diff --git a/conf/modules/dysgu.config b/conf/modules/dysgu.config new file mode 100644 index 0000000000..f637ae4cc3 --- /dev/null +++ b/conf/modules/dysgu.config @@ -0,0 +1,26 @@ +/* +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Config file for defining DSL2 per module options and publishing paths +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Available keys to override module options: + ext.args = Additional arguments appended to command in module. + ext.args2 = Second set of arguments appended to command in module (multi-tool modules). + ext.args3 = Third set of arguments appended to command in module (multi-tool modules). + ext.prefix = File name prefix for output files. + ext.when = When to run the module. +---------------------------------------------------------------------------------------- +*/ + +// DYSGU + +process { + withName: 'DYSGU' { + ext.args = { params.wes ? "--exome" : '' } + ext.prefix = { "${meta.id}.dysgu" } + publishDir = [ + mode: params.publish_dir_mode, + path: { "${params.outdir}/variant_calling/dysgu/${meta.id}" }, + pattern: "*.{vcf.gz,vcf.gz.tbi}" + ] + } +} diff --git a/docs/output.md b/docs/output.md index 7f8455f95d..45562b60c1 100644 --- a/docs/output.md +++ b/docs/output.md @@ -45,6 +45,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d - [Structural Variants](#structural-variants) - [Manta](#manta) - [TIDDIT](#tiddit) + - [DYSGU](#dysgu) - [Sample heterogeneity, ploidy and CNVs](#sample-heterogeneity-ploidy-and-cnvs) - [ASCAT](#ascat) - [CNVKit](#cnvkit) @@ -639,6 +640,18 @@ It is optimized for analysis of germline variation in small sets of individuals +#### DYSGU + +[DYSGU](https://github.com/kcleal/dysgu) dysgu (pronounced duss-key) is a set of command line tools and python-API, for calling structural variants using paired-end or long read sequencing data. For further reading and documentation see the [DYSGU manual](https://github.com/kcleal/dysgu/blob/master/README.rst). + +
+Output files for normal samples + +**Output directory: `{outdir}/variantcalling/dysgu//`** + +- `.dysgu.vcf.gz` and `.dysgu.vcf.gz.tbi` + - VCF with tabix index containing SV calls + ### Sample heterogeneity, ploidy and CNVs #### ASCAT diff --git a/modules.json b/modules.json index 26d801647b..5627439759 100644 --- a/modules.json +++ b/modules.json @@ -139,6 +139,11 @@ "installed_by": ["modules"], "patch": "modules/nf-core/dragmap/hashtable/dragmap-hashtable.diff" }, + "dysgu": { + "branch": "master", + "git_sha": "c27498285a0beca2239b395cf88129c586a837fc", + "installed_by": ["modules"] + }, "ensemblvep/download": { "branch": "master", "git_sha": "3db4f8488315cd7d7cf3fcb64251f6603210e831", diff --git a/modules/nf-core/deepvariant/main.nf b/modules/nf-core/deepvariant/main.nf index 507b6c1174..ed95f066be 100644 --- a/modules/nf-core/deepvariant/main.nf +++ b/modules/nf-core/deepvariant/main.nf @@ -38,8 +38,8 @@ process DEEPVARIANT { --output_gvcf=${prefix}.g.vcf.gz \\ ${args} \\ ${regions} \\ - --intermediate_results_dir=. \\ - --num_shards=${task.cpus} + --intermediate_results_dir=tmp \\ + --num_shards=1 cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/nf-core/dragmap/align/main.nf b/modules/nf-core/dragmap/align/main.nf index 30e47992f3..7c831063c2 100644 --- a/modules/nf-core/dragmap/align/main.nf +++ b/modules/nf-core/dragmap/align/main.nf @@ -3,7 +3,7 @@ process DRAGMAP_ALIGN { label 'process_high' conda "${moduleDir}/environment.yml" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/mulled-v2-580d344d9d4a496cd403932da8765f9e0187774d:df80ed8d23d0a2c43181a2b3dd1b39f2d00fab5c-0': 'biocontainers/mulled-v2-580d344d9d4a496cd403932da8765f9e0187774d:df80ed8d23d0a2c43181a2b3dd1b39f2d00fab5c-0' }" diff --git a/modules/nf-core/dysgu/environment.yml b/modules/nf-core/dysgu/environment.yml new file mode 100644 index 0000000000..5efb6db61a --- /dev/null +++ b/modules/nf-core/dysgu/environment.yml @@ -0,0 +1,7 @@ +name: dysgu +channels: + - conda-forge + - bioconda + - defaults +dependencies: + - dysgu diff --git a/modules/nf-core/dysgu/main.nf b/modules/nf-core/dysgu/main.nf new file mode 100644 index 0000000000..17c4d381c3 --- /dev/null +++ b/modules/nf-core/dysgu/main.nf @@ -0,0 +1,56 @@ +process DYSGU { + tag "$meta.id" + label 'process_medium' + + conda "${moduleDir}/environment.yml" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'oras://community.wave.seqera.io/library/dysgu:48830f55112c399e': + 'community.wave.seqera.io/library/dysgu:faf71ac972284412' }" + + input: + tuple val(meta), path(input), path(index) + tuple val(meta2), path(fasta) + tuple val(meta3), path(fai) + + output: + tuple val(meta), path('*.vcf.gz') , emit: vcf + tuple val(meta), path('*.vcf.gz.tbi') , emit: tbi + path 'versions.yml' , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def args2 = task.ext.args2 ?: '' + def args3 = task.ext.args3 ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + """ + dysgu run \\ + -p ${task.cpus} \\ + -x \\ + $fasta \\ + . \\ + $input \\ + | bgzip ${args2} --threads ${task.cpus} --stdout > ${prefix}.vcf.gz + tabix ${args3} ${prefix}.vcf.gz + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + dysgu: \$(dysgu --version 2>&1) + END_VERSIONS + """ + + stub: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + """ + echo "" | gzip > ${prefix}.vcf.gz + touch ${prefix}.vcf.gz.tbi + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + dysgu: \$(dysgu --version 2>&1) + END_VERSIONS + """ +} diff --git a/modules/nf-core/dysgu/meta.yml b/modules/nf-core/dysgu/meta.yml new file mode 100644 index 0000000000..67c6c70abf --- /dev/null +++ b/modules/nf-core/dysgu/meta.yml @@ -0,0 +1,68 @@ +name: dysgu + +description: Dysgu calls structural variants (SVs) from mapped sequencing reads. It is designed for accurate and efficient detection of structural variations. +keywords: + - structural variants + - sv + - vcf +tools: + - dysgu: + description: Structural variant caller for mapped sequencing data + homepage: https://github.com/kcleal/dysgu + documentation: https://github.com/kcleal/dysgu/blob/master/README.rst + tool_dev_url: https://github.com/kcleal/dysgu + doi: "10.1093/nar/gkac039" + licence: ["GPL-3.0-or-later"] + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. `[ id:'sample1' ]` + - input: + type: file + description: Input BAM file + pattern: "*.bam" + - index: + type: file + description: BAM index file + pattern: "*.bai" + - fasta: + type: file + description: Genome reference FASTA file + pattern: "*.{fa,fasta}" + - meta2: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome' ] + - fai: + type: file + description: Genome reference FASTA index file + pattern: "*.{fa.fai,fasta.fai}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'sample1' ] + - vcf: + type: file + description: VCF file with identified structural variants + pattern: "*.{vcf.gz}" + - tbi: + type: file + description: The index of the BCF/VCF file + pattern: "*.{vcf.gz.tbi}" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" + +authors: + - "@famosab" + - "@poddarharsh15" +maintainers: + - "@poddarharsh15" diff --git a/modules/nf-core/dysgu/tests/main.nf.test b/modules/nf-core/dysgu/tests/main.nf.test new file mode 100644 index 0000000000..1714b5b7ab --- /dev/null +++ b/modules/nf-core/dysgu/tests/main.nf.test @@ -0,0 +1,96 @@ +nextflow_process { + + name "Test Process DYSGU" + script "../main.nf" + process "DYSGU" + config "./nextflow.config" + tag "modules" + tag "modules_nfcore" + tag "dysgu" + + + test("human - bam") { + + when { + process { + """ + input[0] = [ [ id:'test'], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.recalibrated.sorted.bam', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.recalibrated.sorted.bam.bai', checkIfExists: true) + ] + input[1] = [ [ id:'reference'], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai', checkIfExists: true) + ] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out.versions).match() }, + { assert