR4](https://hub.docker.com/r/staphb/vigor4/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/vigor4)](https://hub.docker.com/r/staphb/vigor4) |
    • [4.1.20190131](./vigor4/4.1.20190131/)
    • [4.1.20200702](./vigor4/4.1.20200702/)
    | https://github.com/JCVenterInstitute/VIGOR4 | | [Viridian](https://hub.docker.com/r/staphb/viridian/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/viridian)](https://hub.docker.com/r/staphb/viridian) |
    • [1.2.2](./viridian/1.2.2/)
    • [1.3.0](./viridian/1.3.0/)
    | https://github.com/iqbal-lab-org/viridian | | [VirSorter2](https://hub.docker.com/r/staphb/virsorter2/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/virsorter2)](https://hub.docker.com/r/staphb/virsorter2/) |
    • 2.1
    | https://github.com/jiarong/VirSorter2 | -| [VirulenceFinder](https://hub.docker.com/r/staphb/virulencefinder/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/virulencefinder)](https://hub.docker.com/r/staphb/virulencefinder/) |
    • [2.1.4](virulencefinder/2.0.4/)
    | https://bitbucket.org/genomicepidemiology/virulencefinder/src/master/
    https://bitbucket.org/genomicepidemiology/virulencefinder_db/src/master/ | +| [VirulenceFinder](https://hub.docker.com/r/staphb/virulencefinder/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/virulencefinder)](https://hub.docker.com/r/staphb/virulencefinder/) |
    • [2.0.4](virulencefinder/2.0.4/)
    • [3.0.0](virulencefinder/3.0.0/)
    | https://bitbucket.org/genomicepidemiology/virulencefinder/src/master/
    https://bitbucket.org/genomicepidemiology/virulencefinder_db/src/master/ | | [wtdbg2](https://hub.docker.com/r/staphb/wtdbg2/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/wtdbg2)](https://hub.docker.com/r/staphb/wtdbg2) |
    • 2.5
    | https://github.com/ruanjue/wtdbg2 | You can also view the list of images on Docker hub here: https://hub.docker.com/r/staphb/ diff --git a/virulencefinder/3.0.0/Dockerfile b/virulencefinder/3.0.0/Dockerfile new file mode 100644 index 000000000..3588a1873 --- /dev/null +++ b/virulencefinder/3.0.0/Dockerfile @@ -0,0 +1,129 @@ +ARG VIRULENCEFINDER_VER="3.0.0" +ARG VIRULENCEFINDER_DB_VER="2.0.0" +# Database sometimes is not properly versioned, so using most recent commit made on 2024-04-06 would be something like +# see here: https://bitbucket.org/genomicepidemiology/virulencefinder_db/commits/bcf7f0b26271a59ca85715fa2ab8a0c380e5357b +# ARG VIRULENCEFINDER_DB_COMMIT_HASH="bcf7f0b26271a59ca85715fa2ab8a0c380e5357b" + +FROM ubuntu:jammy AS app + +# re-instantiating for use in the app layer +ARG VIRULENCEFINDER_VER +ARG VIRULENCEFINDER_DB_COMMIT_HASH +ARG VIRULENCEFINDER_DB_VER +ARG KMA_VER="1.4.15" + +# metadata +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="VirulenceFinder" +LABEL software.version="${VIRULENCEFINDER_VER}" +LABEL description="Tool for identifying the virulence genes in E. coli, Enterococcus, Staphylococcus aureus, & Listeria from reads or assemblies" +LABEL website="https://bitbucket.org/genomicepidemiology/virulencefinder" +LABEL license="https://bitbucket.org/genomicepidemiology/virulencefinder/src/master/" +LABEL maintainer="Curtis Kapsak" +LABEL maintainer.email="kapsakcj@gmail.com" +LABEL maintainer1="Erin Young" +LABEL maintainer1.email="eriny@utah.gov" + +# install dependencies; cleanup apt garbage +# ncbi-blast+ v2.12.0 (ubuntu:jammy), min required version is 2.8.1 +# python3 v3.10.12, min required version is 3.10 +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + procps \ + git \ + ncbi-blast+ \ + python3 \ + python3-pip \ + python3-setuptools \ + python3-dev \ + gcc \ + make \ + libz-dev \ + dos2unix \ + unzip \ + python-is-python3 && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* && \ + update-alternatives --install /usr/bin/python python /usr/bin/python3 10 + +# Install kma +# apt deps: libz-dev (for compiling) +RUN git clone --branch ${KMA_VER} --depth 1 https://bitbucket.org/genomicepidemiology/kma.git && \ + cd kma &&\ + make &&\ + mv kma kma_index kma_shm kma_update /usr/local/bin/ + +# download VIRULENCEFINDER database +# index database w/ kma +# NOTE: files HAVE to go into '/database' since that is the default location expected by virulencefinder +# dos2unix on the FASTA files to ensure they have LF line endings +RUN mkdir /database && \ + git clone --depth 1 https://bitbucket.org/genomicepidemiology/virulencefinder_db.git /databases && \ + cd /databases && \ + git fetch --depth 1 origin tag ${VIRULENCEFINDER_DB_VER} && \ + rm -rf .git && \ + dos2unix *.fsa && \ + python3 INSTALL.py kma_index + +# install virulencefinder to specific tag/version; make /data +RUN git clone --branch ${VIRULENCEFINDER_VER} --depth 1 https://bitbucket.org/genomicepidemiology/virulencefinder.git && \ + rm -rf /virulencefinder/.git && \ + cd /virulencefinder && \ + pip3 install . && \ + mkdir /data + +# set $PATH and locale settings for singularity compatibility +ENV PATH="/virulencefinder:${PATH}" \ + LC_ALL=C.UTF-8 \ + CGE_BLASTN=/usr/bin/blastn \ + CGE_VIRULENCEFINDER_DB=/databases + +# set final working directory for production docker image (app layer only) +WORKDIR /data + +# force bash shell so below lines to make an alias runs properly +SHELL ["/bin/bash", "-c"] + +# setting a janky alias for everyone that uses the "latest" tag +RUN echo -e '#!/bin/bash\npython -m virulencefinder "$@"' > /usr/bin/virulencefinder.py && \ + chmod +x /usr/bin/virulencefinder.py + +# default command is to pull up help options for virulencefinder +CMD [ "python", "-m", "virulencefinder", "-h" ] + +### START OF TEST STAGE ### +FROM app AS test + +RUN python -m virulencefinder -h && /usr/bin/virulencefinder.py -h + +# set working directory for test layer +WORKDIR /test + +# download an example assembly; test with VirulenceFinder +# Escherichia coli complete genome (Unicycler assembly) +# GenBank Nucleotide entry: https://www.ncbi.nlm.nih.gov/nuccore/CP113091.1/ +# BioSample:SAMN08799860 +RUN mkdir asm-input && \ + wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/012/224/845/GCA_012224845.2_ASM1222484v2/GCA_012224845.2_ASM1222484v2_genomic.fna.gz && \ + gunzip GCA_012224845.2_ASM1222484v2_genomic.fna.gz && \ + python -m virulencefinder -h && \ + which blastn && \ + head -n 5 /test/GCA_012224845.2_ASM1222484v2_genomic.fna && \ + python -m virulencefinder -ifa /test/GCA_012224845.2_ASM1222484v2_genomic.fna --extented_output -o asm-input && \ + ls asm-input && \ + cat asm-input/results_tab.tsv + +# download Illumina reads for the same sample ^ and test reads as input into VirulenceFinder +RUN mkdir /test/reads-input && \ + wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR690/006/SRR6903006/SRR6903006_1.fastq.gz && \ + wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR690/006/SRR6903006/SRR6903006_2.fastq.gz && \ + python -m virulencefinder -ifq SRR6903006_1.fastq.gz SRR6903006_2.fastq.gz --extented_output -o /test/reads-input && \ + cat /test/reads-input/results_tab.tsv + +# test using FASTA supplied with VirulenceFinder code; print help options +# expect to see hits to astA and 2 stx genes; unfortunately it finds astA and 3 stx genes (that don't match) +# issue created here: https://bitbucket.org/genomicepidemiology/virulencefinder/issues/11/test-results-do-not-match-expected-results +RUN cd /virulencefinder/tests && \ + python -m virulencefinder -ifa data/test.fsa -o . && \ + ls diff --git a/virulencefinder/3.0.0/README.md b/virulencefinder/3.0.0/README.md new file mode 100644 index 000000000..fb1dad22f --- /dev/null +++ b/virulencefinder/3.0.0/README.md @@ -0,0 +1,130 @@ +# VirulenceFinder 3.0.0 Docker Image + +A docker image that contains VirulenceFinder, a tool for identifying virulence factors in E. coli, Enterococcus, S. aureus, and Listeria isolates from reads or assemblies + +[Link to StaPH-B DockerHub repository](https://hub.docker.com/r/staphb/virulencefinder) + +Main tool: + +- Main Code Repo: [https://bitbucket.org/genomicepidemiology/virulencefinder/src/master/](https://bitbucket.org/genomicepidemiology/virulencefinder/src/master/) +- VirulenceFinder database: [https://bitbucket.org/genomicepidemiology/virulencefinder_db/src/master/](https://bitbucket.org/genomicepidemiology/virulencefinder_db/src/master/) +- You may be familiar with the web version of VirulenceFinder: [https://cge.food.dtu.dk/services/VirulenceFinder/](https://cge.food.dtu.dk/services/VirulenceFinder/) + +Additional tools: + +- python 3.10.12 +- cgecore 1.5.6 +- biopython 1.84 +- numpy 2.1.3 +- pandas 2.2.3 +- tabulate 0.9.0 +- [kma](https://bitbucket.org/genomicepidemiology/kma/src/master/) 1.4.15 +- ncbi-blast+ 2.12.0 + +Database version: + +VirulenceFinder database version: tag 2.0.0 made on 2024-05-29. [Link to commit history](https://bitbucket.org/genomicepidemiology/virulencefinder_db/downloads/?tab=tags) + +## Usage + +```bash +$ virulencefinder.py -h +usage: __main__.py [-h] [-ifa INPUTFASTA [INPUTFASTA ...]] [-ifq INPUTFASTQ [INPUTFASTQ ...]] [--nanopore] [-o OUTPUTPATH] [-tmp TMP_DIR] [-b BLASTPATH] [-k KMAPATH] [-p DB_PATH] [-d DATABASES] [-l MIN_COV] + [-t THRESHOLD] [-x] [--speciesinfo_json SPECIESINFO_JSON] [-db_vir_kma DB_PATH_VIR_KMA] [-q] [-j OUT_JSON] [-v] [--overlap OVERLAP] + +options: + -h, --help show this help message and exit + -ifa INPUTFASTA [INPUTFASTA ...], --inputfasta INPUTFASTA [INPUTFASTA ...] + FASTA or FASTQ input files. + -ifq INPUTFASTQ [INPUTFASTQ ...], --inputfastq INPUTFASTQ [INPUTFASTQ ...] + Input fastq file(s). Assumed to be single-end fastq if only one file is provided, and assumed to be paired-end data if two files are provided. + --nanopore If nanopore data is used + -o OUTPUTPATH, --outputPath OUTPUTPATH + Path to blast output + -tmp TMP_DIR, --tmp_dir TMP_DIR + Temporary directory for storage of the results from the external software. Defaults to 'tmp' dir in the given output dir. + -b BLASTPATH, --blastPath BLASTPATH + Path to blastn + -k KMAPATH, --kmaPath KMAPATH + Path to KMA + -p DB_PATH, --databasePath DB_PATH + Path to the databases + -d DATABASES, --databases DATABASES + Databases chosen to search in - if non or all is specified all is used + -l MIN_COV, --mincov MIN_COV + Minimum coverage + -t THRESHOLD, --threshold THRESHOLD + Minimum hreshold for identity + -x, --extented_output + Give extented output with allignment files, template and query hits in fasta and a tab seperated file with gene profile results + --speciesinfo_json SPECIESINFO_JSON + Argument used by the cge pipeline. It takes a list in json format consisting of taxonomy, from domain -> species. A database is chosen based on the taxonomy. + -db_vir_kma DB_PATH_VIR_KMA, --db_path_vir_kma DB_PATH_VIR_KMA + Path to the virulencefinder databases indexed with KMA. Defaults to the value of the --db_res flag. + -q, --quiet + -j OUT_JSON, --out_json OUT_JSON + Specify JSON filename and output directory. If the directory doesn't exist, it will be created. + -v, --version Version of Virulencefinder + --overlap OVERLAP Genes are allowed to overlap this number ofnucleotides. +``` + +## Notes and Recommendations + +- You do not need to supply a database or use the `-p` or `-d` flags + - Database is included in the image and is in the default/expected location within the image filesystem: `/database` + - (*NOT RECOMMENDED*) If you do need to use your own database, you will need to first index it with `kma` and use the `virulencefinder.py -p` flag. You can find instructions for this on the VirulenceFinder Bitbucket README. `kma` is included in this docker image for database indexing. + - VirulenceFinder does **NOT** create an output directory when you use the `-o` flag. You MUST create it beforehand or it will throw an error. + - **Default % Identity threshold: 90%**. Adjust with `-t 0.95` + - **Default % coverage threshold: 60%**. Adjust with `-l 0.70` + - Use the `-x` flag (extended output) if you want the traditional/legacy VirulenceFinder output files `results_tab.tsv results.txt Virulence_genes.fsa Hit_in_genome_seq.fsa`. Otherwise you will need to parse the default output file `data.json` for results + - (*RECOMMENDED*) Use raw reads due to the increased sensitivity (without loss of specificity) and the additional information gleaned from KMA output (specifically the depth metric). You also save time from having to assemble the genome first. [CITATION NEEDED, PROBABLY THE KMA PAPER] +- Querying reads: + - This will run VirulenceFinder with `kma` (instead of ncbi-blast+) + - Only one of the PE read files is necessary. There is likely little benefit to using both R1 and R2. It will take longer to run if you use both R1 and R2 files. +- Querying assemblies: + - This will run VirulenceFinder with `ncbi-blast+` + - VirulenceFinder does not clean up after itself. `tmp/` (which contains 7 different `.xml` files) will exist in the specified output directory + +## Example Usage: Docker + +```bash +# download the image +$ docker pull staphb/virulencefinder:latest + +# input files are in my PWD +$ ls +E-coli.skesa.fasta E-coli.R1.fastq.gz E-coli.R2.fastq.gz + +# make an output directory +$ mkdir output-dir-reads output-dir-asm + +# query reads, mount PWD to /data inside container (broken into two lines for readabilty) +$ docker run --rm -u $(id -u):$(id -g) -v $PWD:/data staphb/virulencefinder:latest \ + virulencefinder.py -ifq /data/E-coli.R1.fastq.gz -o /data/output-dir-reads -x + +# query assembly +$ docker run --rm -u $(id -u):$(id -g) -v $PWD:/data staphb/virulencefinder:latest \ + virulencefinder.py -ifa /data/E-coli.skesa.fasta -o /data/output-dir-asm -x +``` + +## Example Usage: Singularity + +```bash +# download the image +$ singularity build virulencefinder.latest.sif docker://staphb/virulencefinder:latest + +# files are in my PWD +$ ls +E-coli.skesa.fasta E-coli.R1.fastq.gz E-coli.R2.fastq.gz + +# make an output directory +$ mkdir output-dir-reads output-dir-asm + +# query reads; mount PWD to /data inside container +$ singularity exec --no-home -B $PWD:/data virulencefinder.latest.sif \ + virulencefinder.py -ifq /data/E-coli.R1.fastq.gz /data/E-coli.R2.fastq.gz -o /data/output-dir-reads -x + +# assembly +$ singularity exec --no-home -B $PWD:/data virulencefinder.latest.sif \ + virulencefinder.py -ifa /data/E-coli.skesa.fasta -o /data/output-dir-asm -x +``` From 592a9d338fb5e124682433ebede16ffa72af7a81 Mon Sep 17 00:00:00 2001 From: Young Date: Sat, 9 Nov 2024 09:00:58 -0700 Subject: [PATCH 70/92] updating augur to version 26.0.0 (#1054) * updating augur to version 26.0.0 * minor changes to dockerfile to silence warnings, quiet down some output, and use recommend CMD format --------- Co-authored-by: Curtis Kapsak --- README.md | 2 +- augur/26.0.0/Dockerfile | 65 +++++++++++++++++++++++++++++++++++++++++ augur/26.0.0/README.md | 46 +++++++++++++++++++++++++++++ 3 files changed, 112 insertions(+), 1 deletion(-) create mode 100644 augur/26.0.0/Dockerfile create mode 100644 augur/26.0.0/README.md diff --git a/README.md b/README.md index ac6306bd5..8958441d7 100644 --- a/README.md +++ b/README.md @@ -120,7 +120,7 @@ To learn more about the docker pull rate limits and the open source software pro | [artic-ncov2019-medaka](https://hub.docker.com/r/staphb/artic-ncov2019-medaka)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/artic-ncov2019-medaka)](https://hub.docker.com/r/staphb/artic-ncov2019-medaka) |
    • 1.1.0
    | https://github.com/artic-network/artic-ncov2019 | | [artic-ncov2019-nanopolish](https://hub.docker.com/r/staphb/artic-ncov2019-nanopolish)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/artic-ncov2019-nanopolish)](https://hub.docker.com/r/staphb/artic-ncov2019-nanopolish) |
    • 1.1.0
    | https://github.com/artic-network/artic-ncov2019 | | [assembly_snptyper](https://hub.docker.com/r/staphb/assembly_snptyperh)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/assembly_snptyper)](https://hub.docker.com/r/staphb/assembly_snptyper) |
    • [0.1.1](./assembly_snptyper/0.1.1/)
    | https://github.com/boasvdp/assembly_snptyper | -| [Augur](https://hub.docker.com/r/staphb/augur)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/augur)](https://hub.docker.com/r/staphb/augur) |
    • [6.3.0](./augur/6.3.0/)
    • [7.0.2](./augur/7.0.2/)
    • [8.0.0](./augur/8.0.0/)
    • [9.0.0](./augur/9.0.0/)
    • [16.0.3](./augur/16.0.3/)
    • [24.2.2](./augur/24.2.2/)
    • [24.2.3](./augur/24.2.3/)
    • [24.3.0](./augur/24.3.0/)
    • [24.4.0](./augur/24.4.0/)
    | https://github.com/nextstrain/augur | +| [Augur](https://hub.docker.com/r/staphb/augur)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/augur)](https://hub.docker.com/r/staphb/augur) |
    • [6.3.0](./augur/6.3.0/)
    • [7.0.2](./augur/7.0.2/)
    • [8.0.0](./augur/8.0.0/)
    • [9.0.0](./augur/9.0.0/)
    • [16.0.3](./augur/16.0.3/)
    • [24.2.2](./augur/24.2.2/)
    • [24.2.3](./augur/24.2.3/)
    • [24.3.0](./augur/24.3.0/)
    • [24.4.0](./augur/24.4.0/)
    • [26.0.0](./augur/26.0.0/)
    | https://github.com/nextstrain/augur | | [Auspice](https://hub.docker.com/r/staphb/auspice)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/auspice)](https://hub.docker.com/r/staphb/auspice) |
    • 2.12.0
    | https://github.com/nextstrain/auspice | | [bakta](https://hub.docker.com/r/staphb/bakta)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bakta)](https://hub.docker.com/r/staphb/bakta) |
    • [1.9.2](./bakta/1.9.2/)
    • [1.9.2-light](./bakta/1.9.2-5.1-light/)
    • [1.9.3](./bakta/1.9.3/)
    • [1.9.3-light](./bakta/1.9.3-5.1-light/)
    • [1.9.4](./bakta/1.9.4/)
    • [1.9.4-5.1-light](./bakta/1.9.4-5.1-light/)
    | https://github.com/oschwengers/bakta | | [bandage](https://hub.docker.com/r/staphb/bandage)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/bandage)](https://hub.docker.com/r/staphb/bandage) |
    • [0.8.1](./bandage/0.8.1/)
    | https://rrwick.github.io/Bandage/ | diff --git a/augur/26.0.0/Dockerfile b/augur/26.0.0/Dockerfile new file mode 100644 index 000000000..b108c2582 --- /dev/null +++ b/augur/26.0.0/Dockerfile @@ -0,0 +1,65 @@ +FROM python:3.11-slim AS app + +ARG AUGUR_VER="26.0.0" + +# LABEL instructions tag the image with metadata that might be important to the user +# Optional, but highly recommended +LABEL base.image="python:3.11-slim" +LABEL dockerfile.version="1" +LABEL software="augur" +LABEL software.version=${AUGUR_VER} +LABEL description="Augur is the bioinformatics toolkit we use to track evolution from sequence and serological data.The output of augur is a series of JSONs that can be used to visualize your results using Auspice." +LABEL website="https://github.com/nextstrain/augur" +LABEL license="https://github.com/nextstrain/augur/blob/master/LICENSE.txt" +LABEL maintainer="John Arnn" +LABEL maintainer.email="jarnn@utah.gov" + +# 'RUN' executes code during the build +# Install dependencies via apt-get or yum if using a centos or fedora base +RUN apt-get update && apt-get install -y --no-install-recommends \ + procps \ + ca-certificates \ + wget \ + mafft \ + iqtree \ + raxml \ + fasttree \ + vcftools && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +RUN wget -q https://github.com/nextstrain/augur/archive/refs/tags/${AUGUR_VER}.tar.gz && \ + tar -xzf ${AUGUR_VER}.tar.gz && \ + pip install ${AUGUR_VER}.tar.gz && \ + rm -v ${AUGUR_VER}.tar.gz + #&& \ + #cd augur-${AUGUR_VER} && \ + #python3 -m pip install '.[full]' + +CMD [ "augur", "--help" ] + +WORKDIR /data + +FROM app AS test + +RUN augur --help + +WORKDIR /test + +RUN apt-get update && apt-get install -y --no-install-recommends git + +RUN git clone https://github.com/nextstrain/zika-tutorial && \ + cd zika-tutorial && \ + mkdir results && \ + augur index --sequences data/sequences.fasta --output results/sequence_index.tsv && \ + augur filter --sequences data/sequences.fasta \ + --sequence-index results/sequence_index.tsv \ + --metadata data/metadata.tsv \ + --exclude config/dropped_strains.txt \ + --output results/filtered.fasta \ + --sequences-per-group 20 \ + --min-date 2012 && \ + augur align \ + --sequences results/filtered.fasta \ + --reference-sequence config/zika_outgroup.gb \ + --output results/aligned.fasta \ + --fill-gaps diff --git a/augur/26.0.0/README.md b/augur/26.0.0/README.md new file mode 100644 index 000000000..bd1b41b9f --- /dev/null +++ b/augur/26.0.0/README.md @@ -0,0 +1,46 @@ +# Augur Container + +Main tool: [Augur](https://github.com/nextstrain/augur) + +Additional tools: + +- mafft 7.505 +- iqtree2 2.0.7 +- raxml 8.2.12 +- fasttree 2.1.11 +- vcftools 0.1.16 +- biopython 1.84 +- matplotlib 3.9.2 +- numpy 1.26.4 +- pandas 1.5.3 +- phylo-treetime 0.11.4 +- python 3.11.10 +- scipy 1.14.1 + +Definition: One held to foretell events by omens. + +Augur is the bioinformatics toolkit we use to track evolution from sequence and serological data. It provides a collection of commands which are designed to be composable into larger processing pipelines. + +The output of augur is a series of JSONs that can be used to visualize your results using Auspice. + +Note: Auspice is a different tool. + +## Example Usage + +```bash +augur index --sequences sequences.fasta --output sequence_index.tsv +``` + +```bash +augur filter \ + --sequences data/sequences.fasta \ + --sequence-index results/sequence_index.tsv \ + --metadata data/metadata.tsv \ + --exclude config/dropped_strains.txt \ + --output results/filtered.fasta \ + --group-by country year month \ + --sequences-per-group 20 \ + --min-date 2012 +``` + +Better documentation can be found [here.](https://docs.nextstrain.org/en/latest/tutorials/creating-a-workflow.html) From f13d65273968c74bb8575ab2f6a6ca9072f0a6a4 Mon Sep 17 00:00:00 2001 From: Young Date: Sat, 9 Nov 2024 09:04:54 -0700 Subject: [PATCH 71/92] update pango aliasor weekly (#1083) --- .github/workflows/update_pango_aliasor.yml | 82 ++++++++++++++++++++++ 1 file changed, 82 insertions(+) create mode 100644 .github/workflows/update_pango_aliasor.yml diff --git a/.github/workflows/update_pango_aliasor.yml b/.github/workflows/update_pango_aliasor.yml new file mode 100644 index 000000000..cc3e46ed2 --- /dev/null +++ b/.github/workflows/update_pango_aliasor.yml @@ -0,0 +1,82 @@ +##### ------------------------------------------------------------------------------------------------ ##### +##### This caller workflow tests, builds, and pushes the image to Docker Hub and Quay using the most ##### +##### recent version of pango_aliasor and downloads the current pangolin lineages. ##### +##### It takes no manual input. ##### +##### ------------------------------------------------------------------------------------------------ ##### + +name: Update pango aliasor + +on: + workflow_dispatch: + schedule: + - cron: '30 7 * * 1' + +run-name: Updating pango aliasor + +jobs: + update: + runs-on: ubuntu-latest + steps: + + - name: pull repo + uses: actions/checkout@v4 + + - name: set pango_aliasor version + id: latest_version + run: | + version=0.3.0 + echo "version=$version" >> $GITHUB_OUTPUT + + file=pango_aliasor/0.3.0/Dockerfile + ls $file + echo "file=$file" >> $GITHUB_OUTPUT + + - name: set up docker buildx + id: buildx + uses: docker/setup-buildx-action@v3 + + - name: build to test + id: docker_build_to_test + uses: docker/build-push-action@v5 + with: + context: pango_aliasor/${{ steps.latest_version.outputs.version }} + target: test + load: true + push: false + tags: pango_aliasor:update + + - name: Get current date + id: date + run: | + date=$(date '+%Y-%m-%d') + echo "the date is $date" + echo "date=$date" >> $GITHUB_OUTPUT + + - name: Login to DockerHub + uses: docker/login-action@v3 + with: + username: ${{ secrets.DOCKER_HUB_USERNAME }} + password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }} + + - name: Login to Quay + uses: docker/login-action@v3 + with: + registry: quay.io + username: ${{ secrets.QUAY_USERNAME }} + password: ${{ secrets.QUAY_ROBOT_TOKEN }} + + - name: Build and push user-defined tag to DockerHub + id: docker_build_user_defined_tag + uses: docker/build-push-action@v5 + with: + file: ${{ steps.latest_version.outputs.file }} + target: app + push: true + tags: | + staphb/pango_aliasor:${{ steps.latest_version.outputs.version }}-${{ steps.date.outputs.date }} + staphb/pango_aliasor:latest + quay.io/staphb/pango_aliasor:${{ steps.latest_version.outputs.version }}-${{ steps.date.outputs.date }} + quay.io/staphb/pango_aliasor:latest + + - name: Image digest + run: echo ${{ steps.docker_build.outputs.digest }} From 02cedd5456f044348d4a2a16de86d28e3aeb6478 Mon Sep 17 00:00:00 2001 From: Young Date: Sat, 9 Nov 2024 09:22:26 -0700 Subject: [PATCH 72/92] adding kaptive version 3.0.0b6 (#1091) * adding kaptive version 3.0.0b6 * updated usage * added help and version * minor changes to kaptive dockerfile and readme --------- Co-authored-by: Curtis Kapsak --- README.md | 2 +- kaptive/3.0.0b6/Dockerfile | 120 +++++++++++++++++++++++++++++++++++++ kaptive/3.0.0b6/README.md | 61 +++++++++++++++++++ 3 files changed, 182 insertions(+), 1 deletion(-) create mode 100644 kaptive/3.0.0b6/Dockerfile create mode 100644 kaptive/3.0.0b6/README.md diff --git a/README.md b/README.md index 8958441d7..3d045918c 100644 --- a/README.md +++ b/README.md @@ -190,7 +190,7 @@ To learn more about the docker pull rate limits and the open source software pro | [isPcr](https://users.soe.ucsc.edu/~kent/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/ispcr)](https://hub.docker.com/r/staphb/ispcr) |
