diff --git a/README.md b/README.md index f435e9475..763a42516 100644 --- a/README.md +++ b/README.md @@ -114,7 +114,7 @@ To learn more about the docker pull rate limits and the open source software pro | [ANIclustermap](https://hub.docker.com/r/staphb/aniclustermap/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/aniclustermap)](https://hub.docker.com/r/staphb/aniclustermap) | | https://github.com/moshi4/ANIclustermap | | [any2fasta](https://hub.docker.com/r/staphb/any2fasta/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/any2fasta)](https://hub.docker.com/r/staphb/any2fasta) | | https://github.com/tseemann/any2fasta | | [ARIBA](https://hub.docker.com/r/staphb/ariba/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/ariba)](https://hub.docker.com/r/staphb/ariba) | | https://github.com/sanger-pathogens/ariba | -| [artic](https://hub.docker.com/r/staphb/artic)
[![docker pulls](https://badgen.net/docker/pulls/staphb/artic)](https://hub.docker.com/r/staphb/artic) | | https://github.com/artic-network/fieldbioinformatics | +| [artic](https://hub.docker.com/r/staphb/artic)
[![docker pulls](https://badgen.net/docker/pulls/staphb/artic)](https://hub.docker.com/r/staphb/artic) | | https://github.com/artic-network/fieldbioinformatics | | [artic-ncov2019](https://hub.docker.com/r/staphb/artic-ncov2019)
[![docker pulls](https://badgen.net/docker/pulls/staphb/artic-ncov2019)](https://hub.docker.com/r/staphb/artic-ncov2019) | | https://github.com/artic-network/fieldbioinformatics | | [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) | | 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) | | https://github.com/artic-network/artic-ncov2019 | diff --git a/artic/1.5.8/Dockerfile b/artic/1.5.8/Dockerfile new file mode 100644 index 000000000..0ca9c8e1e --- /dev/null +++ b/artic/1.5.8/Dockerfile @@ -0,0 +1,96 @@ +ARG ARTIC_VER=1.5.8 + +FROM mambaorg/micromamba:1.5.8 AS app + +ARG ARTIC_VER + +LABEL base.image="mambaorg/micromamba:1.5.8" +LABEL dockerfile.version="1" +LABEL software="artic" +LABEL software.version="${ARTIC_VER}" +LABEL description="A bioinformatics pipeline for working with virus sequencing data sequenced with nanopore" +LABEL website="https://github.com/artic-network/fieldbioinformatics" +LABEL license="https://github.com/artic-network/fieldbioinformatics/blob/master/LICENSE" +LABEL sop="https://artic.network/ncov-2019/ncov2019-bioinformatics-sop.html" +LABEL maintainer="Erin Young" +LABEL maintainer.email="eriny@utah.gov" + +USER root +WORKDIR / + +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + ca-certificates \ + procps \ + gcc \ + make \ + pkg-config \ + zlib1g-dev \ + libbz2-dev \ + liblzma-dev \ + libcurl4-gnutls-dev \ + libssl-dev \ + python3-dev \ + python3-pip \ + python-is-python3 && \ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +RUN micromamba create -n artic -y -c conda-forge -c bioconda -c defaults \ + artic=${ARTIC_VER} && \ + micromamba clean -a -f -y && \ + mkdir /data + +ENV PATH="${PATH}:/opt/conda/envs/artic/bin/" \ + CONDA_PREFIX="/opt/conda/envs/artic/" \ + LC_ALL=C.UTF-8 + +RUN artic_get_models + +CMD artic --help + +WORKDIR /data + +##### ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- ##### +##### Step 2. Set up the testing stage. ##### +##### The docker image is built to the 'test' stage before merging, but ##### +##### the test stage (or any stage after 'app') will be lost. ##### +##### ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- ##### + +# A second FROM insruction creates a new stage +# new base for testing +FROM app AS test +ARG ARTIC_VER + +# print help and version info; check dependencies (not all software has these options available) +# Mostly this ensures the tool of choice is in path and is executable +RUN artic --help && \ + artic --version + +WORKDIR / + +# test that came with artic +RUN wget -q https://github.com/artic-network/fieldbioinformatics/archive/refs/tags/v${ARTIC_VER}.tar.gz && \ + tar -vxf v${ARTIC_VER}.tar.gz && \ + cd /fieldbioinformatics-${ARTIC_VER} && ls && \ + bash ./test-runner.sh clair3 + +WORKDIR /test + +# using on "real" data (sample files were not sequenced with version 5.3.2 primers) +# filtering