-
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.
adding assembly_snptyper version 0.1.1 (#1016)
- Loading branch information
Showing
4 changed files
with
145 additions
and
0 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 +1,109 @@ | ||
| 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="${ASSEMBLYSNPTYPER_VER}" | ||
| LABEL description="Type assembly based on a VCF using minimap2 + samtools" | ||
| LABEL website="https://github.com/boasvdp/assembly_snptyper" | ||
| LABEL license="https://github.com/boasvdp/assembly_snptyper/blob/main/LICENSE" | ||
| LABEL maintainer="Erin Young" | ||
| LABEL maintainer.email="[email protected]" | ||
|
|
||
| ARG DEBIAN_FRONTEND=noninteractive | ||
| RUN apt-get update && apt-get install --no-install-recommends -y \ | ||
| perl \ | ||
| zlib1g \ | ||
| libncurses5 \ | ||
| bzip2 \ | ||
| liblzma-dev \ | ||
| libcurl4-gnutls-dev \ | ||
| wget \ | ||
| ca-certificates \ | ||
| procps \ | ||
| python3 \ | ||
| python3-pip \ | ||
| python-is-python3 \ | ||
| curl \ | ||
| unzip \ | ||
| && apt-get autoclean && rm -rf /var/lib/apt/lists/* | ||
|
|
||
| # copy in samtools and minimap2 executables from builder stage | ||
| COPY --from=builder /usr/local/bin/* /usr/local/bin/ | ||
|
|
||
| RUN pip install pandas | ||
|
|
||
| # install assembly_snptyper; make /data dir | ||
| RUN wget -q https://github.com/boasvdp/assembly_snptyper/archive/refs/tags/v${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 |
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 +1,34 @@ | ||
| # 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 | ||
| ``` | ||
|
|