    • [33](ispcr/33/)
    | https://users.soe.ucsc.edu/~kent/ | | [iVar](https://hub.docker.com/r/staphb/ivar/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/ivar)](https://hub.docker.com/r/staphb/ivar) |
    • [1.1](./ivar/1.1/)
    • [1.1 (+SARS-CoV2 reference)](./ivar/1.1-SC2/)
    • [1.2.1](./ivar/1.2.1/)
    • [1.2.1 (+SC2 ref)](./ivar/1.2.1-SC2/)
    • [1.2.2 (+SC2 ref and artic bedfiles)](./ivar/1.2.2_artic20200528/)
    • [1.3](./ivar/1.3/)
    • [1.3.1](./ivar/1.3.1/)
    • [1.3.2](./ivar/1.3.2/)
    • [1.4.1](./ivar/1.4.1/)
    • [1.4.2](./ivar/1.4.2/)
    • [1.4.3](./ivar/1.4.3/)
    | https://github.com/andersen-lab/ivar | | [Jasmine](https://hub.docker.com/r/staphb/pbjasmine/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/pbjasmine)](https://hub.docker.com/r/staphb/pbjasmine) |
    • [2.0.0](./pbjasmine/2.0.0/)
    | https://github.com/PacificBiosciences/jasmine | -| [Kaptive](https://hub.docker.com/r/staphb/kaptive/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kaptive)](https://hub.docker.com/r/staphb/kaptive) |
    • [2.0.0](./kaptive/2.0.0/)
    • [2.0.3](./kaptive/2.0.3/)
    • [2.0.5](./kaptive/2.0.5/)
    • [2.0.8](./kaptive/2.0.8/)
    | https://github.com/klebgenomics/Kaptive | +| [Kaptive](https://hub.docker.com/r/staphb/kaptive/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kaptive)](https://hub.docker.com/r/staphb/kaptive) |
    • [2.0.0](./kaptive/2.0.0/)
    • [2.0.3](./kaptive/2.0.3/)
    • [2.0.5](./kaptive/2.0.5/)
    • [2.0.8](./kaptive/2.0.8/)
    • [3.0.0b6](./kaptive/3.0.0b6/)
    | https://github.com/klebgenomics/Kaptive | | [Kleborate](https://hub.docker.com/r/staphb/kleborate/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kleborate)](https://hub.docker.com/r/staphb/kleborate) |
    • [2.0.4](./kleborate/2.0.4/)
    • [2.1.0](./kleborate/2.1.0/)
    • [2.2.0](./kleborate/2.3.2/)
    • [2.3.2](./kleborate/2.3.2)
    • [2.3.2-2023-05](kleborate/2.3.2-2023-05/)
    • [2.4.1](kleborate/2.4.1/)
    | https://github.com/katholt/Kleborate/
    https://github.com/katholt/Kaptive/ | | [kma](https://hub.docker.com/r/staphb/kma/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kma)](https://hub.docker.com/r/staphb/kma) |
    • 1.2.21
    • 1.4.10 (no database)
    • [1.4.14](./kma/1.4.14/) (no database)
    | https://bitbucket.org/genomicepidemiology/kma/ | | [Kraken](https://hub.docker.com/r/staphb/kraken/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kraken)](https://hub.docker.com/r/staphb/kraken) |
    • 1.0
    • 1.1.1
    • 1.1.1 (no database)
    | https://github.com/DerrickWood/kraken | diff --git a/kaptive/3.0.0b6/Dockerfile b/kaptive/3.0.0b6/Dockerfile new file mode 100644 index 000000000..c8c830388 --- /dev/null +++ b/kaptive/3.0.0b6/Dockerfile @@ -0,0 +1,120 @@ +FROM ubuntu:jammy AS app + +# for easy upgrade later. ARG variables only persist during image build time +ARG MINIMAP2_VER="2.28" +ARG MASH_VER="2.3" +ARG KAPTIVE_VER="3.0.0b6" +ARG VP_GENOMOSEROTYPING_VER="1.0" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="Kaptive" +LABEL software.version="${KAPTIVE_VER}" +LABEL description="Report information about surface polysaccharide loci for Klebsiella pneumoniae species complex and Acinetobacter baumannii genome assemblies" +LABEL website="https://github.com/klebgenomics/Kaptive/" +LABEL license="https://github.com/klebgenomics/Kaptive/blob/master/LICENSE" +LABEL website.VPdatabase="https://github.com/aldertzomer/vibrio_parahaemolyticus_genomoserotyping" +LABEL license.VPdatabase="https://github.com/aldertzomer/vibrio_parahaemolyticus_genomoserotyping/blob/main/LICENSE" +LABEL maintainer="Tamas Stirling" +LABEL maintainer.email="stirling.tamas@gmail.com" +LABEL maintainer2="Curtis Kapsak" +LABEL maintainer2.email="kapsakcj@gmail.com" +LABEL maintainer3="Erin Young" +LABEL maintainer3.email="eriny@utah.gov" + +# install prerequisites. Cleanup apt garbage +RUN apt-get update && apt-get install -y --no-install-recommends \ + python3 \ + python3-pip \ + wget \ + ca-certificates \ + bzip2 \ + procps \ + curl && \ + rm -rf /var/lib/apt/lists/* && apt-get autoclean + +# mash; update UID and GID of mash files; make /data +# UID and GID changes because the original owner is UID: 1081147385 and GID: 1360859114 which does NOT play well with systems that limits GIDs and UIDs +RUN wget -q https://github.com/marbl/Mash/releases/download/v${MASH_VER}/mash-Linux64-v${MASH_VER}.tar && \ + tar -xvf mash-Linux64-v${MASH_VER}.tar --no-same-owner && \ + rm -rf mash-Linux64-v${MASH_VER}.tar && \ + chown root:root /mash-Linux64-v${MASH_VER}/* + +# install minimap2 binary; make /data +RUN curl -L https://github.com/lh3/minimap2/releases/download/v${MINIMAP2_VER}/minimap2-${MINIMAP2_VER}_x64-linux.tar.bz2 | \ + tar -jxvf - --no-same-owner + +# install kaptive +RUN pip install --no-cache-dir kaptive==${KAPTIVE_VER} + +# move databases +RUN wget -q https://github.com/klebgenomics/Kaptive/releases/download/v${KAPTIVE_VER}/kaptive-${KAPTIVE_VER}.tar.gz && \ + tar -vxf kaptive-${KAPTIVE_VER}.tar.gz --no-same-owner && \ + mkdir -p /data /kaptive/ && \ + mv /kaptive-${KAPTIVE_VER}/reference_database /kaptive/reference_database && \ + rm -rf kaptive-${KAPTIVE_VER}.tar.gz kaptive-${KAPTIVE_VER} + +# download Vibrio parahemolyticus database; mv gbk files to where the other references are +RUN wget -q https://github.com/aldertzomer/vibrio_parahaemolyticus_genomoserotyping/archive/refs/tags/${VP_GENOMOSEROTYPING_VER}.tar.gz && \ + tar -xzf ${VP_GENOMOSEROTYPING_VER}.tar.gz && \ + rm -v ${VP_GENOMOSEROTYPING_VER}.tar.gz && \ + mv -v vibrio_parahaemolyticus_genomoserotyping-${VP_GENOMOSEROTYPING_VER}/*gbk /kaptive/reference_database/. && \ + rm -rf vibrio_parahaemolyticus_genomoserotyping-${VP_GENOMOSEROTYPING_VER} + +# set PATH +ENV PATH="/mash-Linux64-v${MASH_VER}:/minimap2-${MINIMAP2_VER}_x64-linux:${PATH}" + +# set working directory +WORKDIR /data + +# default command is to print help options +CMD [ "kaptive", "--help" ] + +# test layer +FROM app AS test + +RUN kaptive --help && kaptive --version + +WORKDIR /test1 + +# test with A. baumannii; testing both k and o locus +RUN echo "downloading an A. baumannii genome & testing Kaptive..." && \ + wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/016/486/705/GCA_016486705.1_PDT000751301.1/GCA_016486705.1_PDT000751301.1_genomic.fna.gz && \ + gzip -d GCA_016486705.1_PDT000751301.1_genomic.fna.gz && \ + kaptive assembly /kaptive/reference_database/Acinetobacter_baumannii_k_locus_primary_reference.gbk GCA_016486705.1_PDT000751301.1_genomic.fna -o abau_k.txt && head abau_k.txt && \ + kaptive assembly /kaptive/reference_database/Acinetobacter_baumannii_OC_locus_primary_reference.gbk GCA_016486705.1_PDT000751301.1_genomic.fna -o abau_oc.txt && head abau_oc.txt + +WORKDIR /test2 +# test with K. pneumoniae; testing both k and o locus +RUN echo "downloading an K. pneumoniae genome & testing Kaptive..." && \ + wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/022/268/055/GCA_022268055.1_PDT000434809.1/GCA_022268055.1_PDT000434809.1_genomic.fna.gz && \ + gzip -d GCA_022268055.1_PDT000434809.1_genomic.fna.gz && \ + kaptive assembly /kaptive/reference_database/Klebsiella_k_locus_primary_reference.gbk GCA_022268055.1_PDT000434809.1_genomic.fna -o kpneu_k.txt && \ + kaptive assembly /kaptive/reference_database/Klebsiella_o_locus_primary_reference.gbk GCA_022268055.1_PDT000434809.1_genomic.fna -o kpneu_o.txt && \ + head kpneu_k.txt kpneu_o.txt + +WORKDIR /test3 +# test with recommended usage in documentatation +RUN echo "downloading an K. pneumoniae genome & testing Kaptive..." && \ + wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/022/268/055/GCA_022268055.1_PDT000434809.1/GCA_022268055.1_PDT000434809.1_genomic.fna.gz && \ + gzip -d GCA_022268055.1_PDT000434809.1_genomic.fna.gz && \ + kaptive assembly kpsc_k assemblies/*.fna -o kaptive_results.tsv && \ + head kaptive_results.tsv + +WORKDIR /test4 + +### test with at 2 Vibrio parahaemolyticus genomes with a known serotype. These 2 are pulled from the publication describing custom database ## +# GCA_001558495.2 - expect OL1 and KL1 +# GCA_001728135.1 - expect OL4 KL53 +# more info on test genome here: https://www.ncbi.nlm.nih.gov/data-hub/genome/GCF_001558495.2/ +# strain: ATCC17802 +# more info on 2nd test genome here: https://www.ncbi.nlm.nih.gov/data-hub/genome/GCF_001728135.1/ +# strain: CDC_K5009W +RUN echo "downloading an 2 V. parahaemolyticus genomes & testing Kaptive..." && \ + wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/558/495/GCF_001558495.2_ASM155849v2/GCF_001558495.2_ASM155849v2_genomic.fna.gz && \ + wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/728/135/GCF_001728135.1_ASM172813v1/GCF_001728135.1_ASM172813v1_genomic.fna.gz && \ + gzip -d GCF_001558495.2_ASM155849v2_genomic.fna.gz && \ + gzip -d GCF_001728135.1_ASM172813v1_genomic.fna.gz && \ + kaptive assembly /kaptive/reference_database/VibrioPara_Kaptivedb_K.gbk *.fna -o Vparahaemolyticus_K.txt && \ + kaptive assembly /kaptive/reference_database/VibrioPara_Kaptivedb_O.gbk *.fna -o Vparahaemolyticus_O.txt && \ + head Vparahaemolyticus_K.txt Vparahaemolyticus_O.txt \ No newline at end of file diff --git a/kaptive/3.0.0b6/README.md b/kaptive/3.0.0b6/README.md new file mode 100644 index 000000000..7e87de341 --- /dev/null +++ b/kaptive/3.0.0b6/README.md @@ -0,0 +1,61 @@ +# Kaptive Container + +Main tool: [Kaptive](https://github.com/klebgenomics/Kaptive) + +Additional tools: + +- minimap2 2.28 +- python 3.10.12 +- biopython 1.84 +- matplotlib 3.9.2 +- dna-features-viewer 3.1.3 +- numpy 2.1.3 + +## Kaptive databases + +There are few databases included in this docker image: + +- Klebsiella pneumoniae species complex + - included w/ Kaptive +- Acinetobacter baumannii + - included w/ Kaptive +- Vibrio parahaemolyticus + - Located in separate GitHub repo: https://github.com/aldertzomer/vibrio_parahaemolyticus_genomoserotyping + - Publication: https://www.microbiologyresearch.org/content/journal/mgen/10.1099/mgen.0.001007 + +The databases (Genbank/GBK files) are located as follows in the container filesystem: + +```bash +# Klebsiella pneumoniae species complex +/kaptive/reference_database/Klebsiella_k_locus_primary_reference.gbk +/kaptive/reference_database/Klebsiella_o_locus_primary_reference.gbk + +# Acinetobacter baumannii +/kaptive/reference_database/Acinetobacter_baumannii_k_locus_primary_reference.gbk +/kaptive/reference_database/Acinetobacter_baumannii_OC_locus_primary_reference.gbk + +# Vibrio parahaeolyticus +/kaptive/reference_database/VibrioPara_Kaptivedb_K.gbk +/kaptive/reference_database/VibrioPara_Kaptivedb_O.gbk +``` + +Example commands for each of these databases can be found below. + +## Example Usage + +```bash +# K locus, A. baumannii +kaptive.py assembly /kaptive/reference_database/Acinetobacter_baumannii_k_locus_primary_reference.gbk assembly.fasta -o outfile.txt +# O locus, A. baumannii +kaptive.py assembly /kaptive/reference_database/Acinetobacter_baumannii_OC_locus_primary_reference.gbk assembly.fasta -o outfile.txt + +# K locus, K. pneumoniae +kaptive.py assembly /kaptive/reference_database/Klebsiella_k_locus_primary_reference.gbk assembly.fasta -o outfile.txt +# O locus, K. pneumoniae +kaptive.py assembly /kaptive/reference_database/Klebsiella_o_locus_primary_reference.gbk assembly.fasta -o outfile.txt + +# K locus, V. parahaemolyticus +kaptive.py assembly /kaptive/reference_database/VibrioPara_Kaptivedb_K.gbk assembly.fasta -o outfile.txt +# O locus, V. parahaemolyticus +kaptive.py assembly /kaptive/reference_database/VibrioPara_Kaptivedb_O.gbk assembly.fasta -o outfile.txt +``` From 9e1fe42da18408537dd6e8f1265a5e33b2a8433a Mon Sep 17 00:00:00 2001 From: Young Date: Sat, 9 Nov 2024 09:57:27 -0700 Subject: [PATCH 73/92] Adding kleborate version 3.1.2 (#1092) * adding kleborate version 3.0.0 * adding kleborate version 3.1.2 * removed extra comments * removed git * fixed extra path * silenced some warnings; updated some comments; updated CMD to recommended format; uninstall old version of mash installed automatically via pypi since we install it manually * removed inaccurate comment --------- Co-authored-by: Curtis Kapsak --- README.md | 2 +- kleborate/3.1.2/Dockerfile | 67 ++++++++++++++++++++++++++++++ kleborate/3.1.2/README.md | 85 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 153 insertions(+), 1 deletion(-) create mode 100644 kleborate/3.1.2/Dockerfile create mode 100644 kleborate/3.1.2/README.md diff --git a/README.md b/README.md index 3d045918c..4dbed681a 100644 --- a/README.md +++ b/README.md @@ -191,7 +191,7 @@ To learn more about the docker pull rate limits and the open source software pro | [iVar](https://hub.docker.com/r/staphb/ivar/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/ivar)](https://hub.docker.com/r/staphb/ivar) |
    • [1.1](./ivar/1.1/)
    • [1.1 (+SARS-CoV2 reference)](./ivar/1.1-SC2/)
    • [1.2.1](./ivar/1.2.1/)
    • [1.2.1 (+SC2 ref)](./ivar/1.2.1-SC2/)
    • [1.2.2 (+SC2 ref and artic bedfiles)](./ivar/1.2.2_artic20200528/)
    • [1.3](./ivar/1.3/)
    • [1.3.1](./ivar/1.3.1/)
    • [1.3.2](./ivar/1.3.2/)
    • [1.4.1](./ivar/1.4.1/)
    • [1.4.2](./ivar/1.4.2/)
    • [1.4.3](./ivar/1.4.3/)
    | https://github.com/andersen-lab/ivar | | [Jasmine](https://hub.docker.com/r/staphb/pbjasmine/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/pbjasmine)](https://hub.docker.com/r/staphb/pbjasmine) |
    • [2.0.0](./pbjasmine/2.0.0/)
    | https://github.com/PacificBiosciences/jasmine | | [Kaptive](https://hub.docker.com/r/staphb/kaptive/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kaptive)](https://hub.docker.com/r/staphb/kaptive) |
    • [2.0.0](./kaptive/2.0.0/)
    • [2.0.3](./kaptive/2.0.3/)
    • [2.0.5](./kaptive/2.0.5/)
    • [2.0.8](./kaptive/2.0.8/)
    • [3.0.0b6](./kaptive/3.0.0b6/)
    | https://github.com/klebgenomics/Kaptive | -| [Kleborate](https://hub.docker.com/r/staphb/kleborate/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kleborate)](https://hub.docker.com/r/staphb/kleborate) |
    • [2.0.4](./kleborate/2.0.4/)
    • [2.1.0](./kleborate/2.1.0/)
    • [2.2.0](./kleborate/2.3.2/)
    • [2.3.2](./kleborate/2.3.2)
    • [2.3.2-2023-05](kleborate/2.3.2-2023-05/)
    • [2.4.1](kleborate/2.4.1/)
    | https://github.com/katholt/Kleborate/
    https://github.com/katholt/Kaptive/ | +| [Kleborate](https://hub.docker.com/r/staphb/kleborate/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kleborate)](https://hub.docker.com/r/staphb/kleborate) |
    • [2.0.4](./kleborate/2.0.4/)
    • [2.1.0](./kleborate/2.1.0/)
    • [2.2.0](./kleborate/2.3.2/)
    • [2.3.2](./kleborate/2.3.2)
    • [2.3.2-2023-05](kleborate/2.3.2-2023-05/)
    • [2.4.1](kleborate/2.4.1/)
    • [3.1.2](kleborate/3.1.2/)
    | https://github.com/katholt/Kleborate/
    https://github.com/katholt/Kaptive/ | | [kma](https://hub.docker.com/r/staphb/kma/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kma)](https://hub.docker.com/r/staphb/kma) |
    • 1.2.21
    • 1.4.10 (no database)
    • [1.4.14](./kma/1.4.14/) (no database)
    | https://bitbucket.org/genomicepidemiology/kma/ | | [Kraken](https://hub.docker.com/r/staphb/kraken/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kraken)](https://hub.docker.com/r/staphb/kraken) |
    • 1.0
    • 1.1.1
    • 1.1.1 (no database)
    | https://github.com/DerrickWood/kraken | | [Kraken2](https://hub.docker.com/r/staphb/kraken2/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/kraken2)](https://hub.docker.com/r/staphb/kraken2) |
    • 2.0.8-beta (no database)
    • 2.0.8-beta (MiniKraken2_v1_8GB db)
    • 2.0.8-beta_hv (human + virus db)
    • 2.0.9-beta (no db)
    • 2.0.9-beta (Minikraken v2 RefSeq: bacteria, archaea, viral, and human 8GB db)
    • 2.1.0 (no db)
    • 2.1.1 (no db)
    • 2.1.2 (no db)
    • [2.1.3](kraken2/2.1.3/) (no db)
    | https://github.com/DerrickWood/kraken2 | diff --git a/kleborate/3.1.2/Dockerfile b/kleborate/3.1.2/Dockerfile new file mode 100644 index 000000000..f8911970c --- /dev/null +++ b/kleborate/3.1.2/Dockerfile @@ -0,0 +1,67 @@ +FROM ubuntu:jammy AS app + +# for easy upgrade later. ARG variables only persist during image build time +ARG KLEBORATE_VER="3.1.2" +ARG MINIMAP2_VER="2.28" +ARG MASH_VER="2.3" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="Kleborate" +LABEL software.version="${KLEBORATE_VER}" +LABEL description="tool to screen genome assemblies of Klebsiella pneumoniae and the Klebsiella pneumoniae species complex (KpSC)" +LABEL website="https://github.com/katholt/Kleborate" +LABEL license="https://github.com/katholt/Kleborate/blob/master/LICENSE" +LABEL maintainer="Curtis Kapsak" +LABEL maintainer.email="kapsakcj@gmail.com" +LABEL maintainer2="Frank Ambrosio" +LABEL maintainer2.email="frank.ambrosio@theiagen.com" +LABEL maintainer3="Erin Young" +LABEL maintainer3.email="eriny@utah.gov" + +# install prerequisites. Cleanup apt garbage +RUN apt-get update && apt-get install -y --no-install-recommends \ + python3 \ + python3-pip \ + wget \ + ca-certificates \ + bzip2 \ + procps \ + curl && \ + rm -rf /var/lib/apt/lists/* && apt-get autoclean + +# mash; update UID and GID of mash files; make /data +# UID and GID changes because the original owner is UID: 1081147385 and GID: 1360859114 which does NOT play well with systems that limits GIDs and UIDs +RUN wget -q https://github.com/marbl/Mash/releases/download/v${MASH_VER}/mash-Linux64-v${MASH_VER}.tar && \ + tar -xvf mash-Linux64-v${MASH_VER}.tar --no-same-owner && \ + rm -rf mash-Linux64-v${MASH_VER}.tar && \ + chown root:root /mash-Linux64-v${MASH_VER}/* + +# install minimap2 binary +RUN curl -L https://github.com/lh3/minimap2/releases/download/v${MINIMAP2_VER}/minimap2-${MINIMAP2_VER}_x64-linux.tar.bz2 | \ + tar -jxvf - --no-same-owner + +# set PATH +ENV PATH="/mash-Linux64-v${MASH_VER}:/minimap2-${MINIMAP2_VER}_x64-linux:${PATH}" + +# install kleborate; uninstall mash (that comes with kleborate via pypi, see: https://github.com/klebgenomics/Kleborate/issues/90); make /data +RUN pip install --no-cache-dir kleborate==${KLEBORATE_VER} && \ + pip uninstall mash -y && \ + mkdir /data + +# set working directory +WORKDIR /data + +CMD [ "kleborate", "--help" ] + +FROM app AS test + +WORKDIR /test + +# from https://kleborate.readthedocs.io/en/latest/Installation.html +RUN wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/002/813/595/GCF_002813595.1_ASM281359v1/GCF_002813595.1_ASM281359v1_genomic.fna.gz && \ + kleborate -a GCF_002813595.1_ASM281359v1_genomic.fna.gz -o kleborate_test -p kpsc && \ + head kleborate_test/klebsiella_pneumo_complex_output.txt + +# print help and version info +RUN kleborate --help && kleborate --version && kleborate --list_modules \ No newline at end of file diff --git a/kleborate/3.1.2/README.md b/kleborate/3.1.2/README.md new file mode 100644 index 000000000..e3417f55f --- /dev/null +++ b/kleborate/3.1.2/README.md @@ -0,0 +1,85 @@ +# Kleborate container + +Main tool : [Kleborate](https://github.com/katholt/Kleborate) + +:warning: **Note:** Kleborate v3 is different from v2, please see here for the differences: https://kleborate.readthedocs.io/en/latest/index.html#changes-from-v2 + +Additional tools: + +- [mash](https://github.com/marbl/Mash) version 2.3 +- [minimap2](https://github.com/lh3/minimap2) version 2.28 +- [kaptive](https://github.com/klebgenomics/Kaptive) version 3.0.0b6 +- biopython 1.84 +- dna-features-viewer 3.1.3 +- matplotlib 3.9.2 +- numpy 2.1.3 + +Full documentation: [https://github.com/katholt/Kleborate/wiki](https://github.com/katholt/Kleborate/wiki) + +Description: +> Kleborate is a tool to screen genome assemblies of Klebsiella pneumoniae and the Klebsiella pneumoniae species complex (KpSC) for: +> +> - MLST sequence type +> - species (e.g. K. pneumoniae, K. quasipneumoniae, K. variicola, etc.) +> - ICEKp