-
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.
* added seqsero2 version 1.3.1 * added maintainer * added line to delete samtools source code to save space; edited comment for setting PATH --------- Co-authored-by: kapsakcj <[email protected]>
- Loading branch information
Showing
3 changed files
with
197 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 +1,129 @@ | ||
| FROM ubuntu:bionic as app | ||
|
|
||
| # for easy upgrade later. ARG variables only persist during build time | ||
| ARG SEQSERO2_VER="1.3.1" | ||
| ARG SPADES_VER="3.15.5" | ||
| ARG SAMTOOLS_VER="1.8" | ||
| ARG SALMID_VER="0.11" | ||
|
|
||
| # Metadata | ||
| LABEL base.image="ubuntu:bionic" | ||
| LABEL dockerfile.version="1" | ||
| LABEL software="SeqSero2" | ||
| LABEL software.version="${SEQSERO2_VER}" | ||
| LABEL description="Salmonella serotyping from genome sequencing data" | ||
| LABEL website="https://github.com/denglab/SeqSero2" | ||
| LABEL license="https://github.com/denglab/SeqSero2/blob/master/LICENSE" | ||
| LABEL maintainer="Erin Young" | ||
| LABEL maintainer.email="[email protected]" | ||
| LABEL maintainer1="Jake Garfin" | ||
| LABEL maintainer1.email="[email protected]" | ||
| LABEL maintainer2="Curtis Kapsak" | ||
| LABEL maintainer2.email="[email protected]" | ||
| LABEL maintainer3="Kelsey Florek" | ||
| LABEL maintainer3.email="[email protected]" | ||
|
|
||
| # python = 2.7.17 | ||
| # python3 = 3.6.9 | ||
| # biopython = 1.73 | ||
| # bedtools = 2.26.0 | ||
| # sra-toolkit = 2.8.2 | ||
| # bwa = 0.7.17 | ||
| # ncbi-blast+ = 2.6.0 | ||
| RUN apt-get update && apt-get install -y --no-install-recommends \ | ||
| python3 \ | ||
| python3-pip \ | ||
| python3-setuptools \ | ||
| bwa \ | ||
| ncbi-blast+ \ | ||
| sra-toolkit \ | ||
| bedtools \ | ||
| wget \ | ||
| ca-certificates \ | ||
| unzip \ | ||
| zlib1g-dev \ | ||
| libbz2-dev \ | ||
| liblzma-dev \ | ||
| build-essential \ | ||
| libncurses5-dev && \ | ||
| rm -rf /var/lib/apt/lists/* && apt-get autoclean | ||
|
|
||
| # Install samtools | ||
| RUN wget -q https://github.com/samtools/samtools/releases/download/${SAMTOOLS_VER}/samtools-${SAMTOOLS_VER}.tar.bz2 && \ | ||
| tar -xjf samtools-${SAMTOOLS_VER}.tar.bz2 && \ | ||
| rm -v samtools-${SAMTOOLS_VER}.tar.bz2 && \ | ||
| cd samtools-${SAMTOOLS_VER} && \ | ||
| ./configure && \ | ||
| make && \ | ||
| make install && \ | ||
| cd / && \ | ||
| rm -rfv /samtools-${SAMTOOLS_VER} | ||
|
|
||
| # Install salmID | ||
| RUN wget -q https://github.com/hcdenbakker/SalmID/archive/${SALMID_VER}.tar.gz && \ | ||
| tar -xzf ${SALMID_VER}.tar.gz && \ | ||
| rm -rvf ${SALMID_VER}.tar.gz | ||
|
|
||
| # install SPAdes binary | ||
| RUN wget -q https://github.com/ablab/spades/releases/download/v${SPADES_VER}/SPAdes-${SPADES_VER}-Linux.tar.gz && \ | ||
| tar -xzf SPAdes-${SPADES_VER}-Linux.tar.gz && \ | ||
| rm -r SPAdes-${SPADES_VER}-Linux.tar.gz | ||
|
|
||
| # Install SeqSero2; make /data | ||
| RUN wget -q https://github.com/denglab/SeqSero2/archive/v${SEQSERO2_VER}.tar.gz && \ | ||
| tar -xzf v${SEQSERO2_VER}.tar.gz && \ | ||
| rm -vrf v${SEQSERO2_VER}.tar.gz && \ | ||
| cd /SeqSero2-${SEQSERO2_VER}/ && \ | ||
| python3 -m pip install . && \ | ||
| mkdir /data | ||
|
|
||
| # set PATH for manually installed tools. SeqSero2 placed in PATH already with "pip install" cmd | ||
| ENV PATH="${PATH}:/SPAdes-${SPADES_VER}-Linux/bin:/SalmID-${SALMID_VER}:/samtools-${SAMTOOLS_VER}" \ | ||
| LC_ALL=C | ||
|
|
||
| CMD SeqSero2_package.py --help | ||
|
|
||
| WORKDIR /data | ||
|
|
||
| FROM app as test | ||
|
|
||
| WORKDIR /test | ||
|
|
||
| # install ncbi datasets tool (pre-compiled binary); place in $PATH | ||
| RUN wget -q https://ftp.ncbi.nlm.nih.gov/pub/datasets/command-line/LATEST/linux-amd64/datasets && \ | ||
| chmod +x datasets && \ | ||
| mv -v datasets /usr/local/bin | ||
|
|
||
| # download an example assembly; test with SeqSero2 | ||
| # Salmonella enterica serovar Infantis genome: https://www.ncbi.nlm.nih.gov/data-hub/genome/GCA_007765495.1/ | ||
| # BioSample:SAMN07684583 | ||
| ARG GENBANK_ACCESSION="GCA_007765495.1" | ||
| RUN datasets download genome accession ${GENBANK_ACCESSION} --filename ${GENBANK_ACCESSION}.zip && \ | ||
| mkdir -v ${GENBANK_ACCESSION}-download && \ | ||
| unzip ${GENBANK_ACCESSION}.zip -d ${GENBANK_ACCESSION}-download && \ | ||
| rm ${GENBANK_ACCESSION}.zip && \ | ||
| mv -v ${GENBANK_ACCESSION}-download/ncbi_dataset/data/${GENBANK_ACCESSION}/${GENBANK_ACCESSION}*.fna ${GENBANK_ACCESSION}-download/ncbi_dataset/data/${GENBANK_ACCESSION}/${GENBANK_ACCESSION}.genomic.fna && \ | ||
| SeqSero2_package.py \ | ||
| -i ${GENBANK_ACCESSION}-download/ncbi_dataset/data/${GENBANK_ACCESSION}/${GENBANK_ACCESSION}.genomic.fna \ | ||
| -t 4 \ | ||
| -m k \ | ||
| -d ${GENBANK_ACCESSION}-seqsero2-assembly-kmer-mode \ | ||
| -n ${GENBANK_ACCESSION} \ | ||
| -p 2 && \ | ||
| grep 'Infantis' ${GENBANK_ACCESSION}-seqsero2-assembly-kmer-mode/SeqSero_result.txt | ||
|
|
||
| # testing reads as input for the same Salmonella isolate | ||
| # specifically the "allele" mode which does micro assembly first using SPAdes | ||
| RUN wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR608/003/SRR6082043/SRR6082043_1.fastq.gz && \ | ||
| wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR608/003/SRR6082043/SRR6082043_2.fastq.gz && \ | ||
| SeqSero2_package.py \ | ||
| -i SRR6082043_1.fastq.gz SRR6082043_2.fastq.gz \ | ||
| -t 2 \ | ||
| -m a \ | ||
| -d SRR6082043-seqsero2-reads-allele-mode \ | ||
| -n SRR6082043 \ | ||
| -p 2 && \ | ||
| grep 'Infantis' SRR6082043-seqsero2-reads-allele-mode/SeqSero_result.txt | ||
|
|
||
| # print help options, check dependencies, print version | ||
| RUN SeqSero2_package.py --help && SeqSero2_package.py --check && SeqSero2_package.py --version |
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 +1,67 @@ | ||
| # SeqSero2 docker image | ||
|
|
||
| > SeqSero2: Salmonella enterica serotype prediction from genome sequencing data | ||
| Main tool : [SeqSero2](https://github.com/denglab/SeqSero2) | ||
|
|
||
| Additional tools: | ||
|
|
||
| - spades 3.15.5 | ||
| - ncbi-blast+ 2.6.0 | ||
| - python 2.7.17 | ||
| - python3 3.6.9 | ||
| - biopython 1.73 | ||
| - samtools 1.8 | ||
| - bedtools 2.26.0 | ||
| - SalmID 0.11 | ||
| - bwa 0.7.17-r1188 | ||
| - sra-toolkit 2.8.2 | ||
|
|
||
| ## Example Usage | ||
|
|
||
| ```bash | ||
| # paired end Illumina reads as input for allele mode | ||
| $ SeqSero2_package.py \ | ||
| -i SRR6082043_1.fastq.gz SRR6082043_2.fastq.gz \ | ||
| -t 2 \ | ||
| -m a \ | ||
| -d SRR6082043-seqsero2-reads-allele-mode \ | ||
| -n SRR6082043 \ | ||
| -p 2 | ||
| [bam_sort_core] merging from 0 files and 2 in-memory blocks... | ||
| building database... | ||
| mapping... | ||
| check samtools version: 1.9 | ||
| assembling... | ||
| blasting... | ||
|
|
||
| Sample name: SRR6082043 | ||
| Output directory: /test/SRR6082043-seqsero2-reads-allele-mode | ||
| Input files: /test/SRR6082043_1.fastq.gz /test/SRR6082043_2.fastq.gz | ||
| O antigen prediction: 7 | ||
| H1 antigen prediction(fliC): r | ||
| H2 antigen prediction(fljB): 1,5 | ||
| Predicted identification: Salmonella enterica subspecies enterica (subspecies I) | ||
| Predicted antigenic profile: 7:r:1,5 | ||
| Predicted serotype: Infantis | ||
| Note: | ||
|
|
||
| # genome assembly FASTA as input for kmer mode | ||
| $ SeqSero2_package.py \ | ||
| -i GCA_007765495.1.genomic.fna \ | ||
| -t 4 \ | ||
| -m k \ | ||
| -d GCA_007765495.1-seqsero2-assembly-kmer-mode \ | ||
| -n GCA_007765495.1 \ | ||
| -p 2 | ||
| Sample name: GCA_007765495.1 | ||
| Output directory: /test/GCA_007765495.1-seqsero2-assembly-kmer-mode | ||
| Input files: GCA_007765495.1.genomic.fna | ||
| O antigen prediction: 7 | ||
| H1 antigen prediction(fliC): r | ||
| H2 antigen prediction(fljB): 1,5 | ||
| Predicted identification: Salmonella enterica subspecies enterica (subspecies I) | ||
| Predicted antigenic profile: 7:r:1,5 | ||
| Predicted serotype: Infantis | ||
| Note: | ||
| ``` |