diff --git a/CHANGELOG.md b/CHANGELOG.md index 99b4f6d855..4fb2d08bec 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -14,12 +14,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Changed - [#859](https://github.com/nf-core/sarek/pull/859) - Back to dev -- [#860](https://github.com/nf-core/sarek/pull/860) - replace local subworkflow with nf-core version - vcf_annotate_snpeff -- [#865](https://github.com/nf-core/sarek/pull/865) - replace local subworkflow with nf-core version - vcf_annotate_ensemblvep +- [#860](https://github.com/nf-core/sarek/pull/860) - Replace local subworkflow with nf-core version - vcf_annotate_snpeff +- [#865](https://github.com/nf-core/sarek/pull/865) - Replace local subworkflow with nf-core version - vcf_annotate_ensemblvep +- [#874](https://github.com/nf-core/sarek/pull/874) - Update all modules ### Fixed - [#870](https://github.com/nf-core/sarek/pull/870) - Fix output for locally realigned reads from haplotypecaller +- [#874](https://github.com/nf-core/sarek/pull/874) - Remove `CITATION.cff` ### Deprecated @@ -27,6 +29,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Dependencies +| Dependency | Old version | New version | +| ---------- | ----------- | ----------- | +| `svdb` | 2.6.1 | 2.8.1 | + ## [3.1.1](https://github.com/nf-core/sarek/releases/tag/3.1.1) - Lilla Luleälven Lilla Luleälven river's main affluent is Rapaätno. diff --git a/CITATION.cff b/CITATION.cff deleted file mode 100644 index 017666c018..0000000000 --- a/CITATION.cff +++ /dev/null @@ -1,56 +0,0 @@ -cff-version: 1.2.0 -message: "If you use `nf-core tools` in your work, please cite the `nf-core` publication" -authors: - - family-names: Ewels - given-names: Philip - - family-names: Peltzer - given-names: Alexander - - family-names: Fillinger - given-names: Sven - - family-names: Patel - given-names: Harshil - - family-names: Alneberg - given-names: Johannes - - family-names: Wilm - given-names: Andreas - - family-names: Garcia - given-names: Maxime Ulysse - - family-names: Di Tommaso - given-names: Paolo - - family-names: Nahnsen - given-names: Sven -title: "The nf-core framework for community-curated bioinformatics pipelines." -version: 2.4.1 -doi: 10.1038/s41587-020-0439-x -date-released: 2022-05-16 -url: https://github.com/nf-core/tools -prefered-citation: - type: article - authors: - - family-names: Ewels - given-names: Philip - - family-names: Peltzer - given-names: Alexander - - family-names: Fillinger - given-names: Sven - - family-names: Patel - given-names: Harshil - - family-names: Alneberg - given-names: Johannes - - family-names: Wilm - given-names: Andreas - - family-names: Garcia - given-names: Maxime Ulysse - - family-names: Di Tommaso - given-names: Paolo - - family-names: Nahnsen - given-names: Sven - doi: 10.1038/s41587-020-0439-x - journal: nature biotechnology - start: 276 - end: 278 - title: "The nf-core framework for community-curated bioinformatics pipelines." - issue: 3 - volume: 38 - year: 2020 - url: https://dx.doi.org/10.1038/s41587-020-0439-x diff --git a/modules.json b/modules.json index 05c489d2d3..85f891c49b 100644 --- a/modules.json +++ b/modules.json @@ -32,7 +32,7 @@ }, "bwa/mem": { "branch": "master", - "git_sha": "cf5b9c30a2adacc581793afb79fae5f5b50bed01", + "git_sha": "653588be2a4aadab487b530643dbc9baf7a485c4", "installed_by": ["modules"] }, "bwamem2/index": { @@ -42,7 +42,7 @@ }, "bwamem2/mem": { "branch": "master", - "git_sha": "cf5b9c30a2adacc581793afb79fae5f5b50bed01", + "git_sha": "653588be2a4aadab487b530643dbc9baf7a485c4", "installed_by": ["modules"] }, "cat/cat": { @@ -119,8 +119,8 @@ }, "ensemblvep": { "branch": "master", - "git_sha": "69f158610f25a3bff40b3eadfedd3ac67a3cfc23", - "installed_by": ["modules", "vcf_annotate_ensemblvep"] + "git_sha": "1ec0d59beb1e794a7a4a4351e15138ffa213aa20", + "installed_by": ["vcf_annotate_ensemblvep", "modules"] }, "fastp": { "branch": "master", @@ -129,7 +129,7 @@ }, "fastqc": { "branch": "master", - "git_sha": "3dd73937b084b547f9272bc901e0f120a7913fd8", + "git_sha": "810e8f2603ec38401d49a4aaed06f6d058745552", "installed_by": ["modules"] }, "fgbio/callmolecularconsensusreads": { @@ -265,7 +265,7 @@ }, "gatk4/mergevcfs": { "branch": "master", - "git_sha": "7578005a576f3ac1b0d4f10c037dde34cdedfb67", + "git_sha": "c25943553f62be5f907e3c12c42eaf0a1b40746d", "installed_by": ["modules"] }, "gatk4/mutect2": { @@ -381,7 +381,7 @@ }, "svdb/merge": { "branch": "master", - "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905", + "git_sha": "4a8a2caf44b87734b41ea4c67f508c14f0745ee7", "installed_by": ["modules"] }, "tabix/bgziptabix": { diff --git a/modules/nf-core/bwa/mem/main.nf b/modules/nf-core/bwa/mem/main.nf index 7eb9d5c2cf..363d1f2e0e 100644 --- a/modules/nf-core/bwa/mem/main.nf +++ b/modules/nf-core/bwa/mem/main.nf @@ -25,7 +25,7 @@ process BWA_MEM { def prefix = task.ext.prefix ?: "${meta.id}" def samtools_command = sort_bam ? 'sort' : 'view' """ - INDEX=`find -L ./ -name "*.amb" | sed 's/.amb//'` + INDEX=`find -L ./ -name "*.amb" | sed 's/\\.amb\$//'` bwa mem \\ $args \\ diff --git a/modules/nf-core/bwamem2/mem/main.nf b/modules/nf-core/bwamem2/mem/main.nf index f8bad4b94a..84b99dfa02 100644 --- a/modules/nf-core/bwamem2/mem/main.nf +++ b/modules/nf-core/bwamem2/mem/main.nf @@ -25,7 +25,7 @@ process BWAMEM2_MEM { def prefix = task.ext.prefix ?: "${meta.id}" def samtools_command = sort_bam ? 'sort' : 'view' """ - INDEX=`find -L ./ -name "*.amb" | sed 's/.amb//'` + INDEX=`find -L ./ -name "*.amb" | sed 's/\\.amb\$//'` bwa-mem2 \\ mem \\ diff --git a/modules/nf-core/ensemblvep/main.nf b/modules/nf-core/ensemblvep/main.nf index 614852f367..a6049034e6 100644 --- a/modules/nf-core/ensemblvep/main.nf +++ b/modules/nf-core/ensemblvep/main.nf @@ -8,7 +8,7 @@ process ENSEMBLVEP { 'quay.io/biocontainers/ensembl-vep:108.2--pl5321h4a94de4_0' }" input: - tuple val(meta), path(vcf, stageAs: "?/*") + tuple val(meta), path(vcf) val genome val species val cache_version diff --git a/modules/nf-core/fastqc/main.nf b/modules/nf-core/fastqc/main.nf index 3bebb2407a..47fd0e5843 100644 --- a/modules/nf-core/fastqc/main.nf +++ b/modules/nf-core/fastqc/main.nf @@ -21,9 +21,15 @@ process FASTQC { script: def args = task.ext.args ?: '' def prefix = task.ext.prefix ?: "${meta.id}" + // Make list of old name and new name pairs to use for renaming in the bash while loop + def old_new_pairs = reads instanceof Path || reads.size() == 1 ? [[ reads, "${prefix}.