associated virulence loci: yersiniabactin (ybt), colibactin (clb), salmochelin (iro), hypermucoidy (rmpA) +> - virulence plasmid associated loci: salmochelin (iro), aerobactin (iuc), hypermucoidy (rmpA, rmpA2) +> - antimicrobial resistance determinants: acquired genes, SNPs, gene truncations and intrinsic β-lactamases +> - K (capsule) and O antigen (LPS) serotype prediction, via wzi alleles and Kaptive + +## Included models + +Kleborate has models for both Klebsiella and Escherichia species. The available presets and models are listed below. + +Available presets: kpsc, kosc, escherichia + +``` +Available modules for Kleborate +------------------------------- +enterobacterales__species: Mash-based species detection for enterobacterales species + +escherichia__mlst_achtman: chromosomal MLST for Escherichia coli using the Achtman scheme + +escherichia__mlst_pasteur: chromosomal MLST for Escherichia coli using the Pasteur scheme + +general__contig_stats: basic stats on the assembly's contigs + +klebsiella__abst: MLST on the KpSC aerobactin locus (iuc genes) + +klebsiella__cbst: MLST on the KpSC colibactin locus (clb genes) + +klebsiella__rmpa2: typing for the rmpA2 gene + +klebsiella__rmst: MLST on the KpSC Rmp locus (rmp genes) + +klebsiella__smst: MLST on the KpSC salmochelin locus (iro genes) + +klebsiella__ybst: MLST on the KpSC yersiniabactin locus (ybt and irp genes) + +klebsiella_oxytoca_complex__mlst: chromosomal MLST for the Klebsiella oxytoca species complex + +klebsiella_pneumo_complex__amr: Genotyping acquired genes and mutations for the Klebsiella pneumoniae species complex + +klebsiella_pneumo_complex__kaptive: In silico serotyping of K and L locus for the Klebsiella pneumoniae species complex + +klebsiella_pneumo_complex__mlst: chromosomal MLST for the Klebsiella pneumoniae species complex + +klebsiella_pneumo_complex__resistance_class_count: Resistance gene classes count, excluding the Bla_chr class which is intrinsicresults of the +klebsiella_pneumo_complex__amr module + +klebsiella_pneumo_complex__resistance_gene_count: Resistance genes counts, excluding the Bla class which is intrinsicresults of the +klebsiella_pneumo_complex__amr module + +klebsiella_pneumo_complex__resistance_score: resistance score (0-3) for the Klebsiella pneumoniae species complex, based on the results of the +klebsiella_pneumo_complex__amr module + +klebsiella_pneumo_complex__virulence_score: virulence score (0-5) for the Klebsiella pneumoniae species complex, based on the results of the abst, cbst +and ybst modules + +klebsiella_pneumo_complex__wzi: WZI typing for K antigen prediction +``` + +## Example Usage + +```bash +kleborate -a sample.fasta -o outdir -p preset +``` From eaefbcf5bca9471dadcd56560b6d538ebf3c8c8d Mon Sep 17 00:00:00 2001 From: Young Date: Sat, 9 Nov 2024 10:33:59 -0700 Subject: [PATCH 74/92] adding medaka version 2.0.1 (#1093) * adding medaka version 2.0.1 * minor changes to medaka dockerfile and readme; also updated run-singularity.yml to use a different runner and more importantly apptainer github action to see if it will appropriately test singularity/apptainer functionality --------- Co-authored-by: Curtis Kapsak --- .github/workflows/run-singularity.yml | 10 +- README.md | 2 +- medaka/2.0.1/Dockerfile | 157 ++++++++++++++++++++++++++ medaka/2.0.1/README.md | 35 ++++++ 4 files changed, 198 insertions(+), 6 deletions(-) create mode 100644 medaka/2.0.1/Dockerfile create mode 100644 medaka/2.0.1/README.md diff --git a/.github/workflows/run-singularity.yml b/.github/workflows/run-singularity.yml index 79ff5401f..fe3a5bad9 100644 --- a/.github/workflows/run-singularity.yml +++ b/.github/workflows/run-singularity.yml @@ -20,15 +20,15 @@ on: jobs: build_singularity: - runs-on: ubuntu-20.04 + runs-on: ubuntu-24.04 steps: - name: Check out Repo uses: actions/checkout@v4 - name: Set up Singularity - uses: eWaterCycle/setup-singularity@v7 + uses: eWaterCycle/setup-apptainer@v2 with: - singularity-version: 3.8.3 + apptainer-version: 1.3.5 - - name: Run a singularity container - run: singularity run docker://${{ inputs.repository_name }}/${{ inputs.image_name }} ${{ inputs.command }} + - name: Run a singularity/apptainer container + run: apptainer run docker://${{ inputs.repository_name }}/${{ inputs.image_name }} ${{ inputs.command }} diff --git a/README.md b/README.md index 4dbed681a..23aa8b187 100644 --- a/README.md +++ b/README.md @@ -209,7 +209,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Mash](https://hub.docker.com/r/staphb/mash/)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/mash)](https://hub.docker.com/r/staphb/mash) |
    • 2.1
    • 2.2
    • 2.3
    | https://github.com/marbl/Mash | | [mashtree](https://hub.docker.com/r/staphb/mashtree)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/mashtree)](https://hub.docker.com/r/staphb/mashtree) |
    • [0.52.0](./mashtree/0.52.0/)
    • [0.57.0](./mashtree/0.57.0/)
    • [1.0.4](./mashtree/1.0.4/)
    • [1.2.0](./mashtree/1.2.0/)
    • [1.4.6](./mashtree/1.4.6/)
    | https://github.com/lskatz/mashtree | | [MaSuRCA](https://hub.docker.com/r/staphb/masurca)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/masurca)](https://hub.docker.com/r/staphb/masurca) |
    • 4.0.8
    • 4.0.9
    • 4.1.0
    | https://github.com/alekseyzimin/masurca | -| [medaka](https://hub.docker.com/r/staphb/medaka)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/medaka)](https://hub.docker.com/r/staphb/medaka) |
    • [0.8.1](./medaka/0.8.1/)
    • [1.0.1](./medaka/1.0.1/)
    • [1.2.0](./medaka/1.2.0/)
    • [2.0.0](./medaka/2.0.0/)
    | https://github.com/nanoporetech/medaka | +| [medaka](https://hub.docker.com/r/staphb/medaka)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/medaka)](https://hub.docker.com/r/staphb/medaka) |
    • [0.8.1](./medaka/0.8.1/)
    • [1.0.1](./medaka/1.0.1/)
    • [1.2.0](./medaka/1.2.0/)
    • [2.0.0](./medaka/2.0.0/)
    • [2.0.1](./medaka/2.0.1/)
    | https://github.com/nanoporetech/medaka | | [metaphlan](https://hub.docker.com/r/staphb/metaphlan)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/metaphlan)](https://hub.docker.com/r/staphb/metaphlan) |
    • [3.0.3-no-db (no database)](./metaphlan/3.0.3-no-db/)
    • [3.0.3 (~3GB db)](./metaphlan/3.0.3/)
    • [4.1.0](./metaphlan/4.1.0/) (no database)
    • [4.1.1](./metaphlan/4.1.1/) (no database)
    | https://github.com/biobakery/MetaPhlAn | | [MIDAS](https://hub.docker.com/r/staphb/midas)
    [![docker pulls](https://badgen.net/docker/pulls/staphb/midas)](https://hub.docker.com/r/staphb/midas) |
    • 1.3.2 (no database)
      • | https://github.com/snayfach/MIDAS | | [minimap2](https://hub.docker.com/r/staphb/minimap2)
      [![docker pulls](https://badgen.net/docker/pulls/staphb/minimap2)](https://hub.docker.com/r/staphb/minimap2) |
      • 2.17
      • 2.18
      • 2.21
      • 2.22
      • 2.23
      • 2.24
      • 2.25
      • [2.26](./minimap2/2.26)
      • [2.27](./minimap2/2.27/)
        • li>[2.28](./minimap2/2.28/)
      | https://github.com/lh3/minimap2 | diff --git a/medaka/2.0.1/Dockerfile b/medaka/2.0.1/Dockerfile new file mode 100644 index 000000000..dfd81d91a --- /dev/null +++ b/medaka/2.0.1/Dockerfile @@ -0,0 +1,157 @@ +ARG MEDAKA_VER="2.0.1" +ARG PYABPOA_VER="1.5.3" +ARG SAMTOOLS_VER="1.21" +ARG BCFTOOLS_VER=${SAMTOOLS_VER} +ARG HTSLIB_VER=${SAMTOOLS_VER} +ARG MINIMAP2_VER="2.28" + +FROM ubuntu:jammy AS builder + +ARG SAMTOOLS_VER +ARG BCFTOOLS_VER +ARG HTSLIB_VER +ARG MINIMAP2_VER + +# install dependencies required for compiling samtools +ARG DEBIAN_FRONTEND=noninteractive + +RUN apt-get update && apt-get install --no-install-recommends -y \ + libncurses5-dev \ + libbz2-dev \ + liblzma-dev \ + libcurl4-gnutls-dev \ + zlib1g-dev \ + libssl-dev \ + gcc \ + wget \ + make \ + perl \ + bzip2 \ + gnuplot \ + ca-certificates \ + curl \ + perl \ + bzip2 \ + autoconf \ + automake \ + make \ + gcc \ + libdeflate-dev \ + zlib1g-dev \ + libbz2-dev \ + liblzma-dev \ + libcurl4-gnutls-dev \ + libssl-dev \ + libperl-dev \ + libgsl0-dev \ + libdeflate-dev \ + procps && \ + rm -rf /var/lib/apt/lists/* && apt-get autoclean + +# download, compile, and install bcftools +RUN wget -q https://github.com/samtools/bcftools/releases/download/${BCFTOOLS_VER}/bcftools-${BCFTOOLS_VER}.tar.bz2 && \ + tar -xjf bcftools-${BCFTOOLS_VER}.tar.bz2 && \ + rm -v bcftools-${BCFTOOLS_VER}.tar.bz2 && \ + cd bcftools-${BCFTOOLS_VER} && \ + ./configure --enable-libgsl --enable-perl-filters &&\ + make && \ + make install + +# download, compile, and install samtools +RUN wget -q https://github.com/samtools/samtools/releases/download/${SAMTOOLS_VER}/samtools-${SAMTOOLS_VER}.tar.bz2 && \ + tar -xjf samtools-${SAMTOOLS_VER}.tar.bz2 && \ + cd samtools-${SAMTOOLS_VER} && \ + ./configure && \ + make && \ + make install + +RUN wget -q https://github.com/samtools/htslib/releases/download/${HTSLIB_VER}/htslib-${HTSLIB_VER}.tar.bz2 && \ + tar -xjf htslib-${HTSLIB_VER}.tar.bz2 && \ + rm -v htslib-${HTSLIB_VER}.tar.bz2 && \ + cd htslib-${HTSLIB_VER} && \ + ./configure && \ + make && \ + make install + +RUN curl -L https://github.com/lh3/minimap2/releases/download/v${MINIMAP2_VER}/minimap2-${MINIMAP2_VER}_x64-linux.tar.bz2 | tar -jxvf - --no-same-owner && \ + mv -v minimap2-${MINIMAP2_VER}_x64-linux/minimap2 /usr/local/bin + +### start of app stage ### +FROM ubuntu:jammy AS app + +ARG MEDAKA_VER +ARG PYABPOA_VER + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version=1 +LABEL container.version="1" +LABEL software="Medaka" +LABEL software.version="${MEDAKA_VER}" +LABEL description="Consensus sequence correction provided by ONT Research" +LABEL website="https://github.com/nanoporetech/medaka" +LABEL license="https://github.com/nanoporetech/medaka/blob/master/LICENSE.md" +LABEL maintainer="Curtis Kapsak" +LABEL maintainer.email="kapsakcj@gmail.com" +LABEL maintainer1="Erin Young" +LABEL maintainer1.email="eriny@utah.gov" + +ARG DEBIAN_FRONTEND=noninteractive + +# install dependencies required for running samtools +RUN apt-get update && apt-get install --no-install-recommends -y \ + perl \ + zlib1g \ + libncurses5 \ + bzip2 \ + libdeflate-dev \ + liblzma-dev \ + libcurl4-gnutls-dev \ + python3 \ + python3-pip \ + python-is-python3 \ + python3-dev \ + build-essential \ + libssl-dev \ + libffi-dev \ + libxml2-dev \ + libxslt1-dev \ + zlib1g-dev \ + libgsl-dev \ + && apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# copy in samtools, htslib, and minimap2 executables from builder stage +COPY --from=builder /usr/local/bin/* /usr/local/bin/ + +# install medaka via pip +RUN pip install medaka-cpu==${MEDAKA_VER} --extra-index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \ + pip install pyabpoa==${PYABPOA_VER} --no-cache-dir + +ENV LC_ALL=C + +# final working directory is /data +WORKDIR /data + +# default command is to pull up help options +CMD [ "medaka", "--help" ] + +### start of test stage ### +FROM app AS test + +RUN apt-get update && apt-get install --no-install-recommends -y wget + +# making sure dependencies are in path +RUN samtools --help && minimap2 --help && tabix --help && bgzip --help + +RUN medaka --help && \ + medaka --version + +# set working directory so that all test inputs & outputs are kept in /test +WORKDIR /test + +# using on real data (CRPA isolate) +RUN wget -q https://www.ebi.ac.uk/ena/browser/api/fasta/GCA_021601745.3 -O GCA_021601745.3.fasta && \ + wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR234/068/SRR23473168/SRR23473168_1.fastq.gz && \ + medaka_consensus -i SRR23473168_1.fastq.gz -d GCA_021601745.3.fasta -o testing -t 4 + +# listing available models +RUN medaka tools list\_models diff --git a/medaka/2.0.1/README.md b/medaka/2.0.1/README.md new file mode 100644 index 000000000..c1cf4e82f --- /dev/null +++ b/medaka/2.0.1/README.md @@ -0,0 +1,35 @@ +# Medaka container + +Main tool : [medaka](https://github.com/nanoporetech/medaka) + +Additional tools: + +- bcftools version 1.21 +- samtools version 1.21 +- htslib version 1.21 +- minimap2 version 2.28 +- pyabpoa verson 1.5.3 + +Full documentation: [https://github.com/nanoporetech/medaka](https://github.com/nanoporetech/medaka) + +> medaka is a tool to create consensus sequences and variant calls from nanopore sequencing data. This task is performed using neural networks applied a pileup of individual sequencing reads against a draft assembly. It provides state-of-the-art results outperforming sequence-graph based methods and signal-based methods, whilst also being faster. + +## Example Usage + +```bash +# listing models +medaka tools list\_models + +# polishing +medaka_consensus -i sample.fastq.gz -d sample.fasta -o medaka/sample -t 4 +``` + +## Medaka models + +Medaka updates frequently. These are the medaka models in this image: + +``` +Available: r103_fast_g507, r103_fast_snp_g507, r103_fast_variant_g507, r103_hac_g507, r103_hac_snp_g507, r103_hac_variant_g507, r103_sup_g507, r103_sup_snp_g507, r103_sup_variant_g507, r1041_e82_260bps_fast_g632, r1041_e82_260bps_fast_variant_g632, r1041_e82_260bps_hac_g632, r1041_e82_260bps_hac_v4.0.0, r1041_e82_260bps_hac_v4.1.0, r1041_e82_260bps_hac_variant_g632, r1041_e82_260bps_hac_variant_v4.1.0, r1041_e82_260bps_joint_apk_ulk_v5.0.0, r1041_e82_260bps_sup_g632, r1041_e82_260bps_sup_v4.0.0, r1041_e82_260bps_sup_v4.1.0, r1041_e82_260bps_sup_variant_g632, r1041_e82_260bps_sup_variant_v4.1.0, r1041_e82_400bps_bacterial_methylation, r1041_e82_400bps_fast_g615, r1041_e82_400bps_fast_g632, r1041_e82_400bps_fast_variant_g615, r1041_e82_400bps_fast_variant_g632, r1041_e82_400bps_hac_g615, r1041_e82_400bps_hac_g632, r1041_e82_400bps_hac_v4.0.0, r1041_e82_400bps_hac_v4.1.0, r1041_e82_400bps_hac_v4.2.0, r1041_e82_400bps_hac_v4.3.0, r1041_e82_400bps_hac_v5.0.0, r1041_e82_400bps_hac_variant_g615, r1041_e82_400bps_hac_variant_g632, r1041_e82_400bps_hac_variant_v4.1.0, r1041_e82_400bps_hac_variant_v4.2.0, r1041_e82_400bps_hac_variant_v4.3.0, r1041_e82_400bps_hac_variant_v5.0.0, r1041_e82_400bps_sup_g615, r1041_e82_400bps_sup_v4.0.0, r1041_e82_400bps_sup_v4.1.0, r1041_e82_400bps_sup_v4.2.0, r1041_e82_400bps_sup_v4.3.0, r1041_e82_400bps_sup_v5.0.0, r1041_e82_400bps_sup_variant_g615, r1041_e82_400bps_sup_variant_v4.1.0, r1041_e82_400bps_sup_variant_v4.2.0, r1041_e82_400bps_sup_variant_v4.3.0, r1041_e82_400bps_sup_variant_v5.0.0, r104_e81_fast_g5015, r104_e81_fast_variant_g5015, r104_e81_hac_g5015, r104_e81_hac_variant_g5015, r104_e81_sup_g5015, r104_e81_sup_g610, r104_e81_sup_variant_g610, r941_e81_fast_g514, r941_e81_fast_variant_g514, r941_e81_hac_g514, r941_e81_hac_variant_g514, r941_e81_sup_g514, r941_e81_sup_variant_g514, r941_min_fast_g507, r941_min_fast_snp_g507, r941_min_fast_variant_g507, r941_min_hac_g507, r941_min_hac_snp_g507, r941_min_hac_variant_g507, r941_min_sup_g507, r941_min_sup_snp_g507, r941_min_sup_variant_g507, r941_prom_fast_g507, r941_prom_fast_snp_g507, r941_prom_fast_variant_g507, r941_prom_hac_g507, r941_prom_hac_snp_g507, r941_prom_hac_variant_g507, r941_prom_sup_g507, r941_prom_sup_snp_g507, r941_prom_sup_variant_g507, r941_sup_plant_g610, r941_sup_plant_variant_g610 +Default consensus: r1041_e82_400bps_sup_v5.0.0 +Default variant: r1041_e82_400bps_sup_variant_v5.0.0 +``` From 617039fa8373ccd640ae130ec8d85ad214b03e5c Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Sat, 9 Nov 2024 17:49:42 +0000 Subject: [PATCH 75/92] add reference to publication describing VADR influenza model creation/testing/validation --- vadr/1.6.3-hav-flu2/README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/vadr/1.6.3-hav-flu2/README.md b/vadr/1.6.3-hav-flu2/README.md index 4509a072a..18bacf245 100644 --- a/vadr/1.6.3-hav-flu2/README.md +++ b/vadr/1.6.3-hav-flu2/README.md @@ -22,6 +22,7 @@ Available VADR models: - Dengue virus and other Flaviviridae - RSV v1.5.1-2 - influenza v1.6.3-2 + - More information on this model can be found in the publication describing the creation, testing, and validation here: [https://doi.org/10.1093/database/baae091](https://doi.org/10.1093/database/baae091) Additional VADR models: From a3c8a0adf10f1f5e26ec60b3b7eb7386bebb6d9a Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Sat, 9 Nov 2024 17:56:17 +0000 Subject: [PATCH 76/92] added links to publication describing RGDv2 in readmes for docker iamges that contain the db. closes #824 --- fastani/1.33-RGDv2/README.md | 2 +- fastani/1.34-RGDV2/README.md | 2 +- mummer/4.0.0-RGDv2/README.md | 4 +++- mummer/4.0.0-gnuplot/README.md | 2 +- 4 files changed, 6 insertions(+), 4 deletions(-) diff --git a/fastani/1.33-RGDv2/README.md b/fastani/1.33-RGDv2/README.md index e27a4dbf0..9104ab75a 100644 --- a/fastani/1.33-RGDv2/README.md +++ b/fastani/1.33-RGDv2/README.md @@ -6,7 +6,7 @@ Full documentation: https://github.com/ParBLiSS/FastANI FastANI was developed for fast alignment-free computation of whole-genome Average Nucleotide Identity (ANI). ANI is defined as mean nucleotide identity of orthologous gene pairs shared between two microbial genomes. -This docker image contains the Reference Genome Database version 2 (RGDv2) from the Enteric Diseases Laboratory Branch at the CDC. It contains the genomes of 43 enteric bacterial isolates that are used to for species identification of bacterial isolate WGS data. This database is NOT meant to be comprehensive - it contains the genomes of enteric pathogens commonly sequenced by EDLB and some closely related species. +This docker image contains the Reference Genome Database version 2 (RGDv2) from the Enteric Diseases Laboratory Branch at the CDC. It contains the genomes of 43 enteric bacterial isolates that are used to for species identification of bacterial isolate WGS data. This database is NOT meant to be comprehensive - it contains the genomes of enteric pathogens commonly sequenced by EDLB and some closely related species. Here is the publication describing the database: [https://doi.org/10.3389/fmicb.2023.1225207](https://doi.org/10.3389/fmicb.2023.1225207) The FASTA files for RGDv2 can be found within `/RGDv2/` inside the docker image. diff --git a/fastani/1.34-RGDV2/README.md b/fastani/1.34-RGDV2/README.md index e27a4dbf0..9104ab75a 100644 --- a/fastani/1.34-RGDV2/README.md +++ b/fastani/1.34-RGDV2/README.md @@ -6,7 +6,7 @@ Full documentation: https://github.com/ParBLiSS/FastANI FastANI was developed for fast alignment-free computation of whole-genome Average Nucleotide Identity (ANI). ANI is defined as mean nucleotide identity of orthologous gene pairs shared between two microbial genomes. -This docker image contains the Reference Genome Database version 2 (RGDv2) from the Enteric Diseases Laboratory Branch at the CDC. It contains the genomes of 43 enteric bacterial isolates that are used to for species identification of bacterial isolate WGS data. This database is NOT meant to be comprehensive - it contains the genomes of enteric pathogens commonly sequenced by EDLB and some closely related species. +This docker image contains the Reference Genome Database version 2 (RGDv2) from the Enteric Diseases Laboratory Branch at the CDC. It contains the genomes of 43 enteric bacterial isolates that are used to for species identification of bacterial isolate WGS data. This database is NOT meant to be comprehensive - it contains the genomes of enteric pathogens commonly sequenced by EDLB and some closely related species. Here is the publication describing the database: [https://doi.org/10.3389/fmicb.2023.1225207](https://doi.org/10.3389/fmicb.2023.1225207) The FASTA files for RGDv2 can be found within `/RGDv2/` inside the docker image. diff --git a/mummer/4.0.0-RGDv2/README.md b/mummer/4.0.0-RGDv2/README.md index ff1c03786..9c09e8a3d 100755 --- a/mummer/4.0.0-RGDv2/README.md +++ b/mummer/4.0.0-RGDv2/README.md @@ -1,13 +1,15 @@ # mummer + RGDv2 container + Main tool : [mummer](https://github.com/mummer4/mummer) Additional tools: + - `mash` v2.3 - `ani-m.pl` v0.1 from https://github.com/lskatz/ani-m MUMmer is a versatile alignment tool for DNA and protein sequences. -This docker image contains the **Reference Genome Database version 2 (RGDv2)** from the Enteric Diseases Laboratory Branch at the CDC. It contains the reference genomes of 43 enteric bacterial isolates that are used to for species identification of bacterial isolate WGS data. This database is NOT meant to be comprehensive - it contains the genomes of enteric pathogens commonly sequenced by EDLB and some closely related species. +This docker image contains the **Reference Genome Database version 2 (RGDv2)** from the Enteric Diseases Laboratory Branch at the CDC. It contains the reference genomes of 43 enteric bacterial isolates that are used to for species identification of bacterial isolate WGS data. This database is NOT meant to be comprehensive - it contains the genomes of enteric pathogens commonly sequenced by EDLB and some closely related species. Here is the publication describing the database: [https://doi.org/10.3389/fmicb.2023.1225207](https://doi.org/10.3389/fmicb.2023.1225207) The FASTA files for RGDv2 can be found within the directory `/RGDv2/` inside the docker image. diff --git a/mummer/4.0.0-gnuplot/README.md b/mummer/4.0.0-gnuplot/README.md index 5e5cbab34..58af5c89c 100755 --- a/mummer/4.0.0-gnuplot/README.md +++ b/mummer/4.0.0-gnuplot/README.md @@ -11,7 +11,7 @@ Additional tools: MUMmer is a versatile alignment tool for DNA and protein sequences. -This docker image contains the **Reference Genome Database version 2 (RGDv2)** from the Enteric Diseases Laboratory Branch at the CDC. It contains the reference genomes of 43 enteric bacterial isolates that are used to for species identification of bacterial isolate WGS data. This database is NOT meant to be comprehensive - it contains the genomes of enteric pathogens commonly sequenced by EDLB and some closely related species. +This docker image contains the **Reference Genome Database version 2 (RGDv2)** from the Enteric Diseases Laboratory Branch at the CDC. It contains the reference genomes of 43 enteric bacterial isolates that are used to for species identification of bacterial isolate WGS data. This database is NOT meant to be comprehensive - it contains the genomes of enteric pathogens commonly sequenced by EDLB and some closely related species. Here is the publication describing the database: [https://doi.org/10.3389/fmicb.2023.1225207](https://doi.org/10.3389/fmicb.2023.1225207) The FASTA files for RGDv2 can be found within the directory `/RGDv2/` inside the docker image. From b1f4a42a7850f7dee5d9f2d480ee2bf22c32295f Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Sun, 10 Nov 2024 10:37:04 -0500 Subject: [PATCH 77/92] Update README.md fix markdown bullet --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 23aa8b187..3186a0d1e 100644 --- a/README.md +++ b/README.md @@ -212,7 +212,7 @@ To learn more about the docker pull rate limits and the open source software pro | [medaka](https://hub.docker.com/r/staphb/medaka)
