-
Notifications
You must be signed in to change notification settings - Fork 126
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
4 changed files
with
172 additions
and
2 deletions.
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
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 +1,126 @@ | ||
| # Set global variables | ||
| ARG CAT_VER="6.0.1" | ||
| ARG SAMTOOLS_VER="1.21" | ||
| ARG BWA_VER="0.7.18" | ||
| ARG DIAMOND_VER="2.1.10" | ||
|
|
||
|
|
||
| FROM ubuntu:jammy AS builder | ||
|
|
||
| ARG SAMTOOLS_VER | ||
| ARG BWA_VER | ||
| ARG DIAMOND_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 | ||
|
|
||
|
|
||
| RUN wget -q https://github.com/lh3/bwa/archive/refs/tags/v${BWA_VER}.tar.gz &&\ | ||
| tar -xvf v${BWA_VER}.tar.gz &&\ | ||
| cd bwa-${BWA_VER} &&\ | ||
| make &&\ | ||
| mv bwa /usr/local/bin/ | ||
|
|
||
| RUN wget -q https://github.com/bbuchfink/diamond/releases/download/v${DIAMOND_VER}/diamond-linux64.tar.gz &&\ | ||
| tar -C /usr/local/bin -xvf diamond-linux64.tar.gz && \ | ||
| rm diamond-linux64.tar.gz | ||
|
|
||
|
|
||
| # Application Stage | ||
| FROM ubuntu:jammy AS app | ||
| ARG CAT_VER | ||
|
|
||
|
|
||
| LABEL base.image="ubuntu:jammy" | ||
| LABEL dockerfile.version="1" | ||
| LABEL software="CAT" | ||
| LABEL software.version=${CAT_VER} | ||
| LABEL description="CAT: a tool for taxonomic classification of contigs and metagenome-assembled genomes (MAGs)." | ||
| LABEL website="https://github.com/MGXlab/CAT_pack" | ||
| LABEL license.url="https://github.com/MGXlab/CAT_pack/blob/master/LICENSE.md" | ||
| LABEL maintainer="Taylor K. Paisie" | ||
| LABEL maintainer.email='[email protected]' | ||
|
|
||
| RUN apt-get update && apt-get install -y --no-install-recommends \ | ||
| wget \ | ||
| unzip \ | ||
| ca-certificates \ | ||
| python3 \ | ||
| python3-pip \ | ||
| prodigal && \ | ||
| apt-get autoclean && rm -rf /var/lib/apt/lists/* | ||
|
|
||
| COPY --from=builder /usr/local/bin/* /usr/local/bin/ | ||
|
|
||
|
|
||
|
|
||
| RUN wget -q https://github.com/MGXlab/CAT_pack/archive/refs/tags/v${CAT_VER}.tar.gz && \ | ||
| tar -xvzf v${CAT_VER}.tar.gz && \ | ||
| chmod +x /CAT_pack-${CAT_VER}/CAT_pack/CAT_pack && \ | ||
| rm v${CAT_VER}.tar.gz | ||
|
|
||
|
|
||
| # Add CAT to PATH | ||
| ENV PATH="${PATH}:/CAT_pack-${CAT_VER}/CAT_pack" | ||
|
|
||
| CMD ["CAT_pack", "--help"] | ||
| WORKDIR /data | ||
|
|
||
| # Optional stage: Test data | ||
| FROM app AS test | ||
|
|
||
| ARG CAT_VER | ||
|
|
||
| WORKDIR /data/test | ||
|
|
||
| RUN CAT_pack --help && CAT_pack --version | ||
|
|
||
| RUN wget -nv --no-check-certificate \ | ||
| https://raw.githubusercontent.com/taylorpaisie/docker_containers/main/checkm2/1.0.2/burk_wgs.fa \ | ||
| -O burk_wgs_pos_ctrl.fa &&\ | ||
| wget -nv --no-check-certificate \ | ||
| https://merenlab.org/data/refining-mags/files/GN02_MAG_IV_B_1-contigs.fa \ | ||
| -O GN02_MAG_IV_B_1-contigs.fa | ||
|
|
||
| # Prepare testing database | ||
| RUN mkdir -p db_tests && \ | ||
| gzip -d /CAT_pack-${CAT_VER}/tests/data/prepare/small.fa.gz && \ | ||
| CAT_pack prepare --db_fasta /CAT_pack-${CAT_VER}/tests/data/prepare/small.fa \ | ||
| --acc2tax /CAT_pack-${CAT_VER}/tests/data/prepare/prot2acc.txt \ | ||
| --names /CAT_pack-${CAT_VER}/tests/data/prepare/names.dmp \ | ||
| --nodes /CAT_pack-${CAT_VER}/tests/data/prepare/nodes.dmp \ | ||
| --db_dir db_tests/ | ||
|
|
||
| # Running CAT on contigs | ||
| RUN CAT_pack contigs -c burk_wgs_pos_ctrl.fa \ | ||
| -d db_tests/db \ | ||
| -t db_tests/tax | ||
|
|
||
| # Running BAT on a set of MAGs | ||
| RUN CAT_pack bins -b GN02_MAG_IV_B_1-contigs.fa \ | ||
| -d db_tests/db \ | ||
| -t db_tests/tax | ||
|
|
||
| WORKDIR /data |
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 +1,44 @@ | ||
| # CAT | ||
|
|
||
| Main tool: [CAT](https://github.com/MGXlab/CAT_pack) | ||
|
|
||
| Code repository: https://github.com/MGXlab/CAT_pack | ||
|
|
||
| Basic information on how to use this tool: | ||
| - executable: CAT_pack | ||
| - help: --help | ||
| - version: --version | ||
| - description: | | ||
| > Contig Annotation Tool (CAT) and Bin Annotation Tool (BAT) are pipelines for the taxonomic classification of long DNA sequences and metagenome assembled genomes (MAGs/bins) of both known and (highly) unknown microorganisms, as generated by contemporary metagenomics studies | ||
|
|
||
| Full documentation: https://github.com/MGXlab/CAT_pack | ||
|
|
||
|
|
||
| # Testing CAT: | ||
| ``` | ||
| # Download test data | ||
| wget -nv --no-check-certificate https://raw.githubusercontent.com/taylorpaisie/docker_containers/main/checkm2/1.0.2/burk_wgs.fa -O burk_wgs_pos_ctrl.fa | ||
| wget -nv --no-check-certificate https://merenlab.org/data/refining-mags/files/GN02_MAG_IV_B_1-contigs.fa -O GN02_MAG_IV_B_1-contigs.fa | ||
| # Prepare testing database | ||
| RUN mkdir -p db_tests && \ | ||
| gzip -d /CAT/tests/data/prepare/small.fa.gz && \ | ||
| CAT_pack prepare --db_fasta /CAT/tests/data/prepare/small.fa \ | ||
| --acc2tax /CAT/tests/data/prepare/prot2acc.txt \ | ||
| --names /CAT/tests/data/prepare/names.dmp \ | ||
| --nodes /CAT/tests/data/prepare/nodes.dmp \ | ||
| --db_dir db_tests/ | ||
| # Use CAT and BAT for taxonomic classification for both best datasets | ||
| # Running CAT on contigs | ||
| CAT_pack contigs -c test/burk_wgs_pos_ctrl.fa \ | ||
| -d db_tests/db \ | ||
| -t db_tests/tax | ||
| # Running BAT on a set of MAGs | ||
| CAT_pack bins -b test/GN02_MAG_IV_B_1-contigs.fa \ | ||
| -d db_tests/db \ | ||
| -t db_tests/tax | ||
| ``` |