-
Notifications
You must be signed in to change notification settings - Fork 125
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
adds dockerfile for pangolin 4.3.1 and pdata 1.23.1. also adds tool-s…
…pecific readme and updates the main README.md table
- Loading branch information
Showing
3 changed files
with
227 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,165 @@ | ||
| FROM mambaorg/micromamba:1.5.1 as app | ||
|
|
||
| # build and run as root users since micromamba image has 'mambauser' set as the $USER | ||
| USER root | ||
| # set workdir to default for building; set to /data at the end | ||
| WORKDIR / | ||
|
|
||
| # ARG variables only persist during build time | ||
| # had to include the v for some of these due to GitHub tags. | ||
| # using pangolin-data github tag, NOT what is in the GH release title "v1.2.133" | ||
| ARG PANGOLIN_VER="v4.3.1" | ||
| ARG PANGOLIN_DATA_VER="v1.23.1" | ||
| ARG SCORPIO_VER="v0.3.19" | ||
| ARG CONSTELLATIONS_VER="v0.1.12" | ||
| ARG USHER_VER="0.6.2" | ||
|
|
||
| # metadata labels | ||
| LABEL base.image="mambaorg/micromamba:1.5.1" | ||
| LABEL dockerfile.version="1" | ||
| LABEL software="pangolin" | ||
| LABEL software.version=${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="[email protected]" | ||
|
|
||
| # 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 | ||
| # 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 && \ | ||
| micromamba create -n pangolin -y -f /pangolin/environment.yml | ||
|
|
||
| # 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 && \ | ||
| micromamba clean -a -y && \ | ||
| mkdir /data && \ | ||
| pangolin --all-versions && \ | ||
| usher --version | ||
|
|
||
| WORKDIR /data | ||
|
|
||
| # hardcode pangolin executable into the PATH variable | ||
| ENV PATH="${PATH}:/opt/conda/envs/pangolin/bin/" | ||
|
|
||
| # default command is to pull up help options for virulencefinder; 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 --analysis-mode usher -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 --analysis-mode usher -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 --analysis-mode usher -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 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 --analysis-mode usher -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 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 --analysis-mode usher -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 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 --analysis-mode usher -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 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 --analysis-mode usher -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 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 --analysis-mode usher -o OR716684.1-usher && \ | ||
| column -t -s, OR716684.1-usher/lineage_report.csv |
Oops, something went wrong.