      [![docker pulls](https://badgen.net/docker/pulls/staphb/medaka)](https://hub.docker.com/r/staphb/medaka) |
      • [0.8.1](./medaka/0.8.1/)
      • [1.0.1](./medaka/1.0.1/)
      • [1.2.0](./medaka/1.2.0/)
      • [2.0.0](./medaka/2.0.0/)
      • [2.0.1](./medaka/2.0.1/)
      | https://github.com/nanoporetech/medaka | | [metaphlan](https://hub.docker.com/r/staphb/metaphlan)
      [![docker pulls](https://badgen.net/docker/pulls/staphb/metaphlan)](https://hub.docker.com/r/staphb/metaphlan) |
      • [3.0.3-no-db (no database)](./metaphlan/3.0.3-no-db/)
      • [3.0.3 (~3GB db)](./metaphlan/3.0.3/)
      • [4.1.0](./metaphlan/4.1.0/) (no database)
      • [4.1.1](./metaphlan/4.1.1/) (no database)
      | https://github.com/biobakery/MetaPhlAn | | [MIDAS](https://hub.docker.com/r/staphb/midas)
      [![docker pulls](https://badgen.net/docker/pulls/staphb/midas)](https://hub.docker.com/r/staphb/midas) |
      • 1.3.2 (no database)
        • | https://github.com/snayfach/MIDAS | -| [minimap2](https://hub.docker.com/r/staphb/minimap2)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/minimap2)](https://hub.docker.com/r/staphb/minimap2) |
        • 2.17
        • 2.18
        • 2.21
        • 2.22
        • 2.23
        • 2.24
        • 2.25
        • [2.26](./minimap2/2.26)
        • [2.27](./minimap2/2.27/)
          • li>[2.28](./minimap2/2.28/)
        | https://github.com/lh3/minimap2 | +| [minimap2](https://hub.docker.com/r/staphb/minimap2)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/minimap2)](https://hub.docker.com/r/staphb/minimap2) |
        • 2.17
        • 2.18
        • 2.21
        • 2.22
        • 2.23
        • 2.24
        • 2.25
        • [2.26](./minimap2/2.26)
        • [2.27](./minimap2/2.27/)
        • [2.28](./minimap2/2.28/)
        | https://github.com/lh3/minimap2 | | [minipolish](https://hub.docker.com/r/staphb/minipolish)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/minipolish)](https://hub.docker.com/r/staphb/minipolish) |
        • 0.1.3
        | https://github.com/rrwick/Minipolish | | [mlst](https://hub.docker.com/r/staphb/mlst)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/mlst)](https://hub.docker.com/r/staphb/mlst) |
        • 2.16.2
        • 2.17.6
        • 2.19.0
        • 2.22.0
        • 2.22.1
        • 2.23.0
        • [2.23.0-2023-07 (databases updated July 2023)](mlst/2.23.0-2023-07/)
        • [2.23.0-2023-08 (databases updated Aug 2023)](mlst/2.23.0-2023-08/)
        • [2.23.0-2024-01 (databases updated Jan 2024)](mlst/2.23.0-2024-01/)
        • [2.23.0-2024-03 (databases updated March 2024)](mlst/2.23.0-2024-03/)
        | https://github.com/tseemann/mlst | | [Mugsy](https://hub.docker.com/r/staphb/mugsy)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/mugsy)](https://hub.docker.com/r/staphb/mugsy) |
        • 1r2.3
        | http://mugsy.sourceforge.net/ | From 7c2fe3e7da9c389ddce7c19c3e2c1d52f9fab116 Mon Sep 17 00:00:00 2001 From: Jessica Rowell Date: Tue, 12 Nov 2024 19:26:19 -0500 Subject: [PATCH 78/92] update tostadas container to add table2asn and new environment.yml definition in README --- tostadas/4.0.0/Dockerfile | 72 +++++++++++++++++++++++++++++++++++++++ tostadas/4.0.0/README.md | 42 +++++++++++++++++++++++ 2 files changed, 114 insertions(+) create mode 100644 tostadas/4.0.0/Dockerfile create mode 100644 tostadas/4.0.0/README.md diff --git a/tostadas/4.0.0/Dockerfile b/tostadas/4.0.0/Dockerfile new file mode 100644 index 000000000..81cff5e97 --- /dev/null +++ b/tostadas/4.0.0/Dockerfile @@ -0,0 +1,72 @@ +FROM ubuntu:jammy as app + +ARG TOSTADAS_VER="4.0.0" +ARG TABLE2ASN_RELEASE_DATE="2023-10-05" + +USER root + +WORKDIR / + +LABEL authors="Jessica Rowell and Ankush Gupta" +LABEL base.image="ubuntu:focal" +LABEL dockerfile.version="3" +LABEL software="tostadas" +LABEL software.version=$TOSTADAS_VER +LABEL description="Image for the TOSTADAS: Toolkit for Open Sequence Triage, Annotation and DAtabase Submission pipeline" +LABEL website="https://github.com/CDCgov/tostadas" +LABEL license="https://github.com/CDCgov/tostadas/LICENSE" +LABEL maintainer="Jessica Rowell" +LABEL maintainer.email="jerowell@deloitte.com" +LABEL maintainer2="Kyle O'Connell" +LABEL maintainer2.email="kyoconnell@deloitte.com" + +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + procps && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# download tostadas repo, move to /tostadas, and create /data +RUN wget https://github.com/CDCgov/tostadas/archive/refs/tags/v${TOSTADAS_VER}.tar.gz && \ + tar -xvf v${TOSTADAS_VER}.tar.gz && \ + rm v${TOSTADAS_VER}.tar.gz && \ + mv tostadas-${TOSTADAS_VER} tostadas && \ + mkdir /data + +# use mamba to install conda packages +RUN micromamba env create -f tostadas/environment.yml && \ + micromamba clean -a -y && \ + echo "source activate tostadas" > ~/.bashrc && \ + rm -rf /tostadas + +RUN wget -q https://ftp.ncbi.nlm.nih.gov/asn1-converters/versions/${TABLE2ASN_RELEASE_DATE}/by_program/table2asn/linux64.table2asn.gz && \ + gunzip linux64.table2asn.gz && \ + mv linux64.table2asn table2asn && \ + chmod +x table2asn + +ENV PATH=/opt/conda/envs/tostadas/bin:/opt/conda/envs/env/bin:$PATH \ + LC_ALL=C.UTF-8 + +WORKDIR /data + +##### ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- ##### +###### Step 2. Set up the testing stage. ##### +###### The docker image is built to the 'test' stage before merging, but ##### +###### the test stage (or any stage after 'app') will be lost. ##### +###### ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- ##### + +# A second FROM insruction creates a new stage +FROM app as test +ARG TABLE2ASN_RELEASE_DATE="2023-10-05" + +RUN liftoff --version && \ + samtools --version && \ + python --version && \ + table2asn -help + +ARG FILES="table2asn_readme.txt \ + SubmissionTemplate.sbt \ + short.fsa" + +RUN for file in ${FILES}; do wget -q https://ftp.ncbi.nlm.nih.gov/asn1-converters/versions/${TABLE2ASN_RELEASE_DATE}/documentation/${file}; done && \ + table2asn -t SubmissionTemplate.sbt -i short.fsa -o helicase.sqn \ No newline at end of file diff --git a/tostadas/4.0.0/README.md b/tostadas/4.0.0/README.md new file mode 100644 index 000000000..648d840cd --- /dev/null +++ b/tostadas/4.0.0/README.md @@ -0,0 +1,42 @@ +# tostadas container + +Main tool : [tostadas](https://github.com/CDCgov/tostadas) +Version: 4.0.0 + +Additional tools installed via conda: + - pip + - libgcc-ng=12.1.0=h8d9b700_16 + - libstdcxx-ng=12.1.0=ha89aaad_16 + - liftoff=1.6.3=pyhdfd78af_0 + - lxml=4.9.1=py39hb9d737c_0 + - nameparser=1.0.5=py_0 + - numpy=1.22.4=py39hc58783e_0 + - packaging=21.3=pyhd3eb1b0_0 + - pandas=1.4.2=py39h1832856_2 + - paramiko=3.4.0=pyhd8ed1ab_0 + - python-dateutil=2.8.2=pyhd8ed1ab_0 + - python_abi=3.9=2_cp39 + - pytz=2022.1=pyhd8ed1ab_0 + - pyvcf3=1.0.3=pyhdfd78af_0 + - pyyaml=6.0=py39hb9d737c_4 + - readline=8.1=h46c0cb4_0 + - requests=2.28.0=pyhd8ed1ab_1 + - samtools=1.15.1=h1170115_0 + - setuptools=62.3.2=py39hf3d152e_0 + - simplejson=3.17.6=py39hb9d737c_1 + - tbb=2021.5.0=h924138e_1 + - tbl2asn=25.7=h9ee0642_1 + - tk=8.6.12=h27826a3_0 + - tzdata=2022a=h191b570_0 + - ujson=5.3.0=py39h5a03fae_0 + - urllib3=1.26.9=pyhd8ed1ab_0 + - wgs2ncbi=1.1.2=pl5262hdfd78af_1 + - wheel=0.37.1=pyhd8ed1ab_0 + - xz=5.2.5=h516909a_1 + - yaml=0.2.5=h7f98852_2 + - openpyxl=3.0.10 + - xmltodict=0.13.0=pyhd8ed1ab_0 + +Full documentation: https://github.com/CDCgov/tostadas + +[tostadas](https://github.com/CDCgov/tostadas) is a Nextflow workflow for annotation and submission of MonkeyPox Virus consensus sequences. The resultant container is not intended to run independently of the workflow. From ba84258974b855ae4713ce882eb4f6e682b9cec5 Mon Sep 17 00:00:00 2001 From: Jessica Rowell Date: Tue, 12 Nov 2024 19:35:22 -0500 Subject: [PATCH 79/92] update README version for tostadas --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 3186a0d1e..8849f529d 100644 --- a/README.md +++ b/README.md @@ -300,7 +300,7 @@ To learn more about the docker pull rate limits and the open source software pro | [sylph](https://hub.docker.com/r/staphb/sylph)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/sylph)](https://hub.docker.com/r/staphb/sylph) |
        • [0.4.1](./sylph/0.4.1)
        • [0.5.1](./sylph/0.5.1)
        • [0.6.0](./sylph/0.6.0)
        • [0.6.1](./sylph/0.6.1)
        | https://github.com/bluenote-1577/sylph | | [TBProfiler](https://hub.docker.com/r/staphb/tbprofiler/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/tbprofiler)](https://hub.docker.com/r/staphb/tbprofiler) |
        • [4.3.0](./tbprofiler/4.3.0/)
        • [4.4.0](./tbprofiler/4.4.0/)
        • [4.4.2](./tbprofiler/4.4.2/)
        • [5.0.1](tbprofiler/5.0.1/)
        • [6.2.0](tbprofiler/6.2.0/)
        • [6.2.1](tbprofiler/6.2.1/)
        • [6.3.0](tbprofiler/6.3.0/)
        • [6.4.0](tbprofiler/6.4.0/)
        | https://github.com/jodyphelan/TBProfiler | | [TipToft](https://hub.docker.com/r/staphb/tiptoft/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/tiptoft)](https://hub.docker.com/r/staphb/tiptoft) |
        • 1.0.0
        • 1.0.2
        | https://github.com/andrewjpage/tiptoft | -| [Tostadas](https://hub.docker.com/r/staphb/tostadas/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/tostadas)](https://hub.docker.com/r/staphb/tostadas) |
        • [0.2.0-beta](./tostadas/0.2.0-beta/)
        • [3.1.0](./tostadas/3.1.0/)
        | https://github.com/CDCgov/tostadas | +| [Tostadas](https://hub.docker.com/r/staphb/tostadas/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/tostadas)](https://hub.docker.com/r/staphb/tostadas) |
        • [0.2.0-beta](./tostadas/0.2.0-beta/)
        • [3.1.0](./tostadas/3.1.0/)
        • [4.0.0](./tostadas/4.0.0/)
        | https://github.com/CDCgov/tostadas | | [Treemmer](https://hub.docker.com/r/staphb/treemmer/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/treemmer)](https://hub.docker.com/r/staphb/treemmer) |
        • 0.3
        | https://git.scicore.unibas.ch/TBRU/Treemmer (archived, moved to GitHub)
        https://github.com/fmenardo/Treemmer | | [Trimmomatic](https://hub.docker.com/r/staphb/trimmomatic/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/trimmomatic)](https://hub.docker.com/r/staphb/trimmomatic) |
        • 0.38
        • 0.39
        | http://www.usadellab.org/cms/?page=trimmomatic
        https://github.com/usadellab/Trimmomatic | | [Trycycler](https://hub.docker.com/r/staphb/trycycler/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/trycycler)](https://hub.docker.com/r/staphb/trycycler) |
        • [0.3.1](./trycycler/0.3.1/)
        • [0.3.2](./trycycler/0.3.2/)
        • [0.3.3](./trycycler/0.3.3/)
        • [0.5.0](./trycycler/0.5.0/)
        • [0.5.3](./trycycler/0.5.3/)
        • [0.5.4](./trycycler/0.5.4/)
        • [0.5.5](./trycycler/0.5.5/)
        | https://github.com/rrwick/Trycycler | From 57cfd0a2ec4b86715cc11e5a0723c37f0b4fb318 Mon Sep 17 00:00:00 2001 From: Jessica Rowell Date: Thu, 14 Nov 2024 13:39:28 -0500 Subject: [PATCH 80/92] table2asn was added to environment.yml instead to keep the image lightweight --- tostadas/4.0.0/Dockerfile | 20 +++----------------- 1 file changed, 3 insertions(+), 17 deletions(-) diff --git a/tostadas/4.0.0/Dockerfile b/tostadas/4.0.0/Dockerfile index 81cff5e97..f75416012 100644 --- a/tostadas/4.0.0/Dockerfile +++ b/tostadas/4.0.0/Dockerfile @@ -1,14 +1,13 @@ -FROM ubuntu:jammy as app +FROM mambaorg/micromamba:1.5.8 as app ARG TOSTADAS_VER="4.0.0" -ARG TABLE2ASN_RELEASE_DATE="2023-10-05" USER root WORKDIR / LABEL authors="Jessica Rowell and Ankush Gupta" -LABEL base.image="ubuntu:focal" +LABEL base.image="mambaorg/micromamba:1.5.8" LABEL dockerfile.version="3" LABEL software="tostadas" LABEL software.version=$TOSTADAS_VER @@ -39,11 +38,6 @@ RUN micromamba env create -f tostadas/environment.yml && \ echo "source activate tostadas" > ~/.bashrc && \ rm -rf /tostadas -RUN wget -q https://ftp.ncbi.nlm.nih.gov/asn1-converters/versions/${TABLE2ASN_RELEASE_DATE}/by_program/table2asn/linux64.table2asn.gz && \ - gunzip linux64.table2asn.gz && \ - mv linux64.table2asn table2asn && \ - chmod +x table2asn - ENV PATH=/opt/conda/envs/tostadas/bin:/opt/conda/envs/env/bin:$PATH \ LC_ALL=C.UTF-8 @@ -57,16 +51,8 @@ WORKDIR /data # A second FROM insruction creates a new stage FROM app as test -ARG TABLE2ASN_RELEASE_DATE="2023-10-05" RUN liftoff --version && \ samtools --version && \ python --version && \ - table2asn -help - -ARG FILES="table2asn_readme.txt \ - SubmissionTemplate.sbt \ - short.fsa" - -RUN for file in ${FILES}; do wget -q https://ftp.ncbi.nlm.nih.gov/asn1-converters/versions/${TABLE2ASN_RELEASE_DATE}/documentation/${file}; done && \ - table2asn -t SubmissionTemplate.sbt -i short.fsa -o helicase.sqn \ No newline at end of file + table2asn -help \ No newline at end of file From 9d9f05376673548c92bd9c82b681d4f8845f9657 Mon Sep 17 00:00:00 2001 From: Jessica Rowell Date: Thu, 14 Nov 2024 19:43:19 -0500 Subject: [PATCH 81/92] spelling correction --- tostadas/4.0.0/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tostadas/4.0.0/Dockerfile b/tostadas/4.0.0/Dockerfile index f75416012..fc1d0eb56 100644 --- a/tostadas/4.0.0/Dockerfile +++ b/tostadas/4.0.0/Dockerfile @@ -49,7 +49,7 @@ WORKDIR /data ###### the test stage (or any stage after 'app') will be lost. ##### ###### ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- ##### -# A second FROM insruction creates a new stage +# A second FROM instruction creates a new stage FROM app as test RUN liftoff --version && \ From ab183a55e1edd397662325bfcd1a600af1d02820 Mon Sep 17 00:00:00 2001 From: Jessica Rowell Date: Thu, 14 Nov 2024 19:53:12 -0500 Subject: [PATCH 82/92] Update README to reflect switching tbl2asn for table2asn --- tostadas/4.0.0/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tostadas/4.0.0/README.md b/tostadas/4.0.0/README.md index 648d840cd..518acc1e8 100644 --- a/tostadas/4.0.0/README.md +++ b/tostadas/4.0.0/README.md @@ -24,8 +24,8 @@ Additional tools installed via conda: - samtools=1.15.1=h1170115_0 - setuptools=62.3.2=py39hf3d152e_0 - simplejson=3.17.6=py39hb9d737c_1 + - table2asn=1.28.1179=h48fe88c_0 - tbb=2021.5.0=h924138e_1 - - tbl2asn=25.7=h9ee0642_1 - tk=8.6.12=h27826a3_0 - tzdata=2022a=h191b570_0 - ujson=5.3.0=py39h5a03fae_0 From 9fbf83a64a260ff7f290314dd04bb20e905baec7 Mon Sep 17 00:00:00 2001 From: Young Date: Thu, 14 Nov 2024 18:20:44 -0700 Subject: [PATCH 83/92] Added -f to micromamba clean --- tostadas/4.0.0/Dockerfile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tostadas/4.0.0/Dockerfile b/tostadas/4.0.0/Dockerfile index fc1d0eb56..c7a56b1c7 100644 --- a/tostadas/4.0.0/Dockerfile +++ b/tostadas/4.0.0/Dockerfile @@ -34,7 +34,7 @@ RUN wget https://github.com/CDCgov/tostadas/archive/refs/tags/v${TOSTADAS_VER}.t # use mamba to install conda packages RUN micromamba env create -f tostadas/environment.yml && \ - micromamba clean -a -y && \ + micromamba clean -a -y -f && \ echo "source activate tostadas" > ~/.bashrc && \ rm -rf /tostadas @@ -55,4 +55,4 @@ FROM app as test RUN liftoff --version && \ samtools --version && \ python --version && \ - table2asn -help \ No newline at end of file + table2asn -help From b4cf3002eb129c9c4bd0bc07099d69b55f9ed464 Mon Sep 17 00:00:00 2001 From: Kincekara Date: Tue, 19 Nov 2024 16:17:04 +0000 Subject: [PATCH 84/92] adds quast 5.3.0 --- README.md | 2 +- quast/5.3.0/Dockerfile | 107 +++++++++++++++++++++++++++++++++++++++++ quast/5.3.0/README.md | 36 ++++++++++++++ 3 files changed, 144 insertions(+), 1 deletion(-) create mode 100644 quast/5.3.0/Dockerfile create mode 100644 quast/5.3.0/README.md diff --git a/README.md b/README.md index 3186a0d1e..1639af073 100644 --- a/README.md +++ b/README.md @@ -255,7 +255,7 @@ To learn more about the docker pull rate limits and the open source software pro | [pyGenomeViz](https://hub.docker.com/r/staphb/pygenomeviz/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/pygenomeviz)](https://hub.docker.com/r/staphb/pygenomeviz) |
        • 0.2.2
        • 0.3.2
        • [0.4.2](pygenomeviz/0.4.2/)
        • [0.4.3](pygenomeviz/0.4.3/)
        • [0.4.4](pygenomeviz/0.4.4/)
        • [1.1.0](pygenomeviz/1.1.0/)
        | https://github.com/moshi4/pyGenomeViz | | [pyMLST](https://hub.docker.com/r/staphb/pymlst/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/pymlst)](https://hub.docker.com/r/staphb/pymlst) |
        • [2.1.5](./pymlst/2.1.5/)
        • [2.1.6](./pymlst/2.1.6/)
        | https://github.com/bvalot/pyMLST | | [pypolca](https://hub.docker.com/r/staphb/pypolca/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/pypolca)](https://hub.docker.com/r/staphb/pypolca) |
        • [0.3.1](./pypolca/0.3.1/)
        | https://github.com/gbouras13/pypolca | -| [QUAST](https://hub.docker.com/r/staphb/quast/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/quast)](https://hub.docker.com/r/staphb/quast) |
        • 5.0.0
        • 5.0.2
        • [5.2.0](./quast/5.2.0)
        • [5.2.0-slim](./quast/5.2.0-slim)
        | https://github.com/ablab/quast | +| [QUAST](https://hub.docker.com/r/staphb/quast/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/quast)](https://hub.docker.com/r/staphb/quast) |
        • 5.0.0
        • 5.0.2
        • [5.2.0](./quast/5.2.0)
        • [5.2.0-slim](./quast/5.2.0-slim)
        • [5.3.0](./quast/5.3.0)
        | https://github.com/ablab/quast | | [QuickSNP](https://hub.docker.com/r/staphb/quicksnp/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/quicksnp)](https://hub.docker.com/r/staphb/quicksnp) |
        • 1.0.1
        | https://github.com/k-florek/QuickSNP | | [racon](https://hub.docker.com/r/staphb/racon)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/racon)](https://hub.docker.com/r/staphb/racon)|
        • [1.4.3](./racon/1.4.3/)
        • [1.4.20](./racon/1.4.20/)
        • [1.5.0](./racon/1.5.0/)
        |
      • https://github.com/lbcb-sci/racon
      • https://github.com/isovic/racon (ARCHIVED)
        • | | [rasusa](https://hub.docker.com/r/staphb/rasusa/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/rasusa)](https://hub.docker.com/r/staphb/rasusa) |
        • [0.1.0](./rasusa/0.1.0/)
        • [0.2.0](./rasusa/0.2.0/)
        • [0.3.0](./rasusa/0.3.0/)
        • [0.6.0](./rasusa/0.6.0/)
        • [0.7.0](./rasusa/0.7.0/)
        • [0.8.0](./rasusa/0.8.0/)
        • [2.0.0](./rasusa/2.0.0/)
        • [2.1.0](./rasusa/2.1.0/)
        | https://github.com/mbhall88/rasusa | diff --git a/quast/5.3.0/Dockerfile b/quast/5.3.0/Dockerfile new file mode 100644 index 000000000..e0ac5a569 --- /dev/null +++ b/quast/5.3.0/Dockerfile @@ -0,0 +1,107 @@ +ARG QUAST_VER="5.3.0" + +## Builder ## +FROM ubuntu:focal as builder + +ARG QUAST_VER + +# define timezone to avoid build stalls +ENV TZ=America/New_York +RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone + +RUN apt-get update && apt-get install --no-install-recommends -y \ + wget \ + python2 \ + perl \ + cpanminus \ + g++ \ + make \ + openjdk-8-jre-headless \ + r-base \ + pkg-config \ + libfreetype6-dev \ + libpng-dev \ + libboost-all-dev \ + locales &&\ + locale-gen en_US.UTF-8 &&\ + cpanm Time::HiRes &&\ + apt-get autoclean &&\ + rm -rf /var/lib/apt/lists/* + +# python dependencies +RUN update-alternatives --install /usr/bin/python python /usr/bin/python2 1 &&\ + wget https://bootstrap.pypa.io/pip/2.7/get-pip.py && python get-pip.py &&\ + pip install --no-cache matplotlib simplejson joblib + +# install quast +RUN wget https://github.com/ablab/quast/releases/download/quast_${QUAST_VER}/quast-${QUAST_VER}.tar.gz && \ + tar -xzf quast-${QUAST_VER}.tar.gz && \ + rm -rf quast-${QUAST_VER}.tar.gz && \ + cd /quast-${QUAST_VER} && \ + ./setup.py install + +# add GRIDSS for SV detection +ADD https://github.com/ablab/quast/raw/master/external_tools/gridss/gridss-1.4.1.jar /quast-${QUAST_VER}/quast_libs/gridss/ + +## App ## +FROM ubuntu:jammy as app + +ARG QUAST_VER + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="QUAST" +LABEL software.version=${QUAST_VER} +LABEL description="Genome assembly evaluation tool" +LABEL website="https://github.com/ablab/quast" +LABEL license="https://github.com/ablab/quast/blob/master/LICENSE.txt" +LABEL maintainer="Curtis Kapsak" +LABEL maintainer.email="pjx8@cdc.gov" +LABEL maintainer2="Kutluhan Incekara" +LABEL maintainer2.email="kutluhan.incekara@ct.gov" + +# define timezone to avoid build stalls +ENV TZ=America/New_York +RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone + +# install only necessary programs and libraries to run quast +RUN apt-get update && apt-get install --no-install-recommends -y \ + wget \ + python3 \ + python3-matplotlib \ + perl \ + openjdk-8-jre-headless \ + r-base \ + libidn12 \ + locales &&\ + locale-gen en_US.UTF-8 &&\ + apt-get autoclean &&\ + rm -rf /var/lib/apt/lists/* &&\ + update-alternatives --install /usr/bin/python python /usr/bin/python3 1 &&\ + ln -s /usr/lib/x86_64-linux-gnu/libidn.so.12 /usr/lib/x86_64-linux-gnu/libidn.so.11 + +# copy quast and compiled tools +COPY --from=builder /quast-${QUAST_VER} /quast-${QUAST_VER} + +ENV LC_ALL=C \ + PATH=$PATH:/quast-${QUAST_VER} + +CMD quast.py --help && quast-lg.py --help && metaquast.py --help + +WORKDIR /data + +## Test ## +FROM app as test +# test quast +RUN quast.py --test-sv && mv ./quast_test_output/ ./quast_test_sv_output/ +# test quast-lg +RUN quast-lg.py --test && mv ./quast_test_output/ ./quast_test_lg_output/ +# test metaquast +RUN metaquast.py --test-no-ref +# check logs +RUN tail -n5 ./quast_test_sv_output/quast.log &&\ + tail -n5 ./quast_test_lg_output/quast.log &&\ + tail -n5 ./quast_test_output/metaquast.log + +# Note: libidn is required for makeblastdb. libidn.so.11 symlink is a temporary patch for this version. + diff --git a/quast/5.3.0/README.md b/quast/5.3.0/README.md new file mode 100644 index 000000000..0de330a33 --- /dev/null +++ b/quast/5.3.0/README.md @@ -0,0 +1,36 @@ +# QUAST container + +Main tool: [QUAST](https://github.com/ablab/quast) + +Code repository: https://github.com/ablab/quast + +Additional tools: +- gridss: 1.4.1 + + +Basic information on how to use this tool: +- executable: quast.py +- help: --help +- version: --version +- description: Genome assembly evaluation tool + +Additional information: + +You may need a license key if you want to use GeneMark with Quast!