${reads.extension}" ]] : reads.withIndex().collect { entry, index -> [ entry, "${prefix}_${index + 1}.${entry.extension}" ] } + def rename_to = old_new_pairs*.join(' ').join(' ') + def renamed_files = old_new_pairs.collect{ old_name, new_name -> new_name }.join(' ') """ - printf "%s\\n" $reads | while read f; do [[ \$f =~ ^${prefix}.* ]] || ln -s \$f ${prefix}_\$f ; done - fastqc $args --threads $task.cpus ${prefix}* + printf "%s %s\\n" $rename_to | while read old_name new_name; do + [ -f "\${new_name}" ] || ln -s \$old_name \$new_name + done + fastqc $args --threads $task.cpus $renamed_files cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/nf-core/gatk4/mergevcfs/main.nf b/modules/nf-core/gatk4/mergevcfs/main.nf index 0b065b5b55..08fb3969e3 100644 --- a/modules/nf-core/gatk4/mergevcfs/main.nf +++ b/modules/nf-core/gatk4/mergevcfs/main.nf @@ -9,7 +9,7 @@ process GATK4_MERGEVCFS { input: tuple val(meta), path(vcf) - path dict + tuple val(meta2), path(dict) output: tuple val(meta), path('*.vcf.gz'), emit: vcf diff --git a/modules/nf-core/gatk4/mergevcfs/meta.yml b/modules/nf-core/gatk4/mergevcfs/meta.yml index 3ebce0b9e1..db8c4cb0bf 100644 --- a/modules/nf-core/gatk4/mergevcfs/meta.yml +++ b/modules/nf-core/gatk4/mergevcfs/meta.yml @@ -23,13 +23,16 @@ input: type: list description: Two or more VCF files pattern: "*.{vcf,vcf.gz}" + - meta2: + type: map + description: | + Groovy Map containing reference information + e.g. [ id:'genome'] - ref_dict: type: file description: Optional Sequence Dictionary as input pattern: "*.dict" - - use_ref_dict: - type: boolean - description: Specify whether or not to use a given reference dictionary + output: - vcf: type: file diff --git a/modules/nf-core/svdb/merge/main.nf b/modules/nf-core/svdb/merge/main.nf index 477dbb0d31..7dd926537f 100644 --- a/modules/nf-core/svdb/merge/main.nf +++ b/modules/nf-core/svdb/merge/main.nf @@ -1,10 +1,10 @@ process SVDB_MERGE { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::svdb=2.6.1 bioconda::samtools=1.15.1" : null) + conda (params.enable_conda ? "bioconda::svdb=2.8.1 bioconda::samtools=1.16.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/mulled-v2-c8daa8f9d69d3c5a1a4ff08283a166c18edb0000:56d0a468970fbb474d92f0591abcf677757fb370-0': - 'quay.io/biocontainers/mulled-v2-c8daa8f9d69d3c5a1a4ff08283a166c18edb0000:56d0a468970fbb474d92f0591abcf677757fb370-0' }" + 'https://depot.galaxyproject.org/singularity/mulled-v2-c8daa8f9d69d3c5a1a4ff08283a166c18edb0000:af6f8534cd538a85ff43a2eae1b52b143e7abd05-0': + 'quay.io/biocontainers/mulled-v2-c8daa8f9d69d3c5a1a4ff08283a166c18edb0000:af6f8534cd538a85ff43a2eae1b52b143e7abd05-0' }" input: tuple val(meta), path(vcfs) diff --git a/subworkflows/local/bam_joint_calling_germline_gatk/main.nf b/subworkflows/local/bam_joint_calling_germline_gatk/main.nf index c930a1cc2d..f862f7bd07 100644 --- a/subworkflows/local/bam_joint_calling_germline_gatk/main.nf +++ b/subworkflows/local/bam_joint_calling_germline_gatk/main.nf @@ -1,15 +1,15 @@ // // merge samples with genomicsdbimport, perform joint genotyping with genotypeGVCFS -include { BCFTOOLS_SORT } from '../../../modules/nf-core/bcftools/sort/main' -include { GATK4_APPLYVQSR as GATK4_APPLYVQSR_INDEL } from '../../../modules/nf-core/gatk4/applyvqsr/main' -include { GATK4_APPLYVQSR as GATK4_APPLYVQSR_SNP } from '../../../modules/nf-core/gatk4/applyvqsr/main' -include { GATK4_GENOMICSDBIMPORT } from '../../../modules/nf-core/gatk4/genomicsdbimport/main' -include { GATK4_GENOTYPEGVCFS } from '../../../modules/nf-core/gatk4/genotypegvcfs/main' -include { GATK4_MERGEVCFS as MERGE_GENOTYPEGVCFS } from '../../../modules/nf-core/gatk4/mergevcfs/main' -include { GATK4_MERGEVCFS as MERGE_VQSR } from '../../../modules/nf-core/gatk4/mergevcfs/main' -include { GATK4_VARIANTRECALIBRATOR as VARIANTRECALIBRATOR_INDEL} from '../../../modules/nf-core/gatk4/variantrecalibrator/main' -include { GATK4_VARIANTRECALIBRATOR as VARIANTRECALIBRATOR_SNP } from '../../../modules/nf-core/gatk4/variantrecalibrator/main' -include { TABIX_TABIX as TABIX } from '../../../modules/nf-core/tabix/tabix/main' +include { BCFTOOLS_SORT } from '../../../modules/nf-core/bcftools/sort/main' +include { GATK4_APPLYVQSR as GATK4_APPLYVQSR_INDEL } from '../../../modules/nf-core/gatk4/applyvqsr/main' +include { GATK4_APPLYVQSR as GATK4_APPLYVQSR_SNP } from '../../../modules/nf-core/gatk4/applyvqsr/main' +include { GATK4_GENOMICSDBIMPORT } from '../../../modules/nf-core/gatk4/genomicsdbimport/main' +include { GATK4_GENOTYPEGVCFS } from '../../../modules/nf-core/gatk4/genotypegvcfs/main' +include { GATK4_MERGEVCFS as MERGE_GENOTYPEGVCFS } from '../../../modules/nf-core/gatk4/mergevcfs/main' +include { GATK4_MERGEVCFS as MERGE_VQSR } from '../../../modules/nf-core/gatk4/mergevcfs/main' +include { GATK4_VARIANTRECALIBRATOR as VARIANTRECALIBRATOR_INDEL } from '../../../modules/nf-core/gatk4/variantrecalibrator/main' +include { GATK4_VARIANTRECALIBRATOR as VARIANTRECALIBRATOR_SNP } from '../../../modules/nf-core/gatk4/variantrecalibrator/main' +include { TABIX_TABIX as TABIX } from '../../../modules/nf-core/tabix/tabix/main' workflow BAM_JOINT_CALLING_GERMLINE_GATK { take: @@ -72,13 +72,13 @@ workflow BAM_JOINT_CALLING_GERMLINE_GATK { no_intervals: it[0].num_intervals <= 1 } - vcfs_sorted_input_no_intervals = vcfs_sorted_input.no_intervals.map{ meta , vcf -> - - [[ id: "joint_variant_calling", - num_intervals: meta.num_intervals, - patient: "all_samples", - variantcaller: "haplotypecaller" - ] , vcf ] + vcfs_sorted_input_no_intervals = vcfs_sorted_input.no_intervals.map{ meta, vcf -> + [[ + id: "joint_variant_calling", + num_intervals: meta.num_intervals, + patient: "all_samples", + variantcaller: "haplotypecaller" + ], vcf ] } // Index vcf files if no scatter/gather by intervals @@ -86,17 +86,15 @@ workflow BAM_JOINT_CALLING_GERMLINE_GATK { //Merge scatter/gather vcfs & index //Rework meta for variantscalled.csv and annotation tools - MERGE_GENOTYPEGVCFS(vcfs_sorted_input.intervals.map{meta, vcf -> - [ - [ - id: "joint_variant_calling", - num_intervals: meta.num_intervals, - patient: "all_samples", - variantcaller: "haplotypecaller", - ], - vcf] - }.groupTuple() - ,dict) + MERGE_GENOTYPEGVCFS(vcfs_sorted_input.intervals.map{ meta, vcf -> + [[ + id: "joint_variant_calling", + num_intervals: meta.num_intervals, + patient: "all_samples", + variantcaller: "haplotypecaller" + ], vcf ] + }.groupTuple(), + dict.map{ it -> [[id:it[0].baseName], it]}) vqsr_input = Channel.empty().mix( MERGE_GENOTYPEGVCFS.out.vcf.join(MERGE_GENOTYPEGVCFS.out.tbi), @@ -134,46 +132,45 @@ workflow BAM_JOINT_CALLING_GERMLINE_GATK { //Join results of variant recalibration into a single channel tuple //Rework meta for variantscalled.csv and annotation tools - vqsr_input_snp = vqsr_input.join( VARIANTRECALIBRATOR_SNP.out.recal) - .join( VARIANTRECALIBRATOR_SNP.out.idx) - .join( VARIANTRECALIBRATOR_SNP.out.tranches) - .map{ meta, vcf, tbi, recal, index, tranche -> - - new_meta = [ - id: "recalibrated_joint_variant_calling", - num_intervals: meta.num_intervals, - patient: "all_samples", - variantcaller: "haplotypecaller", - ] - - [new_meta, vcf, tbi, recal, index, tranche] - } + vqsr_input_snp = vqsr_input.join(VARIANTRECALIBRATOR_SNP.out.recal) + .join(VARIANTRECALIBRATOR_SNP.out.idx) + .join(VARIANTRECALIBRATOR_SNP.out.tranches) + .map{ meta, vcf, tbi, recal, index, tranche -> + new_meta = [ + id: "recalibrated_joint_variant_calling", + num_intervals: meta.num_intervals, + patient: "all_samples", + variantcaller: "haplotypecaller", + ] + [new_meta, vcf, tbi, recal, index, tranche] + } //Join results of variant recalibration into a single channel tuple //Rework meta for variantscalled.csv and annotation tools - vqsr_input_indel = vqsr_input.join( VARIANTRECALIBRATOR_INDEL.out.recal).join( - VARIANTRECALIBRATOR_INDEL.out.idx).join( - VARIANTRECALIBRATOR_INDEL.out.tranches).map{ meta, vcf, tbi, recal, index, tranche -> - - new_meta = [ - id: "recalibrated_joint_variant_calling", - num_intervals: meta.num_intervals, - patient: "all_samples", - variantcaller: "haplotypecaller" - ] - - [new_meta, vcf, tbi, recal, index, tranche] - } - - GATK4_APPLYVQSR_SNP(vqsr_input_snp, - fasta, - fai, - dict ) - - GATK4_APPLYVQSR_INDEL(vqsr_input_indel, - fasta, - fai, - dict ) + vqsr_input_indel = vqsr_input.join(VARIANTRECALIBRATOR_INDEL.out.recal) + .join(VARIANTRECALIBRATOR_INDEL.out.idx) + .join(VARIANTRECALIBRATOR_INDEL.out.tranches) + .map{ meta, vcf, tbi, recal, index, tranche -> + new_meta = [ + id: "recalibrated_joint_variant_calling", + num_intervals: meta.num_intervals, + patient: "all_samples", + variantcaller: "haplotypecaller" + ] + [new_meta, vcf, tbi, recal, index, tranche] + } + + GATK4_APPLYVQSR_SNP( + vqsr_input_snp, + fasta, + fai, + dict) + + GATK4_APPLYVQSR_INDEL( + vqsr_input_indel, + fasta, + fai, + dict) vqsr_snp_vcf = GATK4_APPLYVQSR_SNP.out.vcf vqsr_indel_vcf = GATK4_APPLYVQSR_INDEL.out.vcf @@ -183,7 +180,7 @@ workflow BAM_JOINT_CALLING_GERMLINE_GATK { // MERGE_VQSR( vqsr_snp_vcf.mix(vqsr_indel_vcf).groupTuple(), - dict + dict.map{ it -> [[id:it[0].baseName], it]} ) ch_versions = ch_versions.mix(GATK4_GENOMICSDBIMPORT.out.versions) @@ -191,8 +188,6 @@ workflow BAM_JOINT_CALLING_GERMLINE_GATK { ch_versions = ch_versions.mix(VARIANTRECALIBRATOR_SNP.out.versions) ch_versions = ch_versions.mix(GATK4_APPLYVQSR_SNP.out.versions) - - emit: versions = ch_versions // channel: [ versions.yml ] genotype_vcf = Channel.empty().mix( vcfs_sorted_input_no_intervals, MERGE_GENOTYPEGVCFS.out.vcf, MERGE_VQSR.out.vcf) // channel: [ val(meta), [ vcf ] ] diff --git a/subworkflows/local/bam_variant_calling_deepvariant/main.nf b/subworkflows/local/bam_variant_calling_deepvariant/main.nf index 537d1d0d3f..f21ac5616f 100644 --- a/subworkflows/local/bam_variant_calling_deepvariant/main.nf +++ b/subworkflows/local/bam_variant_calling_deepvariant/main.nf @@ -49,7 +49,7 @@ workflow BAM_VARIANT_CALLING_DEEPVARIANT { [groupKey(new_meta, meta.num_intervals), vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) MERGE_DEEPVARIANT_GVCF( deepvariant_gvcf_out.intervals @@ -66,7 +66,7 @@ workflow BAM_VARIANT_CALLING_DEEPVARIANT { [groupKey(new_meta, meta.num_intervals), vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) // Mix output channels for "no intervals" and "with intervals" results deepvariant_gvcf = Channel.empty().mix( diff --git a/subworkflows/local/bam_variant_calling_freebayes/main.nf b/subworkflows/local/bam_variant_calling_freebayes/main.nf index 148b20795e..750d3316db 100644 --- a/subworkflows/local/bam_variant_calling_freebayes/main.nf +++ b/subworkflows/local/bam_variant_calling_freebayes/main.nf @@ -52,8 +52,7 @@ workflow BAM_VARIANT_CALLING_FREEBAYES { ] [groupKey(new_meta, meta.num_intervals), vcf] }.groupTuple(), - dict - ) + dict.map{ it -> [[id:it[0].baseName], it]}) // Mix output channels for "no intervals" and "with intervals" results freebayes_vcf = Channel.empty().mix( diff --git a/subworkflows/local/bam_variant_calling_germline_manta/main.nf b/subworkflows/local/bam_variant_calling_germline_manta/main.nf index 5fcbb0765d..5b322d8f6a 100644 --- a/subworkflows/local/bam_variant_calling_germline_manta/main.nf +++ b/subworkflows/local/bam_variant_calling_germline_manta/main.nf @@ -49,7 +49,7 @@ workflow BAM_VARIANT_CALLING_GERMLINE_MANTA { meta.num_intervals), vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) MERGE_MANTA_SV( manta_sv_vcf.intervals @@ -67,7 +67,7 @@ workflow BAM_VARIANT_CALLING_GERMLINE_MANTA { vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) MERGE_MANTA_DIPLOID( manta_diploid_sv_vcf.intervals @@ -85,7 +85,7 @@ workflow BAM_VARIANT_CALLING_GERMLINE_MANTA { vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) // Mix output channels for "no intervals" and "with intervals" results // Only diploid SV should get annotated diff --git a/subworkflows/local/bam_variant_calling_haplotypecaller/main.nf b/subworkflows/local/bam_variant_calling_haplotypecaller/main.nf index ebf13d2d47..3efaa2948c 100644 --- a/subworkflows/local/bam_variant_calling_haplotypecaller/main.nf +++ b/subworkflows/local/bam_variant_calling_haplotypecaller/main.nf @@ -97,7 +97,7 @@ workflow BAM_VARIANT_CALLING_HAPLOTYPECALLER { [groupKey(new_meta, new_meta.num_intervals), vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) haplotypecaller_vcf = Channel.empty().mix( MERGE_HAPLOTYPECALLER.out.vcf, diff --git a/subworkflows/local/bam_variant_calling_mpileup/main.nf b/subworkflows/local/bam_variant_calling_mpileup/main.nf index 211b206388..c72223b3e4 100644 --- a/subworkflows/local/bam_variant_calling_mpileup/main.nf +++ b/subworkflows/local/bam_variant_calling_mpileup/main.nf @@ -62,7 +62,7 @@ workflow BAM_VARIANT_CALLING_MPILEUP { [groupKey(new_meta, new_meta.num_intervals), vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) ch_versions = ch_versions.mix(SAMTOOLS_MPILEUP.out.versions) ch_versions = ch_versions.mix(BCFTOOLS_MPILEUP.out.versions) diff --git a/subworkflows/local/bam_variant_calling_single_strelka/main.nf b/subworkflows/local/bam_variant_calling_single_strelka/main.nf index a7e0f641c3..77a7f0b7d3 100644 --- a/subworkflows/local/bam_variant_calling_single_strelka/main.nf +++ b/subworkflows/local/bam_variant_calling_single_strelka/main.nf @@ -40,8 +40,7 @@ workflow BAM_VARIANT_CALLING_SINGLE_STRELKA { [groupKey(new_meta, meta.num_intervals), vcf] }.groupTuple(), - dict - ) + dict.map{ it -> [[id:it[0].baseName], it]}) MERGE_STRELKA_GENOME( strelka_genome_vcf.intervals @@ -59,8 +58,7 @@ workflow BAM_VARIANT_CALLING_SINGLE_STRELKA { vcf] }.groupTuple(), - dict - ) + dict.map{ it -> [[id:it[0].baseName], it]}) // Mix output channels for "no intervals" and "with intervals" results // Only strelka variant vcf should get annotated diff --git a/subworkflows/local/bam_variant_calling_somatic_manta/main.nf b/subworkflows/local/bam_variant_calling_somatic_manta/main.nf index bee724e395..8bca21cfb7 100644 --- a/subworkflows/local/bam_variant_calling_somatic_manta/main.nf +++ b/subworkflows/local/bam_variant_calling_somatic_manta/main.nf @@ -59,7 +59,7 @@ workflow BAM_VARIANT_CALLING_SOMATIC_MANTA { vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) MERGE_MANTA_SMALL_INDELS( manta_candidate_sv_vcf.intervals.map{ meta, vcf -> @@ -76,7 +76,7 @@ workflow BAM_VARIANT_CALLING_SOMATIC_MANTA { vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) MERGE_MANTA_DIPLOID( manta_diploid_sv_vcf.intervals.map{ meta, vcf -> @@ -101,7 +101,7 @@ workflow BAM_VARIANT_CALLING_SOMATIC_MANTA { vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) MERGE_MANTA_SOMATIC( manta_somatic_sv_vcf.intervals.map{ meta, vcf -> @@ -118,7 +118,7 @@ workflow BAM_VARIANT_CALLING_SOMATIC_MANTA { vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) // Mix output channels for "no intervals" and "with intervals" results manta_vcf = Channel.empty().mix( diff --git a/subworkflows/local/bam_variant_calling_somatic_mutect2/main.nf b/subworkflows/local/bam_variant_calling_somatic_mutect2/main.nf index a2e09ebfab..3418f7bb84 100644 --- a/subworkflows/local/bam_variant_calling_somatic_mutect2/main.nf +++ b/subworkflows/local/bam_variant_calling_somatic_mutect2/main.nf @@ -76,8 +76,7 @@ workflow BAM_VARIANT_CALLING_SOMATIC_MUTECT2 { [groupKey(new_meta, meta.num_intervals), vcf] }.groupTuple(), - dict - ) + dict.map{ it -> [[id:it[0].baseName], it]}) mutect2_vcf = Channel.empty().mix( MERGE_MUTECT2.out.vcf, diff --git a/subworkflows/local/bam_variant_calling_somatic_strelka/main.nf b/subworkflows/local/bam_variant_calling_somatic_strelka/main.nf index 003c9a73c6..74346897a8 100644 --- a/subworkflows/local/bam_variant_calling_somatic_strelka/main.nf +++ b/subworkflows/local/bam_variant_calling_somatic_strelka/main.nf @@ -41,7 +41,7 @@ workflow BAM_VARIANT_CALLING_SOMATIC_STRELKA { vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) MERGE_STRELKA_INDELS(strelka_vcf_indels.intervals.map{ meta, vcf -> @@ -56,7 +56,7 @@ workflow BAM_VARIANT_CALLING_SOMATIC_STRELKA { meta.num_intervals), vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) // Mix output channels for "no intervals" and "with intervals" results strelka_vcf = Channel.empty().mix( diff --git a/subworkflows/local/bam_variant_calling_tumor_only_manta/main.nf b/subworkflows/local/bam_variant_calling_tumor_only_manta/main.nf index f0351334f7..793641669e 100644 --- a/subworkflows/local/bam_variant_calling_tumor_only_manta/main.nf +++ b/subworkflows/local/bam_variant_calling_tumor_only_manta/main.nf @@ -49,7 +49,7 @@ workflow BAM_VARIANT_CALLING_TUMOR_ONLY_MANTA { vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) MERGE_MANTA_SV( manta_candidate_sv_vcf.intervals.map{ meta, vcf -> @@ -66,7 +66,7 @@ workflow BAM_VARIANT_CALLING_TUMOR_ONLY_MANTA { vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) MERGE_MANTA_TUMOR( manta_tumor_sv_vcf.intervals.map{ meta, vcf -> @@ -83,7 +83,7 @@ workflow BAM_VARIANT_CALLING_TUMOR_ONLY_MANTA { vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) // Mix output channels for "no intervals" and "with intervals" results // Only tumor sv should get annotated diff --git a/subworkflows/local/bam_variant_calling_tumor_only_mutect2/main.nf b/subworkflows/local/bam_variant_calling_tumor_only_mutect2/main.nf index eae2a2b24e..c681c150b2 100644 --- a/subworkflows/local/bam_variant_calling_tumor_only_mutect2/main.nf +++ b/subworkflows/local/bam_variant_calling_tumor_only_mutect2/main.nf @@ -75,7 +75,7 @@ workflow BAM_VARIANT_CALLING_TUMOR_ONLY_MUTECT2 { [groupKey(new_meta, meta.num_intervals), vcf] }.groupTuple(), - dict) + dict.map{ it -> [[id:it[0].baseName], it]}) mutect2_vcf = Channel.empty().mix( MERGE_MUTECT2.out.vcf, diff --git a/tests/config/pytest_tags.yml b/tests/config/pytest_tags.yml index ed429079d8..717b3f09ed 100644 --- a/tests/config/pytest_tags.yml +++ b/tests/config/pytest_tags.yml @@ -1,6 +1,38 @@ # default_extended -default_extended: +tumor_normal_pair: + - conf/modules/** + - modules/** + - subworkflows/** + - workflows/** + - nextflow.config + - main.nf + +save_mapped_only: + - conf/modules/** + - modules/** + - subworkflows/** + - workflows/** + - nextflow.config + - main.nf + +save_output_as_bam_only: + - conf/modules/** + - modules/** + - subworkflows/** + - workflows/** + - nextflow.config + - main.nf + +skip_all_qc: + - conf/modules/** + - modules/** + - subworkflows/** + - workflows/** + - nextflow.config + - main.nf + +skip_markduplicates: - conf/modules/** - modules/** - subworkflows/** diff --git a/tests/test_default_extended.yml b/tests/test_default_extended.yml deleted file mode 100644 index 958627a963..0000000000 --- a/tests/test_default_extended.yml +++ /dev/null @@ -1,446 +0,0 @@ -- name: Run save_mapped - command: nextflow run main.nf -profile test --save_mapped - tags: - - default_extended - - preprocessing - - save_mapped - - variant_calling - files: - - path: results/csv/mapped.csv - md5sum: 3bee45ccf65e301ce09ee4eed8f26933 - - path: results/csv/markduplicates.csv - md5sum: 0d6120bb99e92f6810343270711ca53e - - path: results/csv/markduplicates_no_table.csