From 3eedca9bb4f7d16232ebfca8a80a166f59d9fa58 Mon Sep 17 00:00:00 2001 From: JoseEspinosa Date: Fri, 29 Jan 2021 17:18:45 +0100 Subject: [PATCH 1/5] Add samtools_view --- .github/workflows/samtools_view.yml | 40 ++++++++++++++++++ software/samtools/view/functions.nf | 59 ++++++++++++++++++++++++++ software/samtools/view/main.nf | 34 +++++++++++++++ software/samtools/view/meta.yml | 64 +++++++++++++++++++++++++++++ tests/software/samtools/main.nf | 10 +++++ tests/software/samtools/test.yml | 9 ++++ 6 files changed, 216 insertions(+) create mode 100644 .github/workflows/samtools_view.yml create mode 100644 software/samtools/view/functions.nf create mode 100644 software/samtools/view/main.nf create mode 100644 software/samtools/view/meta.yml diff --git a/.github/workflows/samtools_view.yml b/.github/workflows/samtools_view.yml new file mode 100644 index 00000000..a73ef9e3 --- /dev/null +++ b/.github/workflows/samtools_view.yml @@ -0,0 +1,40 @@ +name: samtools_view +on: + push: + paths: + - software/samtools/view/** + - .github/workflows/samtools_view.yml + - tests/software/samtools/** + pull_request: + paths: + - software/samtools/view/** + - .github/workflows/samtools_view.yml + - tests/software/samtools/** + +jobs: + ci_test: + runs-on: ubuntu-latest + strategy: + matrix: + nxf_version: [20.11.0-edge] + env: + NXF_ANSI_LOG: false + steps: + - uses: actions/checkout@v2 + + - name: Install Nextflow + env: + NXF_VER: ${{ matrix.nxf_version }} + run: | + wget -qO- get.nextflow.io | bash + sudo mv nextflow /usr/local/bin/ + + - name: Set up Python + uses: actions/setup-python@v2 + with: + python-version: "3.x" + - name: Install dependencies + run: python -m pip install --upgrade pip pytest-workflow + + # Test the module + - run: pytest --tag samtools_view --symlink --wt 2 diff --git a/software/samtools/view/functions.nf b/software/samtools/view/functions.nf new file mode 100644 index 00000000..d25eea86 --- /dev/null +++ b/software/samtools/view/functions.nf @@ -0,0 +1,59 @@ +/* + * ----------------------------------------------------- + * Utility functions used in nf-core DSL2 module files + * ----------------------------------------------------- + */ + +/* + * Extract name of software tool from process name using $task.process + */ +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +/* + * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules + */ +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.publish_by_id = args.publish_by_id ?: false + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +/* + * Tidy up and join elements of a list to return a path string + */ +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +/* + * Function to save/publish module results + */ +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_id) { + path_list.add(args.publish_id) + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/software/samtools/view/main.nf b/software/samtools/view/main.nf new file mode 100644 index 00000000..c1fcd417 --- /dev/null +++ b/software/samtools/view/main.nf @@ -0,0 +1,34 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +def options = initOptions(params.options) + +process SAMTOOLS_VIEW { + tag "$meta.id" + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) } + + conda (params.enable_conda ? "bioconda::samtools=1.10" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/samtools:1.10--h9402c20_2" + } else { + container "quay.io/biocontainers/samtools:1.10--h9402c20_2" + } + + input: + tuple val(meta), path(bam) + + output: + tuple val(meta), path("*.bam"), emit: bam + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + samtools view $options.args $bam > ${prefix}.bam + echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt + """ +} \ No newline at end of file diff --git a/software/samtools/view/meta.yml b/software/samtools/view/meta.yml new file mode 100644 index 00000000..773b40b1 --- /dev/null +++ b/software/samtools/view/meta.yml @@ -0,0 +1,64 @@ +name: samtools_view +description: filter/convert SAM/BAM/CRAM file +keywords: + - view + - bam + - sam + - cram +tools: + - samtools: + description: | + SAMtools is a set of utilities for interacting with and post-processing + short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. + These files are generated as output by short read aligners like BWA. + homepage: http://www.htslib.org/ + documentation: hhttp://www.htslib.org/doc/samtools.html + doi: 10.1093/bioinformatics/btp352 +params: + - outdir: + type: string + description: | + The pipeline's output directory. By default, the module will + output files into `$params.outdir/` + - publish_dir_mode: + type: string + description: | + Value for the Nextflow `publishDir` mode parameter. + Available: symlink, rellink, link, copy, copyNoFollow, move. + - enable_conda: + type: boolean + description: | + Run the module with Conda using the software specified + via the `conda` directive + - singularity_pull_docker_container: + type: boolean + description: | + Instead of directly downloading Singularity images for use with Singularity, + force the workflow to pull and convert Docker containers instead. +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: filtered/converted BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@joseespinosa" diff --git a/tests/software/samtools/main.nf b/tests/software/samtools/main.nf index 747a1293..e0d430ae 100644 --- a/tests/software/samtools/main.nf +++ b/tests/software/samtools/main.nf @@ -7,6 +7,7 @@ include { SAMTOOLS_IDXSTATS } from '../../../software/samtools/idxstats/main.nf' include { SAMTOOLS_INDEX } from '../../../software/samtools/index/main.nf' addParams( options: [:] ) include { SAMTOOLS_SORT } from '../../../software/samtools/sort/main.nf' addParams( options: [:] ) include { SAMTOOLS_STATS } from '../../../software/samtools/stats/main.nf' addParams( options: [:] ) +include { SAMTOOLS_VIEW } from '../../../software/samtools/view/main.nf' addParams( options: [:] ) workflow test_samtools_flagstat { @@ -56,3 +57,12 @@ workflow test_samtools_stats { SAMTOOLS_STATS ( input ) } + +workflow test_samtools_view { + + def input = [] + input = [ [ id:'test', single_end:false ], // meta map + file("${launchDir}/tests/data/bam/test.paired_end.sorted.bam", checkIfExists: true) ] + + SAMTOOLS_VIEW ( input ) +} diff --git a/tests/software/samtools/test.yml b/tests/software/samtools/test.yml index d4e61907..d7d969e4 100644 --- a/tests/software/samtools/test.yml +++ b/tests/software/samtools/test.yml @@ -42,3 +42,12 @@ files: - path: output/samtools/test.paired_end.sorted.bam.stats md5sum: 06c183864d6e47ab89b0650cae831a93 + +- name: Run samtools view test workflow + command: nextflow run ./tests/software/samtools/ -profile docker -entry test_samtools_view -c tests/config/nextflow.config + tags: + - samtools + - samtools_view + files: + - path: output/samtools/test.bam + md5sum: 7ea2c325e2249ed7ef44e1d9fdc4f8ff From 22dcdc692dd28eb9e990f293969b592ece4e4c46 Mon Sep 17 00:00:00 2001 From: JoseEspinosa Date: Fri, 29 Jan 2021 17:58:42 +0100 Subject: [PATCH 2/5] Adding samtools_mpileup module --- .github/workflows/samtools_mpileup.yml | 40 +++++++++++++++ software/samtools/mpileup/functions.nf | 59 ++++++++++++++++++++++ software/samtools/mpileup/main.nf | 40 +++++++++++++++ software/samtools/mpileup/meta.yml | 68 ++++++++++++++++++++++++++ tests/software/samtools/main.nf | 12 +++++ tests/software/samtools/test.yml | 9 ++++ 6 files changed, 228 insertions(+) create mode 100644 .github/workflows/samtools_mpileup.yml create mode 100644 software/samtools/mpileup/functions.nf create mode 100644 software/samtools/mpileup/main.nf create mode 100644 software/samtools/mpileup/meta.yml diff --git a/.github/workflows/samtools_mpileup.yml b/.github/workflows/samtools_mpileup.yml new file mode 100644 index 00000000..76d92996 --- /dev/null +++ b/.github/workflows/samtools_mpileup.yml @@ -0,0 +1,40 @@ +name: samtools_mpileup +on: + push: + paths: + - software/samtools/mpileup/** + - .github/workflows/samtools_mpileup.yml + - tests/software/samtools/** + pull_request: + paths: + - software/samtools/mpileup/** + - .github/workflows/samtools_mpileup.yml + - tests/software/samtools/** + +jobs: + ci_test: + runs-on: ubuntu-latest + strategy: + matrix: + nxf_version: [20.11.0-edge] + env: + NXF_ANSI_LOG: false + steps: + - uses: actions/checkout@v2 + + - name: Install Nextflow + env: + NXF_VER: ${{ matrix.nxf_version }} + run: | + wget -qO- get.nextflow.io | bash + sudo mv nextflow /usr/local/bin/ + + - name: Set up Python + uses: actions/setup-python@v2 + with: + python-version: "3.x" + - name: Install dependencies + run: python -m pip install --upgrade pip pytest-workflow + + # Test the module + - run: pytest --tag samtools_mpileup --symlink --wt 2 diff --git a/software/samtools/mpileup/functions.nf b/software/samtools/mpileup/functions.nf new file mode 100644 index 00000000..d25eea86 --- /dev/null +++ b/software/samtools/mpileup/functions.nf @@ -0,0 +1,59 @@ +/* + * ----------------------------------------------------- + * Utility functions used in nf-core DSL2 module files + * ----------------------------------------------------- + */ + +/* + * Extract name of software tool from process name using $task.process + */ +def getSoftwareName(task_process) { + return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase() +} + +/* + * Function to initialise default values and to generate a Groovy Map of available options for nf-core modules + */ +def initOptions(Map args) { + def Map options = [:] + options.args = args.args ?: '' + options.args2 = args.args2 ?: '' + options.publish_by_id = args.publish_by_id ?: false + options.publish_dir = args.publish_dir ?: '' + options.publish_files = args.publish_files + options.suffix = args.suffix ?: '' + return options +} + +/* + * Tidy up and join elements of a list to return a path string + */ +def getPathFromList(path_list) { + def paths = path_list.findAll { item -> !item?.trim().isEmpty() } // Remove empty entries + paths = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes + return paths.join('/') +} + +/* + * Function to save/publish module results + */ +def saveFiles(Map args) { + if (!args.filename.endsWith('.version.txt')) { + def ioptions = initOptions(args.options) + def path_list = [ ioptions.publish_dir ?: args.publish_dir ] + if (ioptions.publish_by_id) { + path_list.add(args.publish_id) + } + if (ioptions.publish_files instanceof Map) { + for (ext in ioptions.publish_files) { + if (args.filename.endsWith(ext.key)) { + def ext_list = path_list.collect() + ext_list.add(ext.value) + return "${getPathFromList(ext_list)}/$args.filename" + } + } + } else if (ioptions.publish_files == null) { + return "${getPathFromList(path_list)}/$args.filename" + } + } +} diff --git a/software/samtools/mpileup/main.nf b/software/samtools/mpileup/main.nf new file mode 100644 index 00000000..9b7c2d28 --- /dev/null +++ b/software/samtools/mpileup/main.nf @@ -0,0 +1,40 @@ +// Import generic module functions +include { initOptions; saveFiles; getSoftwareName } from './functions' + +params.options = [:] +def options = initOptions(params.options) + +process SAMTOOLS_MPILEUP { + tag "$meta.id" + label 'process_medium' + publishDir "${params.outdir}", + mode: params.publish_dir_mode, + saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) } + + conda (params.enable_conda ? "bioconda::samtools=1.10" : null) + if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) { + container "https://depot.galaxyproject.org/singularity/samtools:1.10--h9402c20_2" + } else { + container "quay.io/biocontainers/samtools:1.10--h9402c20_2" + } + + input: + tuple val(meta), path(bam) + path fasta + + output: + tuple val(meta), path("*.mpileup"), emit: mpileup + path "*.version.txt" , emit: version + + script: + def software = getSoftwareName(task.process) + def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}" + """ + samtools mpileup \\ + --fasta-ref $fasta \\ + --output ${prefix}.mpileup \\ + $options.args \\ + $bam + echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt + """ +} \ No newline at end of file diff --git a/software/samtools/mpileup/meta.yml b/software/samtools/mpileup/meta.yml new file mode 100644 index 00000000..9a4ec226 --- /dev/null +++ b/software/samtools/mpileup/meta.yml @@ -0,0 +1,68 @@ +name: samtools_mpileup +description: BAM +keywords: + - mpileup + - bam + - sam + - cram +tools: + - samtools: + description: | + SAMtools is a set of utilities for interacting with and post-processing + short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. + These files are generated as output by short read aligners like BWA. + homepage: http://www.htslib.org/ + documentation: hhttp://www.htslib.org/doc/samtools.html + doi: 10.1093/bioinformatics/btp352 +params: + - outdir: + type: string + description: | + The pipeline's output directory. By default, the module will + output files into `$params.outdir/` + - publish_dir_mode: + type: string + description: | + Value for the Nextflow `publishDir` mode parameter. + Available: symlink, rellink, link, copy, copyNoFollow, move. + - enable_conda: + type: boolean + description: | + Run the module with Conda using the software specified + via the `conda` directive + - singularity_pull_docker_container: + type: boolean + description: | + Instead of directly downloading Singularity images for use with Singularity, + force the workflow to pull and convert Docker containers instead. +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + - fasta-ref: + type: file + description: FASTA reference file + pattern: "*.{fasta,fa}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - mpileup: + type: file + description: mpileup file + pattern: "*.{mpileup}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@drpatelh" + - "@joseespinosa" diff --git a/tests/software/samtools/main.nf b/tests/software/samtools/main.nf index e0d430ae..bf96ae07 100644 --- a/tests/software/samtools/main.nf +++ b/tests/software/samtools/main.nf @@ -8,6 +8,7 @@ include { SAMTOOLS_INDEX } from '../../../software/samtools/index/main.nf' addPa include { SAMTOOLS_SORT } from '../../../software/samtools/sort/main.nf' addParams( options: [:] ) include { SAMTOOLS_STATS } from '../../../software/samtools/stats/main.nf' addParams( options: [:] ) include { SAMTOOLS_VIEW } from '../../../software/samtools/view/main.nf' addParams( options: [:] ) +include { SAMTOOLS_MPILEUP } from '../../../software/samtools/mpileup/main.nf' addParams( options: [:] ) workflow test_samtools_flagstat { @@ -66,3 +67,14 @@ workflow test_samtools_view { SAMTOOLS_VIEW ( input ) } + +workflow test_samtools_mpileup { + + def input = [] + def fasta = [] + input = [ [ id:'test', single_end:false ], // meta map + file("${launchDir}/tests/data/bam/test.paired_end.sorted.bam", checkIfExists: true) ] + fasta = [ file("${launchDir}/tests/data/fasta/E_coli/NC_010473.fa", checkIfExists: true) ] + + SAMTOOLS_MPILEUP ( input, fasta ) +} diff --git a/tests/software/samtools/test.yml b/tests/software/samtools/test.yml index d7d969e4..de2df680 100644 --- a/tests/software/samtools/test.yml +++ b/tests/software/samtools/test.yml @@ -51,3 +51,12 @@ files: - path: output/samtools/test.bam md5sum: 7ea2c325e2249ed7ef44e1d9fdc4f8ff + +- name: Run samtools mpileup test workflow + command: nextflow run ./tests/software/samtools/ -profile docker -entry test_samtools_mpileup -c tests/config/nextflow.config + tags: + - samtools + - samtools_mpileup + files: + - path: output/samtools/test.bam + md5sum: 95c2646fa7bd535207722008c581c81d From 13e9f811601cb4865da10c6806a3d31346c9c323 Mon Sep 17 00:00:00 2001 From: JoseEspinosa Date: Fri, 29 Jan 2021 18:01:58 +0100 Subject: [PATCH 3/5] Fixing lint tests --- software/samtools/mpileup/main.nf | 2 +- software/samtools/mpileup/meta.yml | 2 +- software/samtools/view/main.nf | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/software/samtools/mpileup/main.nf b/software/samtools/mpileup/main.nf index 9b7c2d28..662588fd 100644 --- a/software/samtools/mpileup/main.nf +++ b/software/samtools/mpileup/main.nf @@ -37,4 +37,4 @@ process SAMTOOLS_MPILEUP { $bam echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt """ -} \ No newline at end of file +} diff --git a/software/samtools/mpileup/meta.yml b/software/samtools/mpileup/meta.yml index 9a4ec226..5e7fcc89 100644 --- a/software/samtools/mpileup/meta.yml +++ b/software/samtools/mpileup/meta.yml @@ -48,7 +48,7 @@ input: - fasta-ref: type: file description: FASTA reference file - pattern: "*.{fasta,fa}" + pattern: "*.{fasta,fa}" output: - meta: type: map diff --git a/software/samtools/view/main.nf b/software/samtools/view/main.nf index c1fcd417..968fcc4c 100644 --- a/software/samtools/view/main.nf +++ b/software/samtools/view/main.nf @@ -31,4 +31,4 @@ process SAMTOOLS_VIEW { samtools view $options.args $bam > ${prefix}.bam echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//' > ${software}.version.txt """ -} \ No newline at end of file +} From 720db2bed523eb87d85da92a0561716abc59c6fb Mon Sep 17 00:00:00 2001 From: JoseEspinosa Date: Fri, 29 Jan 2021 18:21:03 +0100 Subject: [PATCH 4/5] Fixing samtools_mpileup test --- tests/software/samtools/test.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/software/samtools/test.yml b/tests/software/samtools/test.yml index de2df680..5fc3b47c 100644 --- a/tests/software/samtools/test.yml +++ b/tests/software/samtools/test.yml @@ -58,5 +58,5 @@ - samtools - samtools_mpileup files: - - path: output/samtools/test.bam + - path: output/samtools/test.mpileup md5sum: 95c2646fa7bd535207722008c581c81d From eb7a3861dbbecd14a0b36f5ff8be0cfde9b07e3c Mon Sep 17 00:00:00 2001 From: Harshil Patel Date: Fri, 29 Jan 2021 18:12:17 +0000 Subject: [PATCH 5/5] Update software/samtools/mpileup/meta.yml --- software/samtools/mpileup/meta.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/software/samtools/mpileup/meta.yml b/software/samtools/mpileup/meta.yml index 5e7fcc89..5494b13b 100644 --- a/software/samtools/mpileup/meta.yml +++ b/software/samtools/mpileup/meta.yml @@ -45,7 +45,7 @@ input: type: file description: BAM/CRAM/SAM file pattern: "*.{bam,cram,sam}" - - fasta-ref: + - fasta: type: file description: FASTA reference file pattern: "*.{fasta,fa}"