        +This key can be downloaded from http://exon.gatech.edu/GeneMark/license_download.cgi page (GeneMark is free for non-commercial use). +You should choose GeneMarkS-T LINUX 64. Download your license key and add it to your data folder or another folder you will bind to the container. Inside the container, copy the key to your home folder. +``` +cp /data/gm_key_64 ~/.gm_key +``` +Full documentation: https://quast.sourceforge.net/docs/manual.html + +## Example Usage + +```bash +# basic statistics without reference +quast.py contigs.fasta +# genome evaluation with reference +quast.py contigs.fasta -r reference.fasta.gz -g genes.gff +# metagenomic assemblies +metaquast.py contigs_1 contigs_2 ... -r reference_1,reference_2,reference_3,... +``` \ No newline at end of file From 020e27d87d5d776ba94cbe6df21704a96fd4134b Mon Sep 17 00:00:00 2001 From: Kincekara Date: Tue, 19 Nov 2024 19:12:24 +0000 Subject: [PATCH 85/92] adds quast 5.3.0-slim --- README.md | 2 +- quast/5.3.0-slim/Dockerfile | 45 +++++++++++++++++++++++++++++++++++++ quast/5.3.0-slim/README.md | 31 +++++++++++++++++++++++++ 3 files changed, 77 insertions(+), 1 deletion(-) create mode 100644 quast/5.3.0-slim/Dockerfile create mode 100644 quast/5.3.0-slim/README.md diff --git a/README.md b/README.md index 3186a0d1e..42b140559 100644 --- a/README.md +++ b/README.md @@ -255,7 +255,7 @@ To learn more about the docker pull rate limits and the open source software pro | [pyGenomeViz](https://hub.docker.com/r/staphb/pygenomeviz/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/pygenomeviz)](https://hub.docker.com/r/staphb/pygenomeviz) |
        • 0.2.2
        • 0.3.2
        • [0.4.2](pygenomeviz/0.4.2/)
        • [0.4.3](pygenomeviz/0.4.3/)
        • [0.4.4](pygenomeviz/0.4.4/)
        • [1.1.0](pygenomeviz/1.1.0/)
        | https://github.com/moshi4/pyGenomeViz | | [pyMLST](https://hub.docker.com/r/staphb/pymlst/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/pymlst)](https://hub.docker.com/r/staphb/pymlst) |
        • [2.1.5](./pymlst/2.1.5/)
        • [2.1.6](./pymlst/2.1.6/)
        | https://github.com/bvalot/pyMLST | | [pypolca](https://hub.docker.com/r/staphb/pypolca/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/pypolca)](https://hub.docker.com/r/staphb/pypolca) |
        • [0.3.1](./pypolca/0.3.1/)
        | https://github.com/gbouras13/pypolca | -| [QUAST](https://hub.docker.com/r/staphb/quast/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/quast)](https://hub.docker.com/r/staphb/quast) |
        • 5.0.0
        • 5.0.2
        • [5.2.0](./quast/5.2.0)
        • [5.2.0-slim](./quast/5.2.0-slim)
        | https://github.com/ablab/quast | +| [QUAST](https://hub.docker.com/r/staphb/quast/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/quast)](https://hub.docker.com/r/staphb/quast) |
        • 5.0.0
        • 5.0.2
        • [5.2.0](./quast/5.2.0)
        • [5.2.0-slim](./quast/5.2.0-slim)
        • [5.3.0](./quast/5.3.0)
        • [5.3.0-slim](./quast/5.3.0-slim)
        | https://github.com/ablab/quast | | [QuickSNP](https://hub.docker.com/r/staphb/quicksnp/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/quicksnp)](https://hub.docker.com/r/staphb/quicksnp) |
        • 1.0.1
        | https://github.com/k-florek/QuickSNP | | [racon](https://hub.docker.com/r/staphb/racon)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/racon)](https://hub.docker.com/r/staphb/racon)|
        • [1.4.3](./racon/1.4.3/)
        • [1.4.20](./racon/1.4.20/)
        • [1.5.0](./racon/1.5.0/)
        |
      • https://github.com/lbcb-sci/racon
      • https://github.com/isovic/racon (ARCHIVED)
        • | | [rasusa](https://hub.docker.com/r/staphb/rasusa/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/rasusa)](https://hub.docker.com/r/staphb/rasusa) |
        • [0.1.0](./rasusa/0.1.0/)
        • [0.2.0](./rasusa/0.2.0/)
        • [0.3.0](./rasusa/0.3.0/)
        • [0.6.0](./rasusa/0.6.0/)
        • [0.7.0](./rasusa/0.7.0/)
        • [0.8.0](./rasusa/0.8.0/)
        • [2.0.0](./rasusa/2.0.0/)
        • [2.1.0](./rasusa/2.1.0/)
        | https://github.com/mbhall88/rasusa | diff --git a/quast/5.3.0-slim/Dockerfile b/quast/5.3.0-slim/Dockerfile new file mode 100644 index 000000000..547ad84fc --- /dev/null +++ b/quast/5.3.0-slim/Dockerfile @@ -0,0 +1,45 @@ +FROM ubuntu:jammy as app + +ARG QUAST_VER="5.3.0" +ARG MINIMAP2_VER="2.28" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="QUAST" +LABEL software.version=${QUAST_VER} +LABEL description="Genome assembly evaluation tool" +LABEL website="https://github.com/ablab/quast" +LABEL license="https://github.com/ablab/quast/blob/master/LICENSE.txt" +LABEL maintainer="Kutluhan Incekara" +LABEL maintainer.email="kutluhan.incekara@ct.gov" + +RUN apt-get update && apt-get install --no-install-recommends -y \ + wget \ + bzip2 \ + python-is-python3 \ + locales &&\ + locale-gen en_US.UTF-8 &&\ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +RUN wget --no-check-certificate https://github.com/lh3/minimap2/releases/download/v${MINIMAP2_VER}/minimap2-${MINIMAP2_VER}_x64-linux.tar.bz2 &&\ + tar --no-same-owner -jxvf minimap2-${MINIMAP2_VER}_x64-linux.tar.bz2 && rm minimap2-${MINIMAP2_VER}_x64-linux.tar.bz2 &&\ + wget --no-check-certificate https://github.com/ablab/quast/releases/download/quast_${QUAST_VER}/quast-${QUAST_VER}.tar.gz &&\ + tar -xvf quast-${QUAST_VER}.tar.gz && rm quast-${QUAST_VER}.tar.gz + +ENV PATH=$PATH:/quast-${QUAST_VER}:/minimap2-${MINIMAP2_VER}_x64-linux/ \ + LC_ALL=C + +CMD quast.py --help && quast-lg.py --help && metaquast.py --help + +WORKDIR /data + +## Test ## +FROM app as test + +ARG QUAST_VER +ARG DPATH="/quast-${QUAST_VER}/test_data" + +# test quast +RUN quast.py ${DPATH}/contigs_1.fasta ${DPATH}/contigs_2.fasta -r ${DPATH}/reference.fasta.gz -o quast_out +# test metaquast +RUN metaquast.py ${DPATH}/meta_contigs_1.fasta ${DPATH}/meta_contigs_2.fasta -r ${DPATH}/meta_ref_1.fasta,${DPATH}/meta_ref_2.fasta,${DPATH}/meta_ref_3.fasta -o metaquast_out diff --git a/quast/5.3.0-slim/README.md b/quast/5.3.0-slim/README.md new file mode 100644 index 000000000..61db315cf --- /dev/null +++ b/quast/5.3.0-slim/README.md @@ -0,0 +1,31 @@ +# QUAST slim container + +Main tool: [QUAST](https://github.com/ablab/quast) + +Code repository: https://github.com/ablab/quast + +Additional tools: +- minimap2 2.28-r1209 + +Basic information on how to use this tool: +- executable: quast.py +- help: --help +- version: --version +- description: Genome assembly evaluation tool + +Additional information: + +This image provides minimal requirements of QUAST. Some of the functions may not work. Please use **staphb/quast:5.3.0** for the full functionality of the program. + +Full documentation: https://quast.sourceforge.net/docs/manual.html + +## Example Usage + +```bash +# basic statistics without reference +quast.py contigs.fasta +# genome evaluation with reference +quast.py contigs.fasta -r reference.fasta.gz +# metagenomic assemblies +metaquast.py contigs_1 contigs_2 ... -r reference_1,reference_2,reference_3,... +``` \ No newline at end of file From 60e4994974472e7cc9bab175333448b46bda840f Mon Sep 17 00:00:00 2001 From: Young Date: Tue, 19 Nov 2024 13:32:53 -0700 Subject: [PATCH 86/92] adding datasets version 16.35.0 (#1103) * adding datasets version 16.35.0 * Update README.md Fix merge issues --------- Co-authored-by: Kutluhan Incekara <46578029+Kincekara@users.noreply.github.com> --- README.md | 2 +- ncbi-datasets/16.35.0/Dockerfile | 46 ++++++++++++++++++++++++++++++++ ncbi-datasets/16.35.0/README.md | 20 ++++++++++++++ 3 files changed, 67 insertions(+), 1 deletion(-) create mode 100644 ncbi-datasets/16.35.0/Dockerfile create mode 100644 ncbi-datasets/16.35.0/README.md diff --git a/README.md b/README.md index 8849f529d..0d533d3d6 100644 --- a/README.md +++ b/README.md @@ -221,7 +221,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Mykrobe + Genotyphi + sonneityping](https://hub.docker.com/r/staphb/mykrobe)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/mykrobe)](https://hub.docker.com/r/staphb/mykrobe) |
        • 0.11.0 (Mykrobe) & 1.9.1 (Genotyphi)
        • 0.12.1 (Mykrobe) & 1.9.1 (Genotyphi) & v20210201 (sonneityping)
        • 0.12.1 (Mykrobe) & 2.0 (Genotyphi) & v20210201 (sonneityping)
        • [0.12.2 (Mykrobe) & 2.0 (Genotyphi) & v20210201 (sonneityping)](mykrobe/0.12.2/)
        • [0.13.0](./mykrobe/0.13.0)
        | https://github.com/Mykrobe-tools/mykrobe
        https://github.com/typhoidgenomics/genotyphi
        https://github.com/katholt/sonneityping | | [NanoPlot](https://hub.docker.com/r/staphb/nanoplot)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/nanoplot)](https://hub.docker.com/r/staphb/nanoplot) |
        • [1.27.0](./nanoplot/1.27.0/)
        • [1.29.0](./nanoplot/1.29.0/)
        • [1.30.1](./nanoplot/1.30.1/)
        • [1.32.0](./nanoplot/1.32.0/)
        • [1.33.0](./nanoplot/1.33.0/)
        • [1.40.0](./nanoplot/1.40.0/)
        • [1.41.6](./nanoplot/1.41.6/)
        • [1.42.0](./nanoplot/1.42.0/)
        | https://github.com/wdecoster/NanoPlot | | [ngmaster](https://hub.docker.com/r/staphb/ngmaster)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/ngmaster)](https://hub.docker.com/r/staphb/ngmaster) |
        • 0.5.8
        • 1.0.0
        | https://github.com/MDU-PHL/ngmaster | -| [NCBI Datasets](https://hub.docker.com/r/staphb/ncbi-datasets)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/ncbi-datasets)](https://hub.docker.com/r/staphb/ncbi-datasets) |
        Click to see all datasets versions **datasets versions**
        • [13.31.0](./ncbi-datasets/13.31.0/)
        • [13.35.0](./ncbi-datasets/13.35.0/)
        • [13.43.2](./ncbi-datasets/13.43.2/)
        • [14.0.0](./ncbi-datasets/14.0.0/)
        • [14.3.0](./ncbi-datasets/14.3.0/)
        • [14.7.0](./ncbi-datasets/14.7.0/)
        • [14.13.2](./ncbi-datasets/14.13.2/)
        • [14.20.0](./ncbi-datasets/14.20.0/)
        • [14.27.0](ncbi-datasets/14.27.0/)
        • [15.1.0](ncbi-datasets/15.1.0/)
        • [15.2.0](ncbi-datasets/15.2.0/)
        • [15.11.0](ncbi-datasets/15.11.0/)
        • [15.27.1](ncbi-datasets/15.27.1/)
        • [15.31.0](ncbi-datasets/15.31.1/)
        • [16.2.0](ncbi-datasets/16.2.0/)
        • [16.8.1](./ncbi-datasets/16.8.1/)
        • [16.10.3](./ncbi-datasets/16.10.3/)
        • [16.15.0](./ncbi-datasets/16.15.0/)
        • [16.22.1](./ncbi-datasets/16.22.1/)
        • [16.30.0](./ncbi-datasets/16.30.0/)
        | [https://github.com/ncbi/datasets](https://github.com/ncbi/datasets)
        [https://www.ncbi.nlm.nih.gov/datasets/docs/v1/](https://www.ncbi.nlm.nih.gov/datasets/docs/v1/) | +| [NCBI Datasets](https://hub.docker.com/r/staphb/ncbi-datasets)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/ncbi-datasets)](https://hub.docker.com/r/staphb/ncbi-datasets) |
        Click to see all datasets versions **datasets versions**
        • [13.31.0](./ncbi-datasets/13.31.0/)
        • [13.35.0](./ncbi-datasets/13.35.0/)
        • [13.43.2](./ncbi-datasets/13.43.2/)
        • [14.0.0](./ncbi-datasets/14.0.0/)
        • [14.3.0](./ncbi-datasets/14.3.0/)
        • [14.7.0](./ncbi-datasets/14.7.0/)
        • [14.13.2](./ncbi-datasets/14.13.2/)
        • [14.20.0](./ncbi-datasets/14.20.0/)
        • [14.27.0](ncbi-datasets/14.27.0/)
        • [15.1.0](ncbi-datasets/15.1.0/)
        • [15.2.0](ncbi-datasets/15.2.0/)
        • [15.11.0](ncbi-datasets/15.11.0/)
        • [15.27.1](ncbi-datasets/15.27.1/)
        • [15.31.0](ncbi-datasets/15.31.1/)
        • [16.2.0](ncbi-datasets/16.2.0/)
        • [16.8.1](./ncbi-datasets/16.8.1/)
        • [16.10.3](./ncbi-datasets/16.10.3/)
        • [16.15.0](./ncbi-datasets/16.15.0/)
        • [16.22.1](./ncbi-datasets/16.22.1/)
        • [16.30.0](./ncbi-datasets/16.30.0/)
        • [16.35.0](ncbi-datasets/16.35.0/)
        | [https://github.com/ncbi/datasets](https://github.com/ncbi/datasets)
        [https://www.ncbi.nlm.nih.gov/datasets/docs/v1/](https://www.ncbi.nlm.nih.gov/datasets/docs/v1/) | | [NCBI AMRFinderPlus](https://hub.docker.com/r/staphb/ncbi-amrfinderplus)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/ncbi-amrfinderplus)](https://hub.docker.com/r/staphb/ncbi-amrfinderplus) | **AMRFinderPlus & database verion**
        Click to see AMRFinderplus v3.11.4 and older versions!
        • 3.1.1b
        • 3.8.4
        • 3.8.28
        • 3.9.3
        • 3.9.8
        • 3.10.1
        • 3.10.5
        • 3.10.16
        • 3.10.20
        • 3.10.24
        • 3.10.30
        • 3.10.36
        • 3.10.42
        • 3.11.2 & 2022-12-19.1
        • [3.11.2 & 2023-02-23.1](ncbi-amrfinderplus/3.11.2-2023-02-23.1/)
        • [3.11.4 & 2023-02-23.1](ncbi-amrfinderplus/3.11.4-2023-02-23.1/)
        • [3.11.8 & 2023-02-23.1](ncbi-amrfinderplus/3.11.8-2023-02-23.1/)
        • [3.11.11 & 2023-04-17.1](ncbi-amrfinderplus/3.11.11-2023-04-17.1)
        • [3.11.14 & 2023-04-17.1](ncbi-amrfinderplus/3.11.14-2023-04-17.1/)
        • [3.11.17 & 2023-07-13.2](ncbi-amrfinderplus/3.11.17-2023-07-13.2/)
        • [3.11.18 & 2023-08-08.2](ncbi-amrfinderplus/3.11.18-2023-08-08.2/)
        • [3.11.20 & 2023-09-26.1](ncbi-amrfinderplus/3.11.20-2023-09-26.1/)
        • [3.11.26 & 2023-11-15.1](ncbi-amrfinderplus/3.11.26-2023-11-15.1/)
        • [3.12.8 & 2024-01-31.1](ncbi-amrfinderplus/3.12.8-2024-01-31.1/)
        • [3.12.8 & 2024-05-02.2](./ncbi-amrfinderplus/3.12.8-2024-05-02.2/)
        • [3.12.8 & 2024-07-22.1](./ncbi-amrfinderplus/3.12.8-2024-07-22.1/)
        • [4.0.3 & 2024-10-22.1 (includes stxtyper)](./ncbi-amrfinderplus/4.0.3-2024-10-22.1/)
        | [https://github.com/ncbi/amr](https://github.com/ncbi/amr) | | [NCBI table2asn](https://hub.docker.com/r/staphb/ncbi-table2asn)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/ncbi-table2asn)](https://hub.docker.com/r/staphb/ncbi-table2asn) |
        • [1.26.678](./ncbi-table2asn/1.26.678/)
        • [1.28.943](./ncbi-table2asn/1.28.943/)
        • [1.28.1021](./ncbi-table2asn/1021/)
        | [https://www.ncbi.nlm.nih.gov/genbank/table2asn/](https://www.ncbi.nlm.nih.gov/genbank/table2asn/)
        [https://ftp.ncbi.nlm.nih.gov/asn1-converters/versions/2022-06-14/by_program/table2asn/](https://ftp.ncbi.nlm.nih.gov/asn1-converters/versions/2022-06-14/by_program/table2asn/) | | [ONTime](https://hub.docker.com/r/staphb/ontime)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/ontime)](https://hub.docker.com/r/staphb/ontime) |
        • [0.2.3](ontime/0.2.3/)
        • [0.3.1](ontime/0.3.1/)
        | https://github.com/mbhall88/ontime | diff --git a/ncbi-datasets/16.35.0/Dockerfile b/ncbi-datasets/16.35.0/Dockerfile new file mode 100644 index 000000000..024e4d6cd --- /dev/null +++ b/ncbi-datasets/16.35.0/Dockerfile @@ -0,0 +1,46 @@ +FROM ubuntu:jammy as app + +ARG DATASETS_VER="16.35.0" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="NCBI's datasets and dataformat" +LABEL software.version="${DATASETS_VER}" +LABEL description="Downloads biological sequence data from NCBI" +LABEL website="https://www.ncbi.nlm.nih.gov/datasets/docs/v1/" +LABEL license="https://github.com/ncbi/datasets/blob/master/pkgs/ncbi-datasets-cli/LICENSE.md" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" + +# unzip isn't needed for datasets/dataformat, but it is often used after downloading files with datasets +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + unzip && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +WORKDIR /usr/local/bin + +# install ncbi datasets tool (pre-compiled binary) +RUN wget https://github.com/ncbi/datasets/releases/download/v${DATASETS_VER}/linux-amd64.cli.package.zip && \ + unzip linux-amd64.cli.package.zip && \ + rm linux-amd64.cli.package.zip && \ + chmod +x dataformat datasets + +ENV LC_ALL=C + +WORKDIR /data + +# datasets is generally datasets --help, but just typing in 'datasets' should bring up a help menu +CMD [ "datasets" ] + +FROM app as test + +RUN dataformat --help && datasets --help + +# stolen from Curtis at https://github.com/StaPH-B/docker-builds/blob/master/pangolin/4.1.2/Dockerfile +RUN datasets download virus genome accession ON924087.1 --filename ON924087.1.zip && \ + unzip ON924087.1.zip && \ + rm ON924087.1.zip && \ + cp ncbi_dataset/data/genomic.fna ON924087.1.fna && \ + wc -c ON924087.1.fna diff --git a/ncbi-datasets/16.35.0/README.md b/ncbi-datasets/16.35.0/README.md new file mode 100644 index 000000000..6474b9282 --- /dev/null +++ b/ncbi-datasets/16.35.0/README.md @@ -0,0 +1,20 @@ +# NCBI datasets and dataformat container + +Main tool : [datasets](https://www.ncbi.nlm.nih.gov/datasets/docs/v1/download-and-install/#use-the-datasets-tool-to-download-biological-data) and [dataformat](https://www.ncbi.nlm.nih.gov/datasets/docs/v1/download-and-install/#use-the-dataformat-tool-to-convert-data-reports-to-other-formats) + +Full documentation: [https://www.ncbi.nlm.nih.gov/datasets/docs/v1/how-tos/](https://www.ncbi.nlm.nih.gov/datasets/docs/v1/how-tos/) + +> Use NCBI Datasets to gather metadata, download data packages, view reports and more + +## Example Usage + +```bash +# will download the fasta for ON924087.1 in a zipped directory +datasets download virus genome accession ON924087.1 --filename ON924087.1.zip + +# unzipping the directory and the fasta file will be located at ncbi_dataset/data/genomic.fna +unzip ON924087.1.zip + +# copying the file into something with a better name +cp ncbi_dataset/data/genomic.fna ncbi_dataset/data/ON924087.1.genomic.fna +``` From bf04981dd4c99b43889857d32d4ccf553cec6d6a Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Tue, 19 Nov 2024 15:37:17 -0500 Subject: [PATCH 87/92] adds stxtyper 1.0.27 dockerfile & readme; updates main readme with links (#1104) --- README.md | 2 +- stxtyper/1.0.27/Dockerfile | 55 ++++++++++++++++++++++++++++++++++++++ stxtyper/1.0.27/README.md | 29 ++++++++++++++++++++ 3 files changed, 85 insertions(+), 1 deletion(-) create mode 100644 stxtyper/1.0.27/Dockerfile create mode 100644 stxtyper/1.0.27/README.md diff --git a/README.md b/README.md index 0d533d3d6..95b9b54cf 100644 --- a/README.md +++ b/README.md @@ -296,7 +296,7 @@ To learn more about the docker pull rate limits and the open source software pro | [SRA-toolkit](https://hub.docker.com/r/staphb/sratoolkit/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/sratoolkit)](https://hub.docker.com/r/staphb/sratoolkit) |
        • 2.9.2
        • [3.0.7](./sratoolkit/3.0.7/)
        | https://github.com/ncbi/sra-tools | | [SRST2](https://hub.docker.com/r/staphb/srst2/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/srst2)](https://hub.docker.com/r/staphb/srst2) |
        • 0.2.0
        • [0.2.0 + custom Vibrio cholerae database](srst2/0.2.0-vibrio-230224/README.md)
        | https://github.com/katholt/srst2 | | [Staramr](https://hub.docker.com/r/staphb/staramr/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/staramr)](https://hub.docker.com/r/staphb/staramr) |
        • [0.5.1](./staramr/0.5.1/)
        • [0.7.1](./staramr/0.7.1/)
        • [0.8.0](./staramr/0.8.0/)
        • [0.10.0](./staramr/0.10.0/)
        | https://github.com/phac-nml/staramr | -| [stxtyper](https://hub.docker.com/r/staphb/stxtyper)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/stxtyper)](https://hub.docker.com/r/staphb/stxtyper) |
        • [1.0.24](stxtyper/1.0.24)
        | https://github.com/ncbi/stxtyper | +| [stxtyper](https://hub.docker.com/r/staphb/stxtyper)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/stxtyper)](https://hub.docker.com/r/staphb/stxtyper) |
        • [1.0.24](stxtyper/1.0.24/)
        • [1.0.27](stxtyper/1.0.27/)
        | https://github.com/ncbi/stxtyper | | [sylph](https://hub.docker.com/r/staphb/sylph)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/sylph)](https://hub.docker.com/r/staphb/sylph) |
        • [0.4.1](./sylph/0.4.1)
        • [0.5.1](./sylph/0.5.1)
        • [0.6.0](./sylph/0.6.0)
        • [0.6.1](./sylph/0.6.1)
        | https://github.com/bluenote-1577/sylph | | [TBProfiler](https://hub.docker.com/r/staphb/tbprofiler/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/tbprofiler)](https://hub.docker.com/r/staphb/tbprofiler) |
        • [4.3.0](./tbprofiler/4.3.0/)
        • [4.4.0](./tbprofiler/4.4.0/)
        • [4.4.2](./tbprofiler/4.4.2/)
        • [5.0.1](tbprofiler/5.0.1/)
        • [6.2.0](tbprofiler/6.2.0/)
        • [6.2.1](tbprofiler/6.2.1/)
        • [6.3.0](tbprofiler/6.3.0/)
        • [6.4.0](tbprofiler/6.4.0/)
        | https://github.com/jodyphelan/TBProfiler | | [TipToft](https://hub.docker.com/r/staphb/tiptoft/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/tiptoft)](https://hub.docker.com/r/staphb/tiptoft) |
        • 1.0.0
        • 1.0.2
