diff --git a/modules.json b/modules.json index 96f0efa..238a13c 100644 --- a/modules.json +++ b/modules.json @@ -34,6 +34,11 @@ "branch": "master", "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d", "installed_by": ["modules"] + }, + "samtools/sort": { + "branch": "master", + "git_sha": "b7800db9b069ed505db3f9d91b8c72faea9be17b", + "installed_by": ["modules"] } } }, diff --git a/modules/nf-core/samtools/sort/environment.yml b/modules/nf-core/samtools/sort/environment.yml new file mode 100644 index 0000000..62054fc --- /dev/null +++ b/modules/nf-core/samtools/sort/environment.yml @@ -0,0 +1,8 @@ +--- +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json +channels: + - conda-forge + - bioconda +dependencies: + - bioconda::htslib=1.21 + - bioconda::samtools=1.21 diff --git a/modules/nf-core/samtools/sort/main.nf b/modules/nf-core/samtools/sort/main.nf new file mode 100644 index 0000000..caf3c61 --- /dev/null +++ b/modules/nf-core/samtools/sort/main.nf @@ -0,0 +1,72 @@ +process SAMTOOLS_SORT { + tag "$meta.id" + label 'process_medium' + + conda "${moduleDir}/environment.yml" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/samtools:1.21--h50ea8bc_0' : + 'biocontainers/samtools:1.21--h50ea8bc_0' }" + + input: + tuple val(meta) , path(bam) + tuple val(meta2), path(fasta) + + output: + tuple val(meta), path("*.bam"), emit: bam, optional: true + tuple val(meta), path("*.cram"), emit: cram, optional: true + tuple val(meta), path("*.crai"), emit: crai, optional: true + tuple val(meta), path("*.csi"), emit: csi, optional: true + path "versions.yml", emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + def extension = args.contains("--output-fmt sam") ? "sam" : + args.contains("--output-fmt cram") ? "cram" : + "bam" + def reference = fasta ? "--reference ${fasta}" : "" + if ("$bam" == "${prefix}.bam") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!" + + """ + samtools cat \\ + ${bam} \\ + | \\ + samtools sort \\ + $args \\ + -T ${prefix} \\ + --threads $task.cpus \\ + ${reference} \\ + -o ${prefix}.${extension} \\ + - + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//') + END_VERSIONS + """ + + stub: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + def extension = args.contains("--output-fmt sam") ? "sam" : + args.contains("--output-fmt cram") ? "cram" : + "bam" + """ + touch ${prefix}.${extension} + if [ "${extension}" == "bam" ]; + then + touch ${prefix}.${extension}.csi + elif [ "${extension}" == "cram" ]; + then + touch ${prefix}.${extension}.crai + fi + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//') + END_VERSIONS + """ +} diff --git a/modules/nf-core/samtools/sort/meta.yml b/modules/nf-core/samtools/sort/meta.yml new file mode 100644 index 0000000..a9dbec5 --- /dev/null +++ b/modules/nf-core/samtools/sort/meta.yml @@ -0,0 +1,92 @@ +name: samtools_sort +description: Sort SAM/BAM/CRAM file +keywords: + - sort + - 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: http://www.htslib.org/doc/samtools.html + doi: 10.1093/bioinformatics/btp352 + licence: ["MIT"] + identifier: biotools:samtools +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(s) + pattern: "*.{bam,cram,sam}" + - - meta2: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome' ] + - fasta: + type: file + description: Reference genome FASTA file + pattern: "*.{fa,fasta,fna}" + optional: true +output: + - bam: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - "*.bam": + type: file + description: Sorted BAM file + pattern: "*.{bam}" + - cram: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - "*.cram": + type: file + description: Sorted CRAM file + pattern: "*.{cram}" + - crai: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - "*.crai": + type: file + description: CRAM index file (optional) + pattern: "*.crai" + - csi: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - "*.csi": + type: file + description: BAM index file (optional) + pattern: "*.csi" + - versions: + - versions.yml: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@drpatelh" + - "@ewels" + - "@matthdsm" +maintainers: + - "@drpatelh" + - "@ewels" + - "@matthdsm" diff --git a/modules/nf-core/samtools/sort/tests/main.nf.test b/modules/nf-core/samtools/sort/tests/main.nf.test new file mode 100644 index 0000000..b05e669 --- /dev/null +++ b/modules/nf-core/samtools/sort/tests/main.nf.test @@ -0,0 +1,192 @@ +nextflow_process { + + name "Test Process SAMTOOLS_SORT" + script "../main.nf" + process "SAMTOOLS_SORT" + tag "modules" + tag "modules_nfcore" + tag "samtools" + tag "samtools/sort" + + test("bam") { + + config "./nextflow.config" + + when { + process { + """ + input[0] = Channel.of([ + [ id:'test', single_end:false ], // meta map + file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.bam', checkIfExists: true) + ]) + input[1] = Channel.of([ + [ id:'fasta' ], // meta map + file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true) + ]) + """ + } + } + + then { + assertAll ( + { assert process.success }, + { assert snapshot( + process.out.bam, + process.out.csi.collect { it.collect { it instanceof Map ? it : file(it).name } }, + process.out.versions + ).match()} + ) + } + } + + test("multiple bam") { + + config "./nextflow.config" + + when { + process { + """ + input[0] = Channel.of([ + [ id:'test', single_end:false ], // meta map + [ + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam', checkIfExists: true) + ] + ]) + input[1] = Channel.of([ + [ id:'fasta' ], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) + ]) + """ + } + } + + then { + assertAll ( + { assert process.success }, + { assert snapshot( + process.out.bam, + process.out.csi.collect { it.collect { it instanceof Map ? it : file(it).name } }, + process.out.versions + ).match()} + ) + } + } + + test("cram") { + + config "./nextflow_cram.config" + + when { + process { + """ + input[0] = Channel.of([ + [ id:'test', single_end:false ], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram', checkIfExists: true) + ]) + input[1] = Channel.of([ + [ id:'fasta' ], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) + ]) + """ + } + } + + then { + assertAll ( + { assert process.success }, + { assert snapshot( + process.out.cram.collect { it.collect { it instanceof Map ? it : file(it).name } }, + process.out.crai.collect { it.collect { it instanceof Map ? it : file(it).name } }, + process.out.versions + ).match()} + ) + } + } + + test("bam - stub") { + + options "-stub" + config "./nextflow.config" + + when { + process { + """ + input[0] = Channel.of([ + [ id:'test', single_end:false ], // meta map + file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.bam', checkIfExists: true) + ]) + input[1] = Channel.of([ + [ id:'fasta' ], // meta map + file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true) + ]) + """ + } + } + + then { + assertAll ( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + } + + test("multiple bam - stub") { + + config "./nextflow.config" + + when { + process { + """ + input[0] = Channel.of([ + [ id:'test', single_end:false ], // meta map + [ + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.sorted.bam', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test2.paired_end.sorted.bam', checkIfExists: true) + ] + ]) + input[1] = Channel.of([ + [ id:'fasta' ], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) + ]) + """ + } + } + + then { + assertAll ( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + } + + test("cram - stub") { + + options "-stub" + config "./nextflow_cram.config" + + when { + process { + """ + input[0] = Channel.of([ + [ id:'test', single_end:false ], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram', checkIfExists: true) + ]) + input[1] = Channel.of([ + [ id:'fasta' ], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true) + ]) + """ + } + } + + then { + assertAll ( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + } +} diff --git a/modules/nf-core/samtools/sort/tests/main.nf.test.snap b/modules/nf-core/samtools/sort/tests/main.nf.test.snap new file mode 100644 index 0000000..469891f --- /dev/null +++ b/modules/nf-core/samtools/sort/tests/main.nf.test.snap @@ -0,0 +1,287 @@ +{ + "cram": { + "content": [ + [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.cram" + ] + ], + [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.cram.crai" + ] + ], + [ + "versions.yml:md5,2659b187d681241451539d4c53500b9f" + ] + ], + "meta": { + "nf-test": "0.9.0", + "nextflow": "24.04.4" + }, + "timestamp": "2024-09-16T08:49:58.207549273" + }, + "bam - stub": { + "content": [ + { + "0": [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.bam:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "1": [ + + ], + "2": [ + + ], + "3": [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.bam.csi:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "4": [ + "versions.yml:md5,2659b187d681241451539d4c53500b9f" + ], + "bam": [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.bam:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "crai": [ + + ], + "cram": [ + + ], + "csi": [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.bam.csi:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "versions": [ + "versions.yml:md5,2659b187d681241451539d4c53500b9f" + ] + } + ], + "meta": { + "nf-test": "0.9.0", + "nextflow": "24.04.4" + }, + "timestamp": "2024-09-16T08:50:08.630951018" + }, + "cram - stub": { + "content": [ + { + "0": [ + + ], + "1": [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.cram:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "2": [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.cram.crai:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "3": [ + + ], + "4": [ + "versions.yml:md5,2659b187d681241451539d4c53500b9f" + ], + "bam": [ + + ], + "crai": [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.cram.crai:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "cram": [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.cram:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "csi": [ + + ], + "versions": [ + "versions.yml:md5,2659b187d681241451539d4c53500b9f" + ] + } + ], + "meta": { + "nf-test": "0.9.0", + "nextflow": "24.04.4" + }, + "timestamp": "2024-09-16T08:50:19.061912443" + }, + "multiple bam": { + "content": [ + [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.bam:md5,8a16ba90c7d294cbb4c33ac0f7127a12" + ] + ], + [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.bam.csi" + ] + ], + [ + "versions.yml:md5,2659b187d681241451539d4c53500b9f" + ] + ], + "meta": { + "nf-test": "0.9.0", + "nextflow": "24.09.0" + }, + "timestamp": "2024-10-08T11:59:55.479443" + }, + "multiple bam - stub": { + "content": [ + { + "0": [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.bam:md5,8a16ba90c7d294cbb4c33ac0f7127a12" + ] + ], + "1": [ + + ], + "2": [ + + ], + "3": [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.bam.csi:md5,d185916eaff9afeb4d0aeab3310371f9" + ] + ], + "4": [ + "versions.yml:md5,2659b187d681241451539d4c53500b9f" + ], + "bam": [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.bam:md5,8a16ba90c7d294cbb4c33ac0f7127a12" + ] + ], + "crai": [ + + ], + "cram": [ + + ], + "csi": [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.bam.csi:md5,d185916eaff9afeb4d0aeab3310371f9" + ] + ], + "versions": [ + "versions.yml:md5,2659b187d681241451539d4c53500b9f" + ] + } + ], + "meta": { + "nf-test": "0.9.0", + "nextflow": "24.09.0" + }, + "timestamp": "2024-10-08T11:36:13.781404" + }, + "bam": { + "content": [ + [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.bam:md5,34aa85e86abefe637f7a4a9887f016fc" + ] + ], + [ + [ + { + "id": "test", + "single_end": false + }, + "test.sorted.bam.csi" + ] + ], + [ + "versions.yml:md5,2659b187d681241451539d4c53500b9f" + ] + ], + "meta": { + "nf-test": "0.9.0", + "nextflow": "24.09.0" + }, + "timestamp": "2024-10-08T11:59:46.372244" + } +} \ No newline at end of file diff --git a/modules/nf-core/samtools/sort/tests/nextflow.config b/modules/nf-core/samtools/sort/tests/nextflow.config new file mode 100644 index 0000000..f642771 --- /dev/null +++ b/modules/nf-core/samtools/sort/tests/nextflow.config @@ -0,0 +1,8 @@ +process { + + withName: SAMTOOLS_SORT { + ext.prefix = { "${meta.id}.sorted" } + ext.args = "--write-index" + } + +} diff --git a/modules/nf-core/samtools/sort/tests/nextflow_cram.config b/modules/nf-core/samtools/sort/tests/nextflow_cram.config new file mode 100644 index 0000000..3a8c018 --- /dev/null +++ b/modules/nf-core/samtools/sort/tests/nextflow_cram.config @@ -0,0 +1,8 @@ +process { + + withName: SAMTOOLS_SORT { + ext.prefix = { "${meta.id}.sorted" } + ext.args = "--write-index --output-fmt cram" + } + +} diff --git a/modules/nf-core/samtools/sort/tests/tags.yml b/modules/nf-core/samtools/sort/tests/tags.yml new file mode 100644 index 0000000..cd63ea2 --- /dev/null +++ b/modules/nf-core/samtools/sort/tests/tags.yml @@ -0,0 +1,3 @@ +samtools/sort: + - modules/nf-core/samtools/sort/** + - tests/modules/nf-core/samtools/sort/**