fastq files +RUN wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR224/050/SRR22452250/SRR22452250_1.fastq.gz && \ + artic guppyplex --min-length 400 --max-length 700 --directory . --prefix SRR22452250_1.fastq.gz --output SRR22452250_1_filtered.fastq.gz + +# running artic minion with user-provided bed and reference +RUN wget -q https://raw.githubusercontent.com/artic-network/primer-schemes/master/nCoV-2019/V5.3.2/SARS-CoV-2.primer.bed && \ + wget -q https://raw.githubusercontent.com/artic-network/primer-schemes/master/nCoV-2019/V5.3.2/SARS-CoV-2.reference.fasta && \ + artic minion --normalise 200 --threads 4 --model ont --read-file SRR22452250_1_filtered.fastq.gz --bed SARS-CoV-2.primer.bed --ref SARS-CoV-2.reference.fasta test1 && \ + ls test1* + +# running artic as it pulls schemes from github +RUN artic minion --normalise 200 --threads 4 --model ont --read-file SRR22452250_1_filtered.fastq.gz --scheme-name sars-cov-2 --scheme-version V5.3.2 test2 && \ + ls test2* + + +RUN echo "included models" && \ + ls ${CONDA_PREFIX}/bin/models \ No newline at end of file diff --git a/artic/1.5.8/README.md b/artic/1.5.8/README.md new file mode 100644 index 000000000..441270496 --- /dev/null +++ b/artic/1.5.8/README.md @@ -0,0 +1,76 @@ +# artic fieldbioinformatics container + +Main tool : [artic](https://github.com/artic-network/fieldbioinformatics) + +Full documentation: [https://github.com/artic-network/fieldbioinformatics](https://github.com/artic-network/fieldbioinformatics) + +There is also a very useful SOP: [https://artic.network/ncov-2019/ncov2019-bioinformatics-sop.html](https://artic.network/ncov-2019/ncov2019-bioinformatics-sop.html) +And additional documentation: [https://artic.readthedocs.io/en/latest/](https://artic.readthedocs.io/en/latest/) + +> A bioinformatics pipeline for working with virus sequencing data sequenced with nanopore. + +WARNING : This container does not contain the primer schemes found at [https://github.com/artic-network/primer-schemes](https://github.com/artic-network/primer-schemes). Those will have to be downloaded and mounted separately. There are now commands to download the use the primers at runtime. + +This image DOES contain the medaka models downloaded with `artic_get_models` + +## Example Usage with the artic primers + +```bash +# filtering reads +artic guppyplex --min-length 400 --max-length 700 --directory . --prefix SRR22452250_1.fastq.gz --output SRR22452250_1_filtered.fastq.gz + +# downloading medaka models for clair3 +artic_get_models + +# running the artic minion workflow +# the result files will all start with test* +artic minion --normalise 200 --medaka-model ont --threads 4 --read-file sample.fastq.gz --scheme-directory primer-schemes --scheme-version 5.3.2 nCoV-2019 test + +# running the artic minion workflow with user-provided primer bedfiles and references +artic minion --normalise 200 --threads 4 --model ont --read-file sample.fastq.gz --scheme-name sars-cov-2 --scheme-version V5.3.2 name + +``` + +In general, any primer scheme can be used as long as it meets [artic's requirements](https://github.com/artic-network/primer-schemes). + + + +## Medaka models + +Artic uses [Clair3](https://github.com/HKU-BAL/Clair3), which uses medaka models. Medaka updates frequently, and artic can throw errors when corresponding ONT models are not found. + +These are the medaka models in this image: +``` +# included models at /opt/conda/envs/artic/bin/models +hifi +hifi_revio +hifi_sequel2 +ilmn +ont +ont_guppy5 +r1041_e82_260bps_fast_g632 +r1041_e82_260bps_hac_g632 +r1041_e82_260bps_hac_v400 +r1041_e82_260bps_hac_v410 +r1041_e82_260bps_sup_g632 +r1041_e82_260bps_sup_v400 +r1041_e82_260bps_sup_v410 +r1041_e82_400bps_fast_g632 +r1041_e82_400bps_hac_g615 +r1041_e82_400bps_hac_g632 +r1041_e82_400bps_hac_v400 +r1041_e82_400bps_hac_v410 +r1041_e82_400bps_hac_v420 +r1041_e82_400bps_hac_v430 +r1041_e82_400bps_hac_v500 +r1041_e82_400bps_sup_g615 +r1041_e82_400bps_sup_v400 +r1041_e82_400bps_sup_v410 +r1041_e82_400bps_sup_v420 +r1041_e82_400bps_sup_v430 +r1041_e82_400bps_sup_v500 +r104_e81_hac_g5015 +r104_e81_sup_g5015 +r941_prom_hac_g360+g422 +r941_prom_sup_g5014 +```