        | https://github.com/andrewjpage/tiptoft | diff --git a/stxtyper/1.0.27/Dockerfile b/stxtyper/1.0.27/Dockerfile new file mode 100644 index 000000000..680dbae12 --- /dev/null +++ b/stxtyper/1.0.27/Dockerfile @@ -0,0 +1,55 @@ +FROM ubuntu:jammy AS app + +ARG STXTYPER_VER="1.0.27" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="stxtyper" +LABEL software.version="${STXTYPER_VER}" +LABEL description="Search for Shiga toxin genes within bacterial genome assemblies" +LABEL website="https://github.com/ncbi/stxtyper" +LABEL license="https://github.com/ncbi/stxtyper/blob/main/LICENSE" +LABEL maintainer="Curtis Kapsak" +LABEL maintainer.email="kapsakcj@gmail.com" + +# install dependencies via apt; cleanup apt garbage +# blast from ubuntu:jammy is v2.12.0 (as of 2024-09-06) +# procps is for ps command (required for nextflow) +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + ncbi-blast+ \ + procps && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# download pre-compiled binary +RUN mkdir /stxtyper && \ +wget -q https://github.com/ncbi/stxtyper/releases/download/v${STXTYPER_VER}/stxtyper_v${STXTYPER_VER}_x86_64_Linux.tar.gz && \ +tar -xzf stxtyper_v${STXTYPER_VER}_x86_64_Linux.tar.gz --strip-components=1 -C /stxtyper && \ +rm -r stxtyper_v${STXTYPER_VER}_x86_64_Linux.tar.gz && \ +ls -lh /stxtyper + +# set PATH to include where stxtyper & fasta_check executables exist +ENV PATH="${PATH}:/stxtyper" \ +TERM=xterm-256color + +# set final working directory as /data for passing data in/out of container +WORKDIR /data + +FROM app AS test + +# print version and help options & run the supplied tests +RUN tblastn -version && \ +stxtyper --version && \ +stxtyper --help && \ +cd /stxtyper && \ +bash test_stxtyper.sh + +# download genome from NCBI and test stxtyper with it +# expect 1 perfect match to stx2o subtype, with COMPLETE operon designation +# https://www.ncbi.nlm.nih.gov/datasets/genome/GCA_012224845.2/ +# grep below requires both strings to be present in the same line +RUN echo "downloading test genome & running through stxtyper..." && \ +wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/012/224/845/GCA_012224845.2_ASM1222484v2/GCA_012224845.2_ASM1222484v2_genomic.fna.gz && \ +stxtyper -n GCA_012224845.2_ASM1222484v2_genomic.fna.gz | tee test-result.tsv && \ +grep 'stx2o' test-result.tsv | grep 'COMPLETE' diff --git a/stxtyper/1.0.27/README.md b/stxtyper/1.0.27/README.md new file mode 100644 index 000000000..16e21e054 --- /dev/null +++ b/stxtyper/1.0.27/README.md @@ -0,0 +1,29 @@ +# stxtyper container + +Main tool: [stxtyper](https://github.com/ncbi/stxtyper) + +Additional tools: + +- ncbi-blast+ 2.12.0 + +Basic information on how to use this tool: + +- executable: `stxtyper` +- help: `stxtyper --help` +- version: `stxtyper --version` +- description: Detects and types Shiga toxin genes in nucleotide sequences + +Full documentation: [https://github.com/ncbi/stxtyper](https://github.com/ncbi/stxtyper) + +Note: [This software is now incorporated into NCBI's AMRFinderPlus software as of version 4.0.3](https://github.com/ncbi/amr/releases/tag/amrfinder_v4.0.3). Stxtyper will run under-the-hood of AMRFinderPlus when using the `amrfinder --organism Escherichia` option. + +## Example Usage + +```bash +# stxtyper accepts both gzipped and uncompressed FASTA files +stxtyper -n GCA_012224845.2_ASM1222484v2_genomic.fna.gz -o stxtyper-results.tsv + +$ column -t test-result.tsv +#target_contig stx_type operon identity target_start target_stop target_strand A_reference A_reference_subtype A_identity A_coverage B_reference B_reference_subtype B_identity B_coverage +CP113091.1 stx2o COMPLETE 100.00 2085533 2086768 + WAK52085.1 stxA2o 100.00 100.00 QZL10983.1 stxB2o 100.00 100.00 +``` From 97ac25d594698ad9b2056b806cb700f70a906bf5 Mon Sep 17 00:00:00 2001 From: Fraser Combe Date: Wed, 20 Nov 2024 11:53:21 -0600 Subject: [PATCH 88/92] Adds updated Dorado 0.8.3 (#1107) * Add Dorado 0.8.0 Dockerfile and README * PR changes dorado * Dorado version 0.8.3 * update 0.8.0 files * correct licence --------- Co-authored-by: Young --- README.md | 2 +- dorado/0.8.3/Dockerfile | 64 ++++++++++++ dorado/0.8.3/README.md | 220 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 285 insertions(+), 1 deletion(-) create mode 100644 dorado/0.8.3/Dockerfile create mode 100644 dorado/0.8.3/README.md diff --git a/README.md b/README.md index 43f6df881..87e8d20f5 100644 --- a/README.md +++ b/README.md @@ -151,7 +151,7 @@ To learn more about the docker pull rate limits and the open source software pro | [datasets-sars-cov-2](https://github.com/CDCgov/datasets-sars-cov-2)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/datasets-sars-cov-2)](https://hub.docker.com/r/staphb/datasets-sars-cov-2) |
        • 0.6.2
        • 0.6.3
        • 0.7.2
        | https://github.com/CDCgov/datasets-sars-cov-2 | | [diamond](https://github.com/bbuchfink/diamond)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/diamond)](https://hub.docker.com/r/staphb/diamond) |
        • [2.1.9](./diamond/2.1.9)
        • [2.1.10](./diamond/2.1.10)
        | https://github.com/bbuchfink/diamond| | [dnaapler](https://hub.docker.com/r/staphb/dnaapler)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/dnaapler)](https://hub.docker.com/r/staphb/dnaapler) |
        • [0.1.0](dnaapler/0.1.0/)
        • [0.4.0](dnaapler/0.4.0/)
        • [0.5.0](./dnaapler/0.5.0/)
        • [0.5.1](./dnaapler/0.5.1/)
        • [0.7.0](./dnaapler/0.7.0/)
        • [0.8.0](./dnaapler/0.8.0/)
        • [0.8.1](./dnaapler/0.8.1/)
        | https://github.com/gbouras13/dnaapler | -| [dorado](https://hub.docker.com/r/staphb/dorado)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/dorado)](https://hub.docker.com/r/staphb/dorado) |
        • [0.8.0](dorado/0.8.0/)
        | [https://github.com/nanoporetech/dorado](https://github.com/nanoporetech/dorado) | +| [dorado](https://hub.docker.com/r/staphb/dorado)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/dorado)](https://hub.docker.com/r/staphb/dorado) |
        • [0.8.0](dorado/0.8.0/)
        • [0.8.3](dorado/0.8.3/)
        | [https://github.com/nanoporetech/dorado](https://github.com/nanoporetech/dorado) | | [dragonflye](https://hub.docker.com/r/staphb/dragonflye)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/dragonflye)](https://hub.docker.com/r/staphb/dragonflye) |
        • [1.0.14](./dragonflye/1.0.14/)
        • [1.1.1](./dragonflye/1.1.1/)
        • [1.1.2](./dragonflye/1.1.2/)
        • [1.2.0](./dragonflye/1.2.0/)
        • [1.2.1](./dragonflye/1.2.1/)
        | https://github.com/rpetit3/dragonflye | | [Dr. PRG ](https://hub.docker.com/r/staphb/drprg)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/drprg)](https://hub.docker.com/r/staphb/drprg) |
        • [0.1.1](drprg/0.1.1/)
        | https://mbh.sh/drprg/ | | [DSK](https://hub.docker.com/r/staphb/dsk)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/dsk)](https://hub.docker.com/r/staphb/dsk) |
        • [0.0.100](./dsk/0.0.100/)
        • [2.3.3](./dsk/2.3.3/)
        | https://gatb.inria.fr/software/dsk/ | diff --git a/dorado/0.8.3/Dockerfile b/dorado/0.8.3/Dockerfile new file mode 100644 index 000000000..bd9116b74 --- /dev/null +++ b/dorado/0.8.3/Dockerfile @@ -0,0 +1,64 @@ +# Use NVIDIA CUDA image as the base image +FROM nvidia/cuda:12.2.0-devel-ubuntu20.04 AS app + +ARG DORADO_VER=0.8.3 + +# Metadata +LABEL base.image="nvidia/cuda:12.2.0-devel-ubuntu20.04" +LABEL dockerfile.version="1" +LABEL software="dorado ${DORADO_VER}" +LABEL software.version="${DORADO_VER}" +LABEL description="A tool for basecalling Fast5/Pod5 files from Oxford Nanopore sequencing" +LABEL website="https://github.com/nanoporetech/dorado" +LABEL license="https://github.com/nanoporetech/dorado/blob/master/LICENSE" +LABEL original.website="https://nanoporetech.github.io/dorado/" +LABEL maintainer="Fraser Combe" +LABEL maintainer.email="fraser.combe@theiagen.com" + +# Set working directory +WORKDIR /usr/src/app + +# Install dependencies +RUN apt-get update && \ + apt-get install -y --no-install-recommends wget ca-certificates pigz && \ + rm -rf /var/lib/apt/lists/* && apt-get autoclean + +# Download and extract Dorado package +RUN wget https://cdn.oxfordnanoportal.com/software/analysis/dorado-${DORADO_VER}-linux-x64.tar.gz \ + && tar -xzvf dorado-${DORADO_VER}-linux-x64.tar.gz -C /opt \ + && rm dorado-${DORADO_VER}-linux-x64.tar.gz + +# Set environment variables for Dorado binary +ENV PATH="/opt/dorado-${DORADO_VER}-linux-x64/bin:${PATH}" + +# Download basecalling models +RUN mkdir /dorado_models && \ + cd /dorado_models && \ + dorado download --model all + +# Default command +CMD ["dorado"] + +# ----------------------------- +# Test Stage +# ----------------------------- +FROM app AS test + + +# Download the specific Pod5 test file +RUN wget -O /usr/src/app/dna_r10.4.1_e8.2_260bps-FLO_PRO114-SQK_NBD114_96_260-4000.pod5 \ + https://github.com/nanoporetech/dorado/raw/release-v0.7/tests/data/pod5/dna_r10.4.1_e8.2_260bps/\ +dna_r10.4.1_e8.2_260bps-FLO_PRO114-SQK_NBD114_96_260-4000.pod5 + +# Set working directory +WORKDIR /usr/src/app + +# Run test command (using CPU mode) +RUN dorado basecaller \ + --device cpu \ + /dorado_models/dna_r10.4.1_e8.2_260bps_sup@v3.5.2 \ + dna_r10.4.1_e8.2_260bps-FLO_PRO114-SQK_NBD114_96_260-4000.pod5 \ + --emit-moves --max-reads 10 > basecalled.sam + +# Verify the output file exists and is not empty +RUN test -s basecalled.sam diff --git a/dorado/0.8.3/README.md b/dorado/0.8.3/README.md new file mode 100644 index 000000000..54cd743c1 --- /dev/null +++ b/dorado/0.8.3/README.md @@ -0,0 +1,220 @@ +# Dorado Docker Image + +This Dockerfile sets up an environment for running **Dorado**, a tool for basecalling Fast5/Pod5 files from Oxford Nanopore sequencing. + +## Table of Contents + +- [Introduction](#introduction) +- [Requirements](#requirements) +- [Building the Docker Image](#building-the-docker-image) +- [Running the Docker Container](#running-the-docker-container) +- [Testing the Docker Image](#testing-the-docker-image) +- [Basecalling Test](#basecalling-test) +- [Verifying the Output](#verifying-the-output) +- [Additional Notes](#additional-notes) +- [License](#license) + +## Introduction + +This Docker image includes: + +- **Dorado**: Version **0.8.3**, a tool for basecalling Oxford Nanopore sequencing data. +- **NVIDIA CUDA**: Version **12.2.0**, for GPU acceleration (requires NVIDIA GPU). +- **Pigz**: Version **2.6**, for parallel compression and decompression. +- **Pre-downloaded basecalling models**: All models are downloaded during the build process for basecalling. + +## Requirements + +- **Docker**: Installed on your system. +- **NVIDIA GPU and Drivers**: Installed and configured. +- **NVIDIA Container Toolkit**: To enable GPU support in Docker containers. + +## Running the Docker Container + +To run the Dorado tool within the Docker container, use the following command: + +```bash +docker run --gpus all -it dorado-image dorado --help +``` + +This command will display the help information for Dorado, confirming that it's installed correctly. + +## Testing the Docker Image + +To test that Dorado is working correctly, you will need to download a sample Pod5 file and perform a basecalling operation using the pre-downloaded basecalling models. + +```bash +wget -O dna_r10.4.1_e8.2_260bps-FLO_PRO114-SQK_NBD114_96_260-4000.pod5 \ + https://github.com/nanoporetech/dorado/raw/release-v0.7/tests/data/pod5/dna_r10.4.1_e8.2_260bps/dna_r10.4.1_e8.2_260bps-FLO_PRO114-SQK_NBD114_96_260-4000.pod5 + + +### Basecalling Test + +Run the following command: + +```bash +docker run --gpus all -v $(pwd):/usr/src/app -it dorado-image bash -c "\ + dorado basecaller /dorado_models/dna_r10.4.1_e8.2_260bps_sup@v3.5.2 \ + /usr/src/app/dna_r10.4.1_e8.2_260bps-FLO_PRO114-SQK_NBD114_96_260-4000.pod5 \ + --emit-moves > /usr/src/app/basecalled.sam" +``` + +**Explanation:** + +- `--gpus all`: Enables GPU support. +- `-v $(pwd):/usr/src/app`: Mounts the current directory to `/usr/src/app` inside the container. +- `bash -c "...":` Runs the basecalling command inside the container. +- `> /usr/src/app/basecalled.sam`: Redirects the output to `basecalled.sam` in your current directory. + +### Verifying the Output + +Check the output file to ensure basecalling was successful: + +```bash +samtools view basecalled.sam +``` + +You should see SAM-formatted basecalling results. + +## Additional Notes + +- **Sample Data**: The sample Pod5 file is downloaded to `/usr/src/app` during the build. +- **Internal Testing**: An internal test stage is included in the Dockerfile to verify installation. +- **Basecalling Models**: All models are downloaded to `/dorado_models` during the build process. + Below is the list of basecalling models included in the Docker image: + ```yaml + + modification models: + - "dna_r9.4.1_e8_fast@v3.4_5mCG@v0.1" + - "dna_r9.4.1_e8_hac@v3.3_5mCG@v0.1" + - "dna_r9.4.1_e8_sup@v3.3_5mCG@v0.1" + - "dna_r9.4.1_e8_fast@v3.4_5mCG_5hmCG@v0" + - "dna_r9.4.1_e8_hac@v3.3_5mCG_5hmCG@v0" + - "dna_r9.4.1_e8_sup@v3.3_5mCG_5hmCG@v0" + - "dna_r10.4.1_e8.2_260bps_fast@v3.5.2_5mCG@v2" + - "dna_r10.4.1_e8.2_260bps_hac@v3.5.2_5mCG@v2" + - "dna_r10.4.1_e8.2_260bps_sup@v3.5.2_5mCG@v2" + - "dna_r10.4.1_e8.2_400bps_fast@v3.5.2_5mCG@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v3.5.2_5mCG@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v3.5.2_5mCG@v2" + - "dna_r10.4.1_e8.2_260bps_fast@v4.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_260bps_hac@v4.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_260bps_sup@v4.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_fast@v4.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v4.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_260bps_fast@v4.1.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_260bps_hac@v4.1.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_260bps_sup@v4.1.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_fast@v4.1.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v4.1.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.1.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_fast@v4.2.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v4.2.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0_5mCG_5hmCG@v3.1" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0_5mC@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0_6mA@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0_6mA@v3" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0_5mC_5hmC@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v4.3.0_5mC_5hmC@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v4.3.0_5mC_5hmC@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v4.3.0_6mA@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v4.3.0_6mA@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v4.3.0_6mA@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v4.3.0_6mA@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v4.3.0_5mCG_5hmCG@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v4.3.0_5mCG_5hmCG@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_4mC_5mC@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_4mC_5mC@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_4mC_5mC@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_4mC_5mC@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_5mC_5hmC@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_5mC_5hmC@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_5mC_5hmC@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_5mC_5hmC@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_5mCG_5hmCG@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_5mCG_5hmCG@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_5mCG_5hmCG@v2" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_6mA@v1" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_6mA@v1" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0_6mA@v2" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0_6mA@v2" + - "rna004_130bps_sup@v3.0.1_m6A_DRACH@v1" + - "rna004_130bps_hac@v5.0.0_m6A@v1" + - "rna004_130bps_sup@v5.0.0_m6A@v1" + - "rna004_130bps_hac@v5.0.0_m6A_DRACH@v1" + - "rna004_130bps_sup@v5.0.0_m6A_DRACH@v1" + - "rna004_130bps_hac@v5.0.0_pseU@v1" + - "rna004_130bps_sup@v5.0.0_pseU@v1" + - "rna004_130bps_hac@v5.1.0_m5C@v1" + - "rna004_130bps_sup@v5.1.0_m5C@v1" + - "rna004_130bps_hac@v5.1.0_inosine_m6A@v1" + - "rna004_130bps_sup@v5.1.0_inosine_m6A@v1" + - "rna004_130bps_hac@v5.1.0_m6A_DRACH@v1" + - "rna004_130bps_sup@v5.1.0_m6A_DRACH@v1" + - "rna004_130bps_hac@v5.1.0_pseU@v1" + - "rna004_130bps_sup@v5.1.0_pseU@v1" + stereo models: + - "dna_r10.4.1_e8.2_4khz_stereo@v1.1" + - "dna_r10.4.1_e8.2_4khz_stereo@v1.1" + - "dna_r10.4.1_e8.2_5khz_stereo@v1.1" + - "dna_r10.4.1_e8.2_5khz_stereo@v1.2" + - "dna_r10.4.1_e8.2_5khz_stereo@v1.3" + simplex models: + - "dna_r9.4.1_e8_fast@v3.4" + - "dna_r9.4.1_e8_hac@v3.3" + - "dna_r9.4.1_e8_sup@v3.3" + - "dna_r9.4.1_e8_sup@v3.6" + - "dna_r10.4.1_e8.2_260bps_fast@v3.5.2" + - "dna_r10.4.1_e8.2_260bps_hac@v3.5.2" + - "dna_r10.4.1_e8.2_260bps_sup@v3.5.2" + - "dna_r10.4.1_e8.2_400bps_fast@v3.5.2" + - "dna_r10.4.1_e8.2_400bps_hac@v3.5.2" + - "dna_r10.4.1_e8.2_400bps_sup@v3.5.2" + - "dna_r10.4.1_e8.2_260bps_fast@v4.0.0" + - "dna_r10.4.1_e8.2_260bps_hac@v4.0.0" + - "dna_r10.4.1_e8.2_260bps_sup@v4.0.0" + - "dna_r10.4.1_e8.2_400bps_fast@v4.0.0" + - "dna_r10.4.1_e8.2_400bps_hac@v4.0.0" + - "dna_r10.4.1_e8.2_400bps_sup@v4.0.0" + - "dna_r10.4.1_e8.2_260bps_fast@v4.1.0" + - "dna_r10.4.1_e8.2_260bps_hac@v4.1.0" + - "dna_r10.4.1_e8.2_260bps_sup@v4.1.0" + - "dna_r10.4.1_e8.2_400bps_fast@v4.1.0" + - "dna_r10.4.1_e8.2_400bps_hac@v4.1.0" + - "dna_r10.4.1_e8.2_400bps_sup@v4.1.0" + - "dna_r10.4.1_e8.2_400bps_fast@v4.2.0" + - "dna_r10.4.1_e8.2_400bps_hac@v4.2.0" + - "dna_r10.4.1_e8.2_400bps_sup@v4.2.0" + - "dna_r10.4.1_e8.2_400bps_fast@v4.3.0" + - "dna_r10.4.1_e8.2_400bps_hac@v4.3.0" + - "dna_r10.4.1_e8.2_400bps_sup@v4.3.0" + - "dna_r10.4.1_e8.2_400bps_fast@v5.0.0" + - "dna_r10.4.1_e8.2_400bps_hac@v5.0.0" + - "dna_r10.4.1_e8.2_400bps_sup@v5.0.0" + - "dna_r10.4.1_e8.2_apk_sup@v5.0.0" + - "rna002_70bps_fast@v3" + - "rna002_70bps_hac@v3" + - "rna004_130bps_fast@v3.0.1" + - "rna004_130bps_hac@v3.0.1" + - "rna004_130bps_sup@v3.0.1" + - "rna004_130bps_fast@v5.0.0" + - "rna004_130bps_hac@v5.0.0" + - "rna004_130bps_sup@v5.0.0" + - "rna004_130bps_fast@v5.1.0" + - "rna004_130bps_hac@v5.1.0" + - "rna004_130bps_sup@v5.1.0" + ``` + +## License + +Dorado is licensed under [Oxford Nanopore Technologies' License](https://github.com/nanoporetech/dorado/blob/master/LICENSE). + + +--- + +**Note**: Please ensure that you have the necessary NVIDIA drivers and the NVIDIA Container Toolkit installed to utilize GPU acceleration. + +--- From 312443cc38244c510d76c6303910ffb95d309952 Mon Sep 17 00:00:00 2001 From: Sage Wright Date: Thu, 21 Nov 2024 09:40:34 -0500 Subject: [PATCH 89/92] tbprofiler v6.4.1 (#1108) * add genoflu * add readme * add to license * add --force-pkgs-dirs * krakentools add * update readmes * silence warnings about AS casing; fix typo * added comment in dockerfile & added additional dependencies and versions to readme for krakentools * pinning biopython and pandas versions and removing unnecessary jq and gawk * fixed version of python installed listed in krakentools readme * add tbprofiler 6.4.0 * update readme * add list_db * exec format, capitalize AS * update versions * pinning delly version due to conflict resolution with usher 0.6.3 which is required by tb-profiler * added delly to list of deps for tb-profiler. Plus link to GH issue describing troubles w delly * add 6.4.1 * update readme * correct versions of a few dependencies in tbprofiler readme * Update Dockerfile * Update README.md --------- Co-authored-by: Curtis Kapsak --- README.md | 2 +- tbprofiler/6.4.1/Dockerfile | 66 +++++++++++++++++++++++++++++++++++++ tbprofiler/6.4.1/README.md | 60 +++++++++++++++++++++++++++++++++ 3 files changed, 127 insertions(+), 1 deletion(-) create mode 100644 tbprofiler/6.4.1/Dockerfile create mode 100644 tbprofiler/6.4.1/README.md diff --git a/README.md b/README.md index 87e8d20f5..686accabf 100644 --- a/README.md +++ b/README.md @@ -298,7 +298,7 @@ To learn more about the docker pull rate limits and the open source software pro | [Staramr](https://hub.docker.com/r/staphb/staramr/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/staramr)](https://hub.docker.com/r/staphb/staramr) |
        • [0.5.1](./staramr/0.5.1/)
        • [0.7.1](./staramr/0.7.1/)
        • [0.8.0](./staramr/0.8.0/)
        • [0.10.0](./staramr/0.10.0/)
        | https://github.com/phac-nml/staramr | | [stxtyper](https://hub.docker.com/r/staphb/stxtyper)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/stxtyper)](https://hub.docker.com/r/staphb/stxtyper) |
        • [1.0.24](stxtyper/1.0.24/)
        • [1.0.27](stxtyper/1.0.27/)
        | https://github.com/ncbi/stxtyper | | [sylph](https://hub.docker.com/r/staphb/sylph)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/sylph)](https://hub.docker.com/r/staphb/sylph) |
        • [0.4.1](./sylph/0.4.1)
        • [0.5.1](./sylph/0.5.1)
        • [0.6.0](./sylph/0.6.0)
        • [0.6.1](./sylph/0.6.1)
        | https://github.com/bluenote-1577/sylph | -| [TBProfiler](https://hub.docker.com/r/staphb/tbprofiler/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/tbprofiler)](https://hub.docker.com/r/staphb/tbprofiler) |
        • [4.3.0](./tbprofiler/4.3.0/)
        • [4.4.0](./tbprofiler/4.4.0/)
        • [4.4.2](./tbprofiler/4.4.2/)
        • [5.0.1](tbprofiler/5.0.1/)
        • [6.2.0](tbprofiler/6.2.0/)
        • [6.2.1](tbprofiler/6.2.1/)
        • [6.3.0](tbprofiler/6.3.0/)
        • [6.4.0](tbprofiler/6.4.0/)
        | https://github.com/jodyphelan/TBProfiler | +| [TBProfiler](https://hub.docker.com/r/staphb/tbprofiler/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/tbprofiler)](https://hub.docker.com/r/staphb/tbprofiler) |
        • [4.3.0](./tbprofiler/4.3.0/)
        • [4.4.0](./tbprofiler/4.4.0/)
        • [4.4.2](./tbprofiler/4.4.2/)
        • [5.0.1](tbprofiler/5.0.1/)
        • [6.2.0](tbprofiler/6.2.0/)
        • [6.2.1](tbprofiler/6.2.1/)
        • [6.3.0](tbprofiler/6.3.0/)
        • [6.4.0](tbprofiler/6.4.0/)
        • [6.4.1](tbprofiler/6.4.1/)
        | https://github.com/jodyphelan/TBProfiler | | [TipToft](https://hub.docker.com/r/staphb/tiptoft/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/tiptoft)](https://hub.docker.com/r/staphb/tiptoft) |
        • 1.0.0
        • 1.0.2
        | https://github.com/andrewjpage/tiptoft | | [Tostadas](https://hub.docker.com/r/staphb/tostadas/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/tostadas)](https://hub.docker.com/r/staphb/tostadas) |