path(process.out.vcf.get(0).get(1)).linesGzip.contains("##fileformat=VCFv4.2") } + ) + } + + } + + + test("human - cram") { + + when { + process { + """ + input[0] = [ [ id:'test'], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/cram/test.paired_end.recalibrated.sorted.cram.crai', checkIfExists: true) + ] + input[1] = [ [ id:'reference'], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai', checkIfExists: true) + ] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out.versions).match() }, + { assert path(process.out.vcf.get(0).get(1)).linesGzip.contains("##fileformat=VCFv4.2") } + ) + } + + } + + + test("human - bam - stub") { + + options "-stub" + + when { + process { + """ + input[0] = [ [ id:'test'], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.recalibrated.sorted.bam', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/bam/test.paired_end.recalibrated.sorted.bam.bai', checkIfExists: true) + ] + input[1] = [ [ id:'reference'], // meta map + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/chr21/sequence/genome.fasta.fai', checkIfExists: true) + ] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + + } + +} \ No newline at end of file diff --git a/modules/nf-core/dysgu/tests/main.nf.test.snap b/modules/nf-core/dysgu/tests/main.nf.test.snap new file mode 100644 index 0000000000..ecf725f5d3 --- /dev/null +++ b/modules/nf-core/dysgu/tests/main.nf.test.snap @@ -0,0 +1,75 @@ +{ + "human - bam - stub": { + "content": [ + { + "0": [ + [ + { + "id": "test" + }, + "test.vcf.gz:md5,68b329da9893e34099c7d8ad5cb9c940" + ] + ], + "1": [ + [ + { + "id": "test" + }, + "test.vcf.gz.tbi:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "2": [ + "versions.yml:md5,cf1e0487502108690603dd16f034bf5e" + ], + "tbi": [ + [ + { + "id": "test" + }, + "test.vcf.gz.tbi:md5,d41d8cd98f00b204e9800998ecf8427e" + ] + ], + "vcf": [ + [ + { + "id": "test" + }, + "test.vcf.gz:md5,68b329da9893e34099c7d8ad5cb9c940" + ] + ], + "versions": [ + "versions.yml:md5,cf1e0487502108690603dd16f034bf5e" + ] + } + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "24.04.2" + }, + "timestamp": "2024-07-08T13:18:45.660262" + }, + "human - bam": { + "content": [ + [ + "versions.yml:md5,cf1e0487502108690603dd16f034bf5e" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "24.04.2" + }, + "timestamp": "2024-07-08T13:19:56.62312" + }, + "human - cram": { + "content": [ + [ + "versions.yml:md5,cf1e0487502108690603dd16f034bf5e" + ] + ], + "meta": { + "nf-test": "0.8.4", + "nextflow": "24.04.2" + }, + "timestamp": "2024-07-08T13:20:04.494134" + } +} \ No newline at end of file diff --git a/modules/nf-core/dysgu/tests/nextflow.config b/modules/nf-core/dysgu/tests/nextflow.config new file mode 100644 index 0000000000..5336ab55cf --- /dev/null +++ b/modules/nf-core/dysgu/tests/nextflow.config @@ -0,0 +1,5 @@ +process { + withName: DYSGU { + ext.args = '--exome ' + } +} \ No newline at end of file diff --git a/modules/nf-core/dysgu/tests/tags.yml b/modules/nf-core/dysgu/tests/tags.yml new file mode 100644 index 0000000000..6bffc95e91 --- /dev/null +++ b/modules/nf-core/dysgu/tests/tags.yml @@ -0,0 +1,2 @@ +dysgu: + - "modules/nf-core/dysgu/**" diff --git a/nextflow.config b/nextflow.config index 84c8a75297..6c92634357 100644 --- a/nextflow.config +++ b/nextflow.config @@ -428,6 +428,7 @@ includeConfig 'conf/modules/ascat.config' includeConfig 'conf/modules/cnvkit.config' includeConfig 'conf/modules/controlfreec.config' includeConfig 'conf/modules/deepvariant.config' +includeConfig 'conf/modules/dysgu.config' includeConfig 'conf/modules/freebayes.config' includeConfig 'conf/modules/haplotypecaller.config' includeConfig 'conf/modules/joint_germline.config' diff --git a/nextflow_schema.json b/nextflow_schema.json index 1611d58f40..fb0b2e7832 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -111,8 +111,8 @@ "type": "string", "fa_icon": "fas fa-toolbox", "description": "Tools to use for duplicate marking, variant calling and/or for annotation.", - "help_text": "Multiple tools separated with commas.