        • [0.2.0-beta](./tostadas/0.2.0-beta/)
        • [3.1.0](./tostadas/3.1.0/)
        • [4.0.0](./tostadas/4.0.0/)
        | https://github.com/CDCgov/tostadas | | [Treemmer](https://hub.docker.com/r/staphb/treemmer/)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/treemmer)](https://hub.docker.com/r/staphb/treemmer) |
        • 0.3
        | https://git.scicore.unibas.ch/TBRU/Treemmer (archived, moved to GitHub)
        https://github.com/fmenardo/Treemmer | diff --git a/tbprofiler/6.4.1/Dockerfile b/tbprofiler/6.4.1/Dockerfile new file mode 100644 index 000000000..20f95f4b5 --- /dev/null +++ b/tbprofiler/6.4.1/Dockerfile @@ -0,0 +1,66 @@ +FROM mambaorg/micromamba:1.5.8 AS app + +USER root +WORKDIR / + +ARG TBPROFILER_VER="6.4.1" + +# this version is the shortened commit hash on the `master` branch here https://github.com/jodyphelan/tbdb/ +# commits are found on https://github.com/jodyphelan/tbdb/commits/master +# this was the latest commit as of 2024-10-31 +ARG TBDB_COMMIT="2c92475219416a449e89782f2b768149d26f7979" + +# LABEL instructions tag the image with metadata that might be important to the user +LABEL base.image="micromamba:1.5.8" +LABEL dockerfile.version="1" +LABEL software="tbprofiler" +LABEL software.version="${TBPROFILER_VER}" +LABEL description="The pipeline aligns reads to the H37Rv reference using bowtie2, BWA or minimap2 and then calls variants using bcftools. These variants are then compared to a drug-resistance database." +LABEL website="https://github.com/jodyphelan/TBProfiler/" +LABEL license="https://github.com/jodyphelan/TBProfiler/blob/master/LICENSE" +LABEL maintainer="John Arnn" +LABEL maintainer.email="jarnn@utah.gov" +LABEL maintainer2="Curtis Kapsak" +LABEL maintainer2.email="kapsakcj@gmail.com" +LABEL maintainer3="Sage Wright" +LABEL maintainer3.email="sagemwright@gmail.com" + +# Install dependencies via apt-get; cleanup apt garbage +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + procps && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# install tb-profiler via bioconda; install into 'base' conda env +RUN micromamba install --yes --name base --channel conda-forge --channel bioconda \ + tb-profiler=${TBPROFILER_VER} && \ + micromamba clean --all --yes -f && micromamba list + +# hardcode 'base' env bin into PATH, so conda env does not have to be "activated" at run time +ENV PATH="/opt/conda/bin:${PATH}" + +# Version of database can be confirmed at /opt/conda/share/tbprofiler/tbdb.version.json +# can also run 'tb-profiler list_db' to find the same version info + +# https://github.com/jodyphelan/tbdb +RUN tb-profiler update_tbdb --commit ${TBDB_COMMIT} && \ + tb-profiler list_db + +WORKDIR /data + +# Added command to bring help menu up upon running container. +CMD ["tb-profiler"] + +# test stage +FROM app AS test + +# checking if tool is in PATH +RUN tb-profiler && tb-profiler version + +WORKDIR /tests + +# download some TB FASTQs and run through tb-profiler +RUN wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR166/009/ERR1664619/ERR1664619_1.fastq.gz && \ + wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR166/009/ERR1664619/ERR1664619_2.fastq.gz && \ + tb-profiler profile -1 ERR1664619_1.fastq.gz -2 ERR1664619_2.fastq.gz -t 2 -p ERR1664619 --txt diff --git a/tbprofiler/6.4.1/README.md b/tbprofiler/6.4.1/README.md new file mode 100644 index 000000000..ccad82606 --- /dev/null +++ b/tbprofiler/6.4.1/README.md @@ -0,0 +1,60 @@ +# TBProfiler Container + +Main tool: [TBProfiler](https://github.com/jodyphelan/TBProfiler) + +The pipeline aligns reads to the H37Rv reference using bowtie2, BWA or minimap2 and then calls variants using bcftools. These variants are then compared to a drug-resistance database. It also predicts the number of reads supporting drug resistance variants as an insight into hetero-resistance. + +## Database + +This tool relies on a database to run. The version (AKA git commit hash) of the database that is included in the docker image is `2c92475`. This is from the GitHub repository https://github.com/jodyphelan/tbdb. This can be confirmed in the json file: `/opt/conda/share/tbprofiler/tbdb.variables.json`: + +```bash +$ grep 'commit' /opt/conda/share/tbprofiler/tbdb.variables.json +{"db-schema-version": "1.0.0", "snpEff_db": "Mycobacterium_tuberculosis_h37rv", "drugs": ["rifampicin", "isoniazid", "ethambutol", "pyrazinamide", "moxifloxacin", "levofloxacin", "bedaquiline", "delamanid", "pretomanid", "linezolid", "streptomycin", "amikacin", "kanamycin", "capreomycin", "clofazimine", "ethionamide", "para-aminosalicylic_acid", "cycloserine"], "tb-profiler-version": ">=6.0.0,<7.0.0", "version": {"name": "tbdb", "commit": "2c92475", "Merge": "8918884 2a51937", "Author": "Jody Phelan ", "Date": "Mon Oct 7 17:06:42 2024 +0100", "db-schema-version": "1.0.0"}, "amplicon": false, "files": {"ref": "tbdb.fasta", "gff": "tbdb.gff", "bed": "tbdb.bed", "json_db": "tbdb.dr.json", "variables": "tbdb.variables.json", "spoligotype_spacers": "tbdb.spoligotype_spacers.txt", "spoligotype_annotations": "tbdb.spoligotype_list.csv", "bedmask": "tbdb.mask.bed", "barcode": "tbdb.barcode.bed", "rules": "tbdb.rules.txt"}} +``` + +Additionally you can run the command `tb-profiler list_db` to list the same information + +```bash +$ tb-profiler list_db +tbdb 2c92475 Jody Phelan Mon Oct 7 17:06:42 2024 +0100 /opt/conda/share/tbprofiler/tbdb +``` + +## Additional included tools/dependencies + +- bedtools 2.31.1 +- gatk4 4.6.1.0 +- kmc 3.2.4 +- pathogen-profiler 4.5.1 +- perl 5.32.1 +- python 3.12.7 +- trimmomatic 0.39 +- bwa 0.7.18 +- minimap2 2.28 +- samtools 1.21 +- bcftools 1.21 +- freebayes 1.3.6 +- tqdm 4.67.0 +- parallel 20240922 +- samclip 0.4.0 +- snpeff 5.2 +- delly 1.2.6 (the more recent version 1.3.1 did not allow for the conda environment to resolve; TBProfiler has specifically pinned v1.2.6. More info here: https://github.com/jodyphelan/TBProfiler/issues/393#issuecomment-2452076859) + +## Example Usage + +Run whole pipeline on Illumina paired-end reads: + +```bash +tb-profiler profile -1 ERR1664619_1.fastq.gz -2 ERR1664619_2.fastq.gz -t 4 -p ERR1664619 --txt +``` + +Make alternative database: + +```bash +tb-profiler create_db --prefix +tb-profiler load_library --prefix +``` + +## Updates + +Release 5.0.1 implemented sqlite3 database locking with https://py-filelock.readthedocs.io/en/latest/index.html. This should fix issues using it over network filing systems (NFS). For more information, official documentation can be found [here.](https://jodyphelan.gitbook.io/tb-profiler/) From 4d997545ca8fdbccd54a80106279c0a0f2195cce Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Fri, 22 Nov 2024 14:58:37 +0000 Subject: [PATCH 90/92] adds dockerfile and readme for pangolin 4.3.1 and pdata 1.31 --- pangolin/4.3.1-pdata-1.31/Dockerfile | 219 +++++++++++++++++++++++++++ pangolin/4.3.1-pdata-1.31/README.md | 53 +++++++ 2 files changed, 272 insertions(+) create mode 100644 pangolin/4.3.1-pdata-1.31/Dockerfile create mode 100644 pangolin/4.3.1-pdata-1.31/README.md diff --git a/pangolin/4.3.1-pdata-1.31/Dockerfile b/pangolin/4.3.1-pdata-1.31/Dockerfile new file mode 100644 index 000000000..c8ba10e99 --- /dev/null +++ b/pangolin/4.3.1-pdata-1.31/Dockerfile @@ -0,0 +1,219 @@ +FROM mambaorg/micromamba:2.0.3-ubuntu22.04 AS app + +# build and run as root users since micromamba image has 'mambauser' set as the $USER +USER root +# set workdir to default for building; set to /data at the end +WORKDIR / + +# ARG variables only persist during build time +# had to include the v for some of these due to GitHub tags. +# using pangolin-data github tag, NOT what is in the GH release title "v1.2.133" +ARG PANGOLIN_VER="v4.3.1" +ARG PANGOLIN_DATA_VER="v1.31" +ARG SCORPIO_VER="v0.3.19" +ARG CONSTELLATIONS_VER="v0.1.12" +ARG USHER_VER="0.6.3" + +# metadata labels +LABEL base.image="mambaorg/micromamba:2.0.3-ubuntu22.04" +LABEL dockerfile.version="1" +LABEL software="pangolin" +LABEL software.version=${PANGOLIN_VER} +LABEL description="Conda environment for Pangolin. Pangolin: Software package for assigning SARS-CoV-2 genome sequences to global lineages." +LABEL website="https://github.com/cov-lineages/pangolin" +LABEL license="GNU General Public License v3.0" +LABEL license.url="https://github.com/cov-lineages/pangolin/blob/master/LICENSE.txt" +LABEL maintainer="Curtis Kapsak" +LABEL maintainer.email="kapsakcj@gmail.com" + +# install dependencies; cleanup apt garbage +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + git \ + procps \ + bsdmainutils && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# get the pangolin repo +RUN wget "https://github.com/cov-lineages/pangolin/archive/${PANGOLIN_VER}.tar.gz" && \ + tar -xf ${PANGOLIN_VER}.tar.gz && \ + rm -v ${PANGOLIN_VER}.tar.gz && \ + mv -v pangolin-* pangolin + +# set the environment; PATH is unnecessary here, but leaving anyways. It's reset later in dockerfile +ENV PATH="$PATH" \ + LC_ALL=C.UTF-8 + +# modify environment.yml to pin specific versions during install +# pin specific versions of usher, scorpio, pangolin-data, constellations, and pulp +# create the conda environment using modified environment.yml +# line to remove "defaults" channel to ensure that it isn't used due to Anaconda's recent ToS changes +RUN sed -i "s|usher.*|usher=${USHER_VER}|" /pangolin/environment.yml && \ + sed -i "s|scorpio.git|scorpio.git@${SCORPIO_VER}|" /pangolin/environment.yml && \ + sed -i "s|pangolin-data.git|pangolin-data.git@${PANGOLIN_DATA_VER}|" /pangolin/environment.yml && \ + sed -i "s|constellations.git|constellations.git@${CONSTELLATIONS_VER}|" /pangolin/environment.yml && \ + sed -i "12 a\ - pulp=2.7.0" /pangolin/environment.yml && \ + sed -i '/.*defaults/d' /pangolin/environment.yml && \ + micromamba create -n pangolin -y -f /pangolin/environment.yml && \ + micromamba clean -a -y -f + +# so that mamba/conda env is active when running below commands +ENV ENV_NAME="pangolin" +ARG MAMBA_DOCKERFILE_ACTIVATE=1 + +WORKDIR /pangolin + +# run pip install step; download optional pre-computed assignment hashes for UShER (useful for running on large batches of samples) +# best to skip using the assigment-cache if running on one sample for speed +# print versions +RUN pip install . && \ + pangolin --add-assignment-cache && \ + mkdir /data && \ + pangolin --all-versions && \ + usher --version + +# final working directory in "app" layer is /data for passing data in/out of container +WORKDIR /data + +# hardcode pangolin executable into the PATH variable +ENV PATH="${PATH}:/opt/conda/envs/pangolin/bin/" XDG_CACHE_HOME=/tmp + +# default command is to pull up help options for pangolin; can be overridden of course +CMD ["pangolin", "-h"] + +# new base for testing +FROM app AS test + +# so that mamba/conda env is active when running below commands +ENV ENV_NAME="pangolin" +ARG MAMBA_DOCKERFILE_ACTIVATE=1 + +# test on test sequences supplied with Pangolin code +RUN pangolin /pangolin/pangolin/test/test_seqs.fasta -o /data/test_seqs-output-pusher && \ + column -t -s, /data/test_seqs-output-pusher/lineage_report.csv + +# test functionality of assignment-cache option +RUN pangolin --use-assignment-cache /pangolin/pangolin/test/test_seqs.fasta + +# download B.1.1.7 genome from Utah +ADD https://raw.githubusercontent.com/StaPH-B/docker-builds/master/tests/SARS-CoV-2/SRR13957123.consensus.fa /test-data/SRR13957123.consensus.fa + +# test on a B.1.1.7 genome +RUN pangolin /test-data/SRR13957123.consensus.fa -o /test-data/SRR13957123-pusher && \ + column -t -s, /test-data/SRR13957123-pusher/lineage_report.csv + + # install unzip for unzipping zip archive from NCBI +RUN apt-get update && apt-get install -y --no-install-recommends unzip + +# install ncbi datasets tool (pre-compiled binary); place in $PATH +RUN wget https://ftp.ncbi.nlm.nih.gov/pub/datasets/command-line/LATEST/linux-amd64/datasets && \ + chmod +x datasets && \ + mv -v datasets /usr/local/bin + +# download assembly for a BA.1 from Florida (https://www.ncbi.nlm.nih.gov/biosample?term=SAMN29506515 and https://www.ncbi.nlm.nih.gov/nuccore/ON924087) +# run pangolin in usher analysis mode +RUN datasets download virus genome accession ON924087.1 --filename ON924087.1.zip && \ + unzip ON924087.1.zip && rm ON924087.1.zip && \ + mv -v ncbi_dataset/data/genomic.fna ON924087.1.genomic.fna && \ + rm -vr ncbi_dataset/ README.md && \ + pangolin ON924087.1.genomic.fna -o ON924087.1-usher && \ + column -t -s, ON924087.1-usher/lineage_report.csv + +# test specific for new lineage, XBB.1.16, introduced in pangolin-data v1.19 +# using this assembly: https://www.ncbi.nlm.nih.gov/nuccore/2440446687 +# biosample here: https://www.ncbi.nlm.nih.gov/biosample?term=SAMN33060589 +# one of the sample included in initial pango-designation here: https://github.com/cov-lineages/pango-designation/issues/1723 +RUN datasets download virus genome accession OQ381818.1 --filename OQ381818.1.zip && \ + unzip -o OQ381818.1.zip && rm OQ381818.1.zip && \ + mv -v ncbi_dataset/data/genomic.fna OQ381818.1.genomic.fna && \ + rm -vr ncbi_dataset/ README.md && \ + pangolin OQ381818.1.genomic.fna -o OQ381818.1-usher && \ + column -t -s, OQ381818.1-usher/lineage_report.csv + +# testing another XBB.1.16, trying to test scorpio functionality. Want pangolin to NOT assign lineage based on pango hash match. +# this test runs as expected, uses scorpio to check for constellation of mutations, then assign using PUSHER placement +RUN datasets download virus genome accession OR177999.1 --filename OR177999.1.zip && \ +unzip -o OR177999.1.zip && rm OR177999.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna OR177999.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin OR177999.1.genomic.fna -o OR177999.1-usher && \ +column -t -s, OR177999.1-usher/lineage_report.csv + + ## test for BA.2.86 + # virus identified in MI: https://www.ncbi.nlm.nih.gov/nuccore/OR461132.1 +RUN datasets download virus genome accession OR461132.1 --filename OR461132.1.zip && \ +unzip -o OR461132.1.zip && rm OR461132.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna OR461132.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin OR461132.1.genomic.fna -o OR461132.1-usher && \ +column -t -s, OR461132.1-usher/lineage_report.csv + + ## test for JN.2 (BA.2.86 sublineage) JN.2 is an alias of B.1.1.529.2.86.1.2 + # NY CDC Quest sample: https://www.ncbi.nlm.nih.gov/nuccore/OR598183 +RUN datasets download virus genome accession OR598183.1 --filename OR598183.1.zip && \ +unzip -o OR598183.1.zip && rm OR598183.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna OR598183.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin OR598183.1.genomic.fna -o OR598183.1-usher && \ +column -t -s, OR598183.1-usher/lineage_report.csv + +## test for JQ.1 (BA.2.86.3 sublineage); JQ.1 is an alias of B.1.1.529.2.86.3.1 +# THANK YOU ERIN AND UPHL!! https://www.ncbi.nlm.nih.gov/nuccore/OR716684 +# this test is important due to the fact that this lineage was included in the UShER tree, despite being designated after the pangolin-designation 1.23 release +# it previously caused and error/bug in pangolin, but now is fixed +RUN datasets download virus genome accession OR716684.1 --filename OR716684.1.zip && \ +unzip -o OR716684.1.zip && rm OR716684.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna OR716684.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin OR716684.1.genomic.fna -o OR716684.1-usher && \ +column -t -s, OR716684.1-usher/lineage_report.csv + +## test for JN.1.22 (BA.2.86.x sublineage; full unaliased lineage is B.1.1.529.2.86.1.1.22) +# see here for commit where it was designated https://github.com/cov-lineages/pango-designation/commit/a90c8e31c154621ed86c985debfea09e17541cda +# Here's the genome on NCBI, which was used to designate JN.1.22 lineage +RUN datasets download virus genome accession PP189069.1 --filename PP189069.1.zip && \ +unzip -o PP189069.1.zip && rm PP189069.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna PP189069.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin PP189069.1.genomic.fna -o PP189069.1-usher && \ +column -t -s, PP189069.1-usher/lineage_report.csv + +## test for JN.1.48 (BA.2.86.x sublineage; full unaliased lineage is B.1.1.529.2.86.1.1.48) +# this lineages which was designated in pango-designation v1.27: https://github.com/cov-lineages/pango-designation/releases/tag/v1.27 +# see here for commit where it was designated https://github.com/cov-lineages/pango-designation/commit/67f48bf24283999f1940f3aee8159f404124ff3f +# Here's the genome on NCBI: https://www.ncbi.nlm.nih.gov/nuccore/PP218754 +RUN datasets download virus genome accession PP218754.1 --filename PP218754.1.zip && \ +unzip -o PP218754.1.zip && rm PP218754.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna PP218754.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin PP218754.1.genomic.fna -o PP218754.1-usher && \ +column -t -s, PP218754.1-usher/lineage_report.csv + +# new lineage LK.1 that was introduced in pango-designation v1.28: https://github.com/cov-lineages/pango-designation/commit/922795c90de355e67200cf4d379e8e5ff22472e4 +# thank you Luis, Lorraine, Marcos & team from PR Sci Trust for sharing your data! +# genome on NCBI: https://www.ncbi.nlm.nih.gov/nuccore/2728145425 +RUN datasets download virus genome accession PP770375.1 --filename PP770375.1.zip && \ +unzip -o PP770375.1.zip && rm PP770375.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna PP770375.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin PP770375.1.genomic.fna -o PP770375.1-usher && \ +column -t -s, PP770375.1-usher/lineage_report.csv + +# new lineage KP.3.3.2 that was introduced in pango-designation v1.29: https://github.com/cov-lineages/pango-designation/commit/7125e606818312b78f0756d7fcab6dba92dd0a9e +# genome on NCBI: https://www.ncbi.nlm.nih.gov/nuccore/PQ073669 +RUN datasets download virus genome accession PQ073669.1 --filename PQ073669.1.zip && \ +unzip -o PQ073669.1.zip && rm PQ073669.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna PQ073669.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin PQ073669.1.genomic.fna -o PQ073669.1-usher && \ +column -t -s, PQ073669.1-usher/lineage_report.csv + +# new lineage MC.2 that was introduced in pango-designation v1.30: https://github.com/cov-lineages/pango-designation/commit/c64dbc47fbfbfd7f4da011deeb1a88dd6baa45f1#diff-a121ea4b8cbeb4c0020511b5535bf24489f0223cc83511df7b8209953115d329R2564181 +# genome on NCBI: https://www.ncbi.nlm.nih.gov/nuccore/PQ034842.1 +RUN datasets download virus genome accession PQ034842.1 --filename PQ034842.1.zip && \ +unzip -o PQ034842.1.zip && rm PQ034842.1.zip && \ +mv -v ncbi_dataset/data/genomic.fna PQ034842.1.genomic.fna && \ +rm -vr ncbi_dataset/ README.md && \ +pangolin PQ034842.1.genomic.fna -o PQ034842.1-usher && \ +column -t -s, PQ034842.1-usher/lineage_report.csv diff --git a/pangolin/4.3.1-pdata-1.31/README.md b/pangolin/4.3.1-pdata-1.31/README.md new file mode 100644 index 000000000..b4d286cb5 --- /dev/null +++ b/pangolin/4.3.1-pdata-1.31/README.md @@ -0,0 +1,53 @@ +# pangolin docker image + +Main tool : [pangolin](https://github.com/cov-lineages/pangolin) + +Full documentation: [https://cov-lineages.org/resources/pangolin.html](https://cov-lineages.org/resources/pangolin.html) + +Phylogenetic Assignment of Named Global Outbreak LINeages + +Additional tools: + +- [pangolin-data](https://github.com/cov-lineages/pangolin-data) 1.31 +- [pangolin-assignment](https://github.com/cov-lineages/pangolin-assignment) 1.31 +- [minimap2](https://github.com/lh3/minimap2) 2.28-r1209 +- [usher](https://github.com/yatisht/usher) 0.6.3 +- [faToVcf](https://github.com/yatisht/usher) 448 +- [scorpio](https://github.com/cov-lineages/scorpio) 0.3.19 +- [constellations](https://github.com/cov-lineages/constellations) 0.1.12 +- [gofasta](https://github.com/virus-evolution/gofasta) 1.2.1 +- [mafft](https://mafft.cbrc.jp/alignment/software/) 7.526 +- python 3.8.19 + +## pangoLEARN deprecation + +As of pangolin version 4.3, pangoLEARN mode has been deprecated. [More info can be found here on the v4.3 release page.](https://github.com/cov-lineages/pangolin/releases/tag/v4.3) + +> If `--analysis-mode fast` or `--analysis-mode pangolearn` is given, pangolin v4.3 will print out a warning and use UShER mode instead, unless `--datadir` is also given specifying a directory with pangoLEARN model files. The next release of pangolin-data (v1.20) will no longer include the model files which have not been updated since v1.18. + +The pangoLEARN model has not been updated since pangolin-data version 1.18. Only the the underlying UShER tree/protobuf file will be maintained for the forseeable future. + +**Please use the UShER mode of pangolin if you want to stay up-to-date with the most recent lineages.** [See pangolin-data release notes here for more details](https://github.com/cov-lineages/pangolin-data/releases) + +## Example Usage + +```bash +# run Pangolin in the default mode (usher). Can optionally supply --analysis-mode usher +$ pangolin /pangolin/pangolin/test/test_seqs.fasta -o /data/test_seqs-output-pusher + +# view the output CSV +$ column -t -s, /data/test_seqs-output-pusher/lineage_report.csv +taxon lineage conflict ambiguity_score scorpio_call scorpio_support scorpio_conflict scorpio_notes version pangolin_version scorpio_version constellation_version is_designated qc_status qc_notes note +India seq B.1.617.1 0.0 B.1.617.1-like 1.0 0.0 scorpio call: Alt alleles 11; Ref alleles 0; Amb alleles 0; Oth alleles 0 PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False pass Ambiguous_content:0.02 Usher placements: B.1.617.1(1/1) +b117 B.1.1.7 0.0 Alpha (B.1.1.7-like) 0.91 0.04 scorpio call: Alt alleles 21; Ref alleles 1; Amb alleles 1; Oth alleles 0 PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False pass Ambiguous_content:0.02 Usher placements: B.1.1.7(2/2) +outgroup_A A 0.0 PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False pass Ambiguous_content:0.02 Usher placements: A(1/1) +issue_57_torsten_seq Unassigned PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False fail failed to map +This_seq_has_6000_Ns_in_18000_bases Unassigned PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False fail failed to map +This_seq_has_no_seq Unassigned PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False fail failed to map +This_seq_is_too_short Unassigned PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False fail Ambiguous_content:0.9 +This_seq_has_lots_of_Ns Unassigned PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False fail Ambiguous_content:0.98 +This_seq_is_literally_just_N Unassigned PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False fail failed to map +Japan_seq B 0.0 PANGO-v1.16 4.1.3 0.3.17 v0.1.10 True pass Ambiguous_content:0.02 Assigned from designation hash. +USA_seq B.1.314 0.0 PANGO-v1.16 4.1.3 0.3.17 v0.1.10 True pass Ambiguous_content:0.02 Assigned from designation hash. +Unassigned_omicron_seq BA.1 0.0 Probable Omicron (BA.1-like) 0.71 0.08 scorpio call: Alt alleles 42; Ref alleles 5; Amb alleles 9; Oth alleles 3 PUSHER-v1.16 4.1.3 0.3.17 v0.1.10 False pass Ambiguous_content:0.03 Usher placements: BA.1(1/1) +``` From 9448d113abaf12df8ca1f2f9d4b37c36e6ba7ce9 Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Fri, 22 Nov 2024 15:15:45 +0000 Subject: [PATCH 91/92] update main readme --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 686accabf..4e9c58238 100644 --- a/README.md +++ b/README.md @@ -228,7 +228,7 @@ To learn more about the docker pull rate limits and the open source software pro | [OrthoFinder](https://hub.docker.com/r/staphb/orthofinder)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/orthofinder)](https://hub.docker.com/r/staphb/orthofinder) |
        • 2.17
        | https://github.com/davidemms/OrthoFinder | | [Panaroo](https://hub.docker.com/r/staphb/panaroo)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/panaroo)](https://hub.docker.com/r/staphb/panaroo) |
        • [1.2.10](panaroo/1.2.10/)
        • [1.3.4](panaroo/1.3.4/)
        • [1.5.0](./panaroo/1.5.0/)
        | (https://hub.docker.com/r/staphb/panaroo) | | [pango_aliasor](https://hub.docker.com/r/staphb/pango_aliasor)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/pango_aliasor)](https://hub.docker.com/r/staphb/pango_aliasor) |
        • [0.3.0](./pango_aliasor/0.3.0/)
        | https://github.com/corneliusroemer/pango_aliasor | -| [Pangolin](https://hub.docker.com/r/staphb/pangolin)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/pangolin)](https://hub.docker.com/r/staphb/pangolin) |
        Click to see Pangolin v4.2 and older versions! **Pangolin version & pangoLEARN data release date**
        • 1.1.14
        • 2.0.4 & 2020-07-20
        • 2.0.5 & 2020-07-20
        • 2.1.1 & 2020-12-17
        • 2.1.3 & 2020-12-17
        • 2.1.6 & 2021-01-06
        • 2.1.7 & 2021-01-11
        • 2.1.7 & 2021-01-20
        • 2.1.8 & 2021-01-22
        • 2.1.10 & 2021-02-01
        • 2.1.11 & 2021-02-01
        • 2.1.11 & 2021-02-05
        • 2.2.1 & 2021-02-06
        • 2.2.2 & 2021-02-06
        • 2.2.2 & 2021-02-11
        • 2.2.2 & 2021-02-12
        • 2.3.0 & 2021-02-12
        • 2.3.0 & 2021-02-18
        • 2.3.0 & 2021-02-21
        • 2.3.2 & 2021-02-21
        • 2.3.3 & 2021-03-16
        • 2.3.4 & 2021-03-16
        • 2.3.5 & 2021-03-16
        • 2.3.6 & 2021-03-16
        • 2.3.6 & 2021-03-29
        • 2.3.8 & 2021-04-01
        • 2.3.8 & 2021-04-14
        • 2.3.8 & 2021-04-21
        • 2.3.8 & 2021-04-23
        • 2.4 & 2021-04-28
        • 2.4.1 & 2021-04-28
        • 2.4.2 & 2021-04-28
        • 2.4.2 & 2021-05-10
        • 2.4.2 & 2021-05-11
        • 2.4.2 & 2021-05-19
        • 3.0.5 & 2021-06-05
        • 3.1.3 & 2021-06-15
        • 3.1.5 & 2021-06-15
        • 3.1.5 & 2021-07-07-2
        • 3.1.7 & 2021-07-09
        • 3.1.8 & 2021-07-28
        • 3.1.10 & 2021-07-28
        • 3.1.11 & 2021-08-09
        • 3.1.11 & 2021-08-24
        • 3.1.11 & 2021-09-17
        • 3.1.14 & 2021-09-28
        • 3.1.14 & 2021-10-13
        • 3.1.16 & 2021-10-18
        • 3.1.16 & 2021-11-04
        • 3.1.16 & 2021-11-09
        • 3.1.16 & 2021-11-18
        • 3.1.16 & 2021-11-25
        • 3.1.17 & 2021-11-25
        • 3.1.17 & 2021-12-06
        • 3.1.17 & 2022-01-05
        • 3.1.18 & 2022-01-20
        • 3.1.19 & 2022-01-20
        • 3.1.20 & 2022-02-02
        • 3.1.20 & 2022-02-28
        **Pangolin version & pangolin-data version**
        • 4.0 & 1.2.133
        • 4.0.1 & 1.2.133
        • 4.0.2 & 1.2.133
        • 4.0.3 & 1.2.133
        • 4.0.4 & 1.2.133
        • 4.0.5 & 1.3
        • 4.0.6 & 1.6
        • 4.0.6 & 1.8
        • 4.0.6 & 1.9
        • 4.1.1 & 1.11
        • 4.1.2 & 1.12
        • 4.1.2 & 1.13
        • 4.1.2 & 1.14
        • 4.1.3 & 1.15.1
        • 4.1.3 & 1.16
        • 4.1.3 & 1.17
        • 4.2 & 1.18
        • 4.2 & 1.18.1
        • 4.2 & 1.18.1.1
        • 4.2 & 1.19
        **Pangolin version & pangolin-data version**
        • [4.3 & 1.20](pangolin/4.3-pdata-1.20/)
        • [4.3 & 1.21](pangolin/4.3-pdata-1.21/)
        • [4.3.1 & 1.22](pangolin/4.3.1-pdata-1.22/)
        • [4.3.1 & 1.23](pangolin/4.3.1-pdata-1.23/)
        • [4.3.1 & 1.23.1](pangolin/4.3.1-pdata-1.23.1/)
        • [4.3.1 & 1.23.1 with XDG_CACHE_HOME=/tmp](pangolin/4.3.1-pdata-1.23.1-1/)
        • [4.3.1 & 1.24](pangolin/4.3.1-pdata-1.24/)
        • [4.3.1 & 1.25.1](pangolin/4.3.1-pdata-1.25.1/)
        • [4.3.1 & 1.26](pangolin/4.3.1-pdata-1.26/)
        • [4.3.1 & 1.27](pangolin/4.3.1-pdata-1.27/)
        • [4.3.1 & 1.28](pangolin/4.3.1-pdata-1.28/)
        • [4.3.1 & 1.28.1](pangolin/4.3.1-pdata-1.28.1/)
        • [4.3.1 & 1.29](pangolin/4.3.1-pdata-1.29/)
        • [4.3.1 & 1.30](pangolin/4.3.1-pdata-1.30/)
        | https://github.com/cov-lineages/pangolin
        https://github.com/cov-lineages/pangoLEARN
        https://github.com/cov-lineages/pango-designation
        https://github.com/cov-lineages/scorpio
        https://github.com/cov-lineages/constellations
        https://github.com/cov-lineages/lineages (archived)
        https://github.com/hCoV-2019/pangolin (archived) | +| [Pangolin](https://hub.docker.com/r/staphb/pangolin)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/pangolin)](https://hub.docker.com/r/staphb/pangolin) |
        Click to see Pangolin v4.2 and older versions! **Pangolin version & pangoLEARN data release date**
        • 1.1.14
        • 2.0.4 & 2020-07-20
        • 2.0.5 & 2020-07-20
        • 2.1.1 & 2020-12-17
        • 2.1.3 & 2020-12-17
        • 2.1.6 & 2021-01-06
        • 2.1.7 & 2021-01-11
        • 2.1.7 & 2021-01-20
        • 2.1.8 & 2021-01-22
        • 2.1.10 & 2021-02-01
        • 2.1.11 & 2021-02-01
        • 2.1.11 & 2021-02-05
        • 2.2.1 & 2021-02-06
        • 2.2.2 & 2021-02-06
        • 2.2.2 & 2021-02-11
        • 2.2.2 & 2021-02-12
        • 2.3.0 & 2021-02-12
        • 2.3.0 & 2021-02-18
        • 2.3.0 & 2021-02-21
        • 2.3.2 & 2021-02-21
        • 2.3.3 & 2021-03-16
        • 2.3.4 & 2021-03-16
        • 2.3.5 & 2021-03-16
        • 2.3.6 & 2021-03-16
        • 2.3.6 & 2021-03-29
        • 2.3.8 & 2021-04-01
        • 2.3.8 & 2021-04-14
        • 2.3.8 & 2021-04-21
        • 2.3.8 & 2021-04-23
        • 2.4 & 2021-04-28
        • 2.4.1 & 2021-04-28
        • 2.4.2 & 2021-04-28
        • 2.4.2 & 2021-05-10
        • 2.4.2 & 2021-05-11
        • 2.4.2 & 2021-05-19
        • 3.0.5 & 2021-06-05
        • 3.1.3 & 2021-06-15
        • 3.1.5 & 2021-06-15
        • 3.1.5 & 2021-07-07-2
        • 3.1.7 & 2021-07-09
        • 3.1.8 & 2021-07-28
        • 3.1.10 & 2021-07-28
        • 3.1.11 & 2021-08-09
        • 3.1.11 & 2021-08-24
        • 3.1.11 & 2021-09-17
        • 3.1.14 & 2021-09-28
        • 3.1.14 & 2021-10-13
        • 3.1.16 & 2021-10-18
        • 3.1.16 & 2021-11-04
        • 3.1.16 & 2021-11-09
        • 3.1.16 & 2021-11-18
        • 3.1.16 & 2021-11-25
        • 3.1.17 & 2021-11-25
        • 3.1.17 & 2021-12-06
        • 3.1.17 & 2022-01-05
        • 3.1.18 & 2022-01-20
        • 3.1.19 & 2022-01-20
        • 3.1.20 & 2022-02-02
        • 3.1.20 & 2022-02-28
        **Pangolin version & pangolin-data version**
        • 4.0 & 1.2.133
        • 4.0.1 & 1.2.133
        • 4.0.2 & 1.2.133
        • 4.0.3 & 1.2.133
        • 4.0.4 & 1.2.133
        • 4.0.5 & 1.3
        • 4.0.6 & 1.6
        • 4.0.6 & 1.8
        • 4.0.6 & 1.9
        • 4.1.1 & 1.11
        • 4.1.2 & 1.12
        • 4.1.2 & 1.13
        • 4.1.2 & 1.14
        • 4.1.3 & 1.15.1
        • 4.1.3 & 1.16
        • 4.1.3 & 1.17
        • 4.2 & 1.18
        • 4.2 & 1.18.1
        • 4.2 & 1.18.1.1
        • 4.2 & 1.19
        **Pangolin version & pangolin-data version**
        • [4.3 & 1.20](pangolin/4.3-pdata-1.20/)
        • [4.3 & 1.21](pangolin/4.3-pdata-1.21/)
        • [4.3.1 & 1.22](pangolin/4.3.1-pdata-1.22/)
        • [4.3.1 & 1.23](pangolin/4.3.1-pdata-1.23/)
        • [4.3.1 & 1.23.1](pangolin/4.3.1-pdata-1.23.1/)
        • [4.3.1 & 1.23.1 with XDG_CACHE_HOME=/tmp](pangolin/4.3.1-pdata-1.23.1-1/)
        • [4.3.1 & 1.24](pangolin/4.3.1-pdata-1.24/)
        • [4.3.1 & 1.25.1](pangolin/4.3.1-pdata-1.25.1/)
        • [4.3.1 & 1.26](pangolin/4.3.1-pdata-1.26/)
        • [4.3.1 & 1.27](pangolin/4.3.1-pdata-1.27/)
        • [4.3.1 & 1.28](pangolin/4.3.1-pdata-1.28/)
        • [4.3.1 & 1.28.1](pangolin/4.3.1-pdata-1.28.1/)
        • [4.3.1 & 1.29](pangolin/4.3.1-pdata-1.29/)
        • [4.3.1 & 1.30](pangolin/4.3.1-pdata-1.30/)
        • [4.3.1 & 1.31](pangolin/4.3.1-pdata-1.31/)
        | https://github.com/cov-lineages/pangolin
        https://github.com/cov-lineages/pangoLEARN
        https://github.com/cov-lineages/pango-designation
        https://github.com/cov-lineages/scorpio
        https://github.com/cov-lineages/constellations
        https://github.com/cov-lineages/lineages (archived)
        https://github.com/hCoV-2019/pangolin (archived) | | [panqc](https://hub.docker.com/r/staphb/panqc)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/panqc)](https://hub.docker.com/r/staphb/panqc) |
        • [0.4.0](./panqc/0.4.0/)
        | https://github.com/maxgmarin/panqc/releases/tag/0.4.0 | | [parallel-perl](https://hub.docker.com/r/staphb/parallel-perl)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/parallel-perl)](https://hub.docker.com/r/staphb/parallel-perl) |
        • 20200722
        | https://www.gnu.org/software/parallel | | [parsnp](https://hub.docker.com/r/staphb/parsnp)
        [![docker pulls](https://badgen.net/docker/pulls/staphb/parsnp)](https://hub.docker.com/r/staphb/parsnp) |
        • [1.5.6](./parsnp/1.5.6/)
        • [2.0.4](./parsnp/2.0.4/)
        • [2.0.5](./parsnp/2.0.5/)
        | https://github.com/marbl/parsnp | From ce6cb6a91c0e64fac6ea083b6f3d5ea46424333c Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Fri, 22 Nov 2024 16:00:48 +0000 Subject: [PATCH 92/92] major rework of pangolin test stage to consolidate to fewer test commands --- pangolin/4.3.1-pdata-1.31/Dockerfile | 124 ++++----------------------- 1 file changed, 18 insertions(+), 106 deletions(-) diff --git a/pangolin/4.3.1-pdata-1.31/Dockerfile b/pangolin/4.3.1-pdata-1.31/Dockerfile index c8ba10e99..49f381a4c 100644 --- a/pangolin/4.3.1-pdata-1.31/Dockerfile +++ b/pangolin/4.3.1-pdata-1.31/Dockerfile @@ -111,109 +111,21 @@ RUN wget https://ftp.ncbi.nlm.nih.gov/pub/datasets/command-line/LATEST/linux-amd chmod +x datasets && \ mv -v datasets /usr/local/bin -# download assembly for a BA.1 from Florida (https://www.ncbi.nlm.nih.gov/biosample?term=SAMN29506515 and https://www.ncbi.nlm.nih.gov/nuccore/ON924087) -# run pangolin in usher analysis mode -RUN datasets download virus genome accession ON924087.1 --filename ON924087.1.zip && \ - unzip ON924087.1.zip && rm ON924087.1.zip && \ - mv -v ncbi_dataset/data/genomic.fna ON924087.1.genomic.fna && \ - rm -vr ncbi_dataset/ README.md && \ - pangolin ON924087.1.genomic.fna -o ON924087.1-usher && \ - column -t -s, ON924087.1-usher/lineage_report.csv - -# test specific for new lineage, XBB.1.16, introduced in pangolin-data v1.19 -# using this assembly: https://www.ncbi.nlm.nih.gov/nuccore/2440446687 -# biosample here: https://www.ncbi.nlm.nih.gov/biosample?term=SAMN33060589 -# one of the sample included in initial pango-designation here: https://github.com/cov-lineages/pango-designation/issues/1723 -RUN datasets download virus genome accession OQ381818.1 --filename OQ381818.1.zip && \ - unzip -o OQ381818.1.zip && rm OQ381818.1.zip && \ - mv -v ncbi_dataset/data/genomic.fna OQ381818.1.genomic.fna && \ - rm -vr ncbi_dataset/ README.md && \ - pangolin OQ381818.1.genomic.fna -o OQ381818.1-usher && \ - column -t -s, OQ381818.1-usher/lineage_report.csv - -# testing another XBB.1.16, trying to test scorpio functionality. Want pangolin to NOT assign lineage based on pango hash match. -# this test runs as expected, uses scorpio to check for constellation of mutations, then assign using PUSHER placement -RUN datasets download virus genome accession OR177999.1 --filename OR177999.1.zip && \ -unzip -o OR177999.1.zip && rm OR177999.1.zip && \ -mv -v ncbi_dataset/data/genomic.fna OR177999.1.genomic.fna && \ -rm -vr ncbi_dataset/ README.md && \ -pangolin OR177999.1.genomic.fna -o OR177999.1-usher && \ -column -t -s, OR177999.1-usher/lineage_report.csv - - ## test for BA.2.86 - # virus identified in MI: https://www.ncbi.nlm.nih.gov/nuccore/OR461132.1 -RUN datasets download virus genome accession OR461132.1 --filename OR461132.1.zip && \ -unzip -o OR461132.1.zip && rm OR461132.1.zip && \ -mv -v ncbi_dataset/data/genomic.fna OR461132.1.genomic.fna && \ -rm -vr ncbi_dataset/ README.md && \ -pangolin OR461132.1.genomic.fna -o OR461132.1-usher && \ -column -t -s, OR461132.1-usher/lineage_report.csv - - ## test for JN.2 (BA.2.86 sublineage) JN.2 is an alias of B.1.1.529.2.86.1.2 - # NY CDC Quest sample: https://www.ncbi.nlm.nih.gov/nuccore/OR598183 -RUN datasets download virus genome accession OR598183.1 --filename OR598183.1.zip && \ -unzip -o OR598183.1.zip && rm OR598183.1.zip && \ -mv -v ncbi_dataset/data/genomic.fna OR598183.1.genomic.fna && \ -rm -vr ncbi_dataset/ README.md && \ -pangolin OR598183.1.genomic.fna -o OR598183.1-usher && \ -column -t -s, OR598183.1-usher/lineage_report.csv - -## test for JQ.1 (BA.2.86.3 sublineage); JQ.1 is an alias of B.1.1.529.2.86.3.1 -# THANK YOU ERIN AND UPHL!! https://www.ncbi.nlm.nih.gov/nuccore/OR716684 -# this test is important due to the fact that this lineage was included in the UShER tree, despite being designated after the pangolin-designation 1.23 release -# it previously caused and error/bug in pangolin, but now is fixed -RUN datasets download virus genome accession OR716684.1 --filename OR716684.1.zip && \ -unzip -o OR716684.1.zip && rm OR716684.1.zip && \ -mv -v ncbi_dataset/data/genomic.fna OR716684.1.genomic.fna && \ -rm -vr ncbi_dataset/ README.md && \ -pangolin OR716684.1.genomic.fna -o OR716684.1-usher && \ -column -t -s, OR716684.1-usher/lineage_report.csv - -## test for JN.1.22 (BA.2.86.x sublineage; full unaliased lineage is B.1.1.529.2.86.1.1.22) -# see here for commit where it was designated https://github.com/cov-lineages/pango-designation/commit/a90c8e31c154621ed86c985debfea09e17541cda -# Here's the genome on NCBI, which was used to designate JN.1.22 lineage -RUN datasets download virus genome accession PP189069.1 --filename PP189069.1.zip && \ -unzip -o PP189069.1.zip && rm PP189069.1.zip && \ -mv -v ncbi_dataset/data/genomic.fna PP189069.1.genomic.fna && \ -rm -vr ncbi_dataset/ README.md && \ -pangolin PP189069.1.genomic.fna -o PP189069.1-usher && \ -column -t -s, PP189069.1-usher/lineage_report.csv - -## test for JN.1.48 (BA.2.86.x sublineage; full unaliased lineage is B.1.1.529.2.86.1.1.48) -# this lineages which was designated in pango-designation v1.27: https://github.com/cov-lineages/pango-designation/releases/tag/v1.27 -# see here for commit where it was designated https://github.com/cov-lineages/pango-designation/commit/67f48bf24283999f1940f3aee8159f404124ff3f -# Here's the genome on NCBI: https://www.ncbi.nlm.nih.gov/nuccore/PP218754 -RUN datasets download virus genome accession PP218754.1 --filename PP218754.1.zip && \ -unzip -o PP218754.1.zip && rm PP218754.1.zip && \ -mv -v ncbi_dataset/data/genomic.fna PP218754.1.genomic.fna && \ -rm -vr ncbi_dataset/ README.md && \ -pangolin PP218754.1.genomic.fna -o PP218754.1-usher && \ -column -t -s, PP218754.1-usher/lineage_report.csv - -# new lineage LK.1 that was introduced in pango-designation v1.28: https://github.com/cov-lineages/pango-designation/commit/922795c90de355e67200cf4d379e8e5ff22472e4 -# thank you Luis, Lorraine, Marcos & team from PR Sci Trust for sharing your data! -# genome on NCBI: https://www.ncbi.nlm.nih.gov/nuccore/2728145425 -RUN datasets download virus genome accession PP770375.1 --filename PP770375.1.zip && \ -unzip -o PP770375.1.zip && rm PP770375.1.zip && \ -mv -v ncbi_dataset/data/genomic.fna PP770375.1.genomic.fna && \ -rm -vr ncbi_dataset/ README.md && \ -pangolin PP770375.1.genomic.fna -o PP770375.1-usher && \ -column -t -s, PP770375.1-usher/lineage_report.csv - -# new lineage KP.3.3.2 that was introduced in pango-designation v1.29: https://github.com/cov-lineages/pango-designation/commit/7125e606818312b78f0756d7fcab6dba92dd0a9e -# genome on NCBI: https://www.ncbi.nlm.nih.gov/nuccore/PQ073669 -RUN datasets download virus genome accession PQ073669.1 --filename PQ073669.1.zip && \ -unzip -o PQ073669.1.zip && rm PQ073669.1.zip && \ -mv -v ncbi_dataset/data/genomic.fna PQ073669.1.genomic.fna && \ -rm -vr ncbi_dataset/ README.md && \ -pangolin PQ073669.1.genomic.fna -o PQ073669.1-usher && \ -column -t -s, PQ073669.1-usher/lineage_report.csv - -# new lineage MC.2 that was introduced in pango-designation v1.30: https://github.com/cov-lineages/pango-designation/commit/c64dbc47fbfbfd7f4da011deeb1a88dd6baa45f1#diff-a121ea4b8cbeb4c0020511b5535bf24489f0223cc83511df7b8209953115d329R2564181 -# genome on NCBI: https://www.ncbi.nlm.nih.gov/nuccore/PQ034842.1 -RUN datasets download virus genome accession PQ034842.1 --filename PQ034842.1.zip && \ -unzip -o PQ034842.1.zip && rm PQ034842.1.zip && \ -mv -v ncbi_dataset/data/genomic.fna PQ034842.1.genomic.fna && \ -rm -vr ncbi_dataset/ README.md && \ -pangolin PQ034842.1.genomic.fna -o PQ034842.1-usher && \ -column -t -s, PQ034842.1-usher/lineage_report.csv +# testing the following lineages: +# BA.1 | ON924087.1 | from Florida https://www.ncbi.nlm.nih.gov/biosample?term=SAMN29506515 and https://www.ncbi.nlm.nih.gov/nuccore/ON924087 +# XBB.1.16 | OQ381818.1 | introduced in p-data 1.19, https://www.ncbi.nlm.nih.gov/nuccore/2440446687 and https://www.ncbi.nlm.nih.gov/biosample?term=SAMN33060589 and https://github.com/cov-lineages/pango-designation/issues/1723 +# another XBB.1.16 | OR177999.1 | https://www.ncbi.nlm.nih.gov/nuccore/OR177999.1 +# BA.2.86 | OR461132.1 | from Michigan https://www.ncbi.nlm.nih.gov/nuccore/OR461132.1 +# JN.2 (BA.2.86 sublineage) JN.2 is an alias of B.1.1.529.2.86.1.2 | OR598183.1 | NY CDC Quest sample https://www.ncbi.nlm.nih.gov/nuccore/OR598183 +# JQ.1 (BA.2.86.3 sublineage); JQ.1 is an alias of B.1.1.529.2.86.3.1 | OR716684.1 | THANK YOU ERIN AND UPHL!! https://www.ncbi.nlm.nih.gov/nuccore/OR716684 this test is important due to the fact that this lineage was included in the UShER tree, despite being designated after the pangolin-designation 1.23 release it previously caused and error/bug in pangolin, but now is fixed +# JN.1.22 (BA.2.86.x sublineage; full unaliased lineage is B.1.1.529.2.86.1.1.22) | PP189069.1 | https://github.com/cov-lineages/pango-designation/commit/a90c8e31c154621ed86c985debfea09e17541cda +# JN.1.48 (BA.2.86.x sublineage; full unaliased lineage is B.1.1.529.2.86.1.1.48) | PP218754.1 | https://github.com/cov-lineages/pango-designation/releases/tag/v1.27 and https://github.com/cov-lineages/pango-designation/commit/67f48bf24283999f1940f3aee8159f404124ff3f and https://www.ncbi.nlm.nih.gov/nuccore/PP218754 +# LK.1 | PP770375.1 | introduced in pango-designation 1.28 https://github.com/cov-lineages/pango-designation/commit/922795c90de355e67200cf4d379e8e5ff22472e4 and https://www.ncbi.nlm.nih.gov/nuccore/2728145425 thank you Luis, Lorraine, Marcos & team from PR Sci Trust for sharing your data! +# KP.3.3.2 | PQ073669.1 | introduced in pango-designation 1.29 https://github.com/cov-lineages/pango-designation/commit/7125e606818312b78f0756d7fcab6dba92dd0a9e and https://www.ncbi.nlm.nih.gov/nuccore/PQ073669 +# MC.2 | PQ034842.1 | introduced in pango-designation 1.30 https://github.com/cov-lineages/pango-designation/commit/c64dbc47fbfbfd7f4da011deeb1a88dd6baa45f1#diff-a121ea4b8cbeb4c0020511b5535bf24489f0223cc83511df7b8209953115d329R2564181 and https://www.ncbi.nlm.nih.gov/nuccore/PQ034842 +# XEC.3 | PQ277908.1 | introduced in pango-designation 1.31 https://github.com/cov-lineages/pango-designation/commit/ba3711a5615956ed97150288eb68356aa0fe7cdd#diff-a121ea4b8cbeb4c0020511b5535bf24489f0223cc83511df7b8209953115d329R2572545 and https://www.ncbi.nlm.nih.gov/nuccore/PQ277908.1 +RUN datasets download virus genome accession ON924087.1,OQ381818.1,OR177999.1,OR461132.1,OR598183.1,OR716684.1,PP189069.1,PP218754.1,PP770375.1,PQ073669.1,PQ034842.1,PQ277908.1 && \ +unzip -o ncbi_dataset.zip && \ +rm -v ncbi_dataset.zip && \ +pangolin ncbi_dataset/data/genomic.fna && \ +column -t -s, lineage_report.csv \ No newline at end of file