\n\n**Variant Calling:**\n\nGermline variant calling can currently be performed with the following variant callers:\n- SNPs/Indels: DeepVariant, FreeBayes, GATK HaplotypeCaller, mpileup, Sentieon Haplotyper, Strelka\n- Structural Variants: Manta, TIDDIT\n- Copy-number: CNVKit\n\nTumor-only somatic variant calling can currently be performed with the following variant callers:\n- SNPs/Indels: FreeBayes, mpileup, Mutect2, Strelka\n- Structural Variants: Manta, TIDDIT\n- Copy-number: CNVKit, ControlFREEC\n\nSomatic variant calling can currently only be performed with the following variant callers:\n- SNPs/Indels: FreeBayes, Mutect2, Strelka\n- Structural variants: Manta, TIDDIT\n- Copy-Number: ASCAT, CNVKit, Control-FREEC\n- Microsatellite Instability: MSIsensorpro\n\n> **NB** Mutect2 for somatic variant calling cannot be combined with `--no_intervals`\n\n**Annotation:**\n \n- snpEff, VEP, merge (both consecutively), and bcftools annotate (needs `--bcftools_annotation`).\n\n> **NB** As Sarek will use bgzip and tabix to compress and index VCF files annotated, it expects VCF files to be sorted when starting from `--step annotate`.", - "pattern": "^((ascat|bcfann|cnvkit|controlfreec|deepvariant|freebayes|haplotypecaller|sentieon_dnascope|sentieon_haplotyper|manta|merge|mpileup|msisensorpro|mutect2|ngscheckmate|sentieon_dedup|snpeff|strelka|tiddit|vep)?,?)*(? **NB** Mutect2 for somatic variant calling cannot be combined with `--no_intervals`\n\n**Annotation:**\n \n- snpEff, VEP, merge (both consecutively), and bcftools annotate (needs `--bcftools_annotation`).\n\n> **NB** As Sarek will use bgzip and tabix to compress and index VCF files annotated, it expects VCF files to be sorted when starting from `--step annotate`.", + "pattern": "^((ascat|bcfann|cnvkit|controlfreec|deepvariant|dysgu|freebayes|haplotypecaller|sentieon_dnascope|sentieon_haplotyper|manta|merge|mpileup|msisensorpro|mutect2|ngscheckmate|sentieon_dedup|snpeff|strelka|tiddit|vep)?,?)*(? [ meta + [ variantcaller:'dysgu' ], vcf ] } + + versions = versions.mix(DYSGU.out.versions) + + emit: + vcf + versions +} diff --git a/subworkflows/local/bam_variant_calling_germline_all/main.nf b/subworkflows/local/bam_variant_calling_germline_all/main.nf index 0065166bd9..3c47fe16ca 100644 --- a/subworkflows/local/bam_variant_calling_germline_all/main.nf +++ b/subworkflows/local/bam_variant_calling_germline_all/main.nf @@ -17,6 +17,7 @@ include { BAM_VARIANT_CALLING_SINGLE_TIDDIT include { SENTIEON_DNAMODELAPPLY } from '../../../modules/nf-core/sentieon/dnamodelapply/main' include { VCF_VARIANT_FILTERING_GATK } from '../vcf_variant_filtering_gatk/main' include { VCF_VARIANT_FILTERING_GATK as SENTIEON_HAPLOTYPER_VCF_VARIANT_FILTERING_GATK } from '../vcf_variant_filtering_gatk/main' +include { BAM_VARIANT_CALLING_DYSGU } from '../bam_variant_calling_dysgu/main' @@ -67,6 +68,7 @@ workflow BAM_VARIANT_CALLING_GERMLINE_ALL { vcf_sentieon_haplotyper = Channel.empty() vcf_strelka = Channel.empty() vcf_tiddit = Channel.empty() + vcf_dysgu = Channel.empty() // BCFTOOLS MPILEUP if (tools.split(',').contains('mpileup')) { @@ -191,6 +193,18 @@ workflow BAM_VARIANT_CALLING_GERMLINE_ALL { versions = versions.mix(BAM_VARIANT_CALLING_GERMLINE_MANTA.out.versions) } + // DYSGU + if (tools.split(',').contains('dysgu')) { + BAM_VARIANT_CALLING_DYSGU ( + cram, + fasta, + fasta_fai + ) + + vcf_dysgu = BAM_VARIANT_CALLING_DYSGU.out.vcf + versions = versions.mix(BAM_VARIANT_CALLING_DYSGU.out.versions) + } + // SENTIEON DNASCOPE if (tools.split(',').contains('sentieon_dnascope')) { BAM_VARIANT_CALLING_SENTIEON_DNASCOPE( @@ -350,7 +364,8 @@ workflow BAM_VARIANT_CALLING_GERMLINE_ALL { vcf_mpileup, vcf_sentieon_haplotyper, vcf_strelka, - vcf_tiddit + vcf_tiddit, + vcf_dysgu ) emit: @@ -366,6 +381,7 @@ workflow BAM_VARIANT_CALLING_GERMLINE_ALL { vcf_sentieon_dnascope vcf_sentieon_haplotyper vcf_tiddit + vcf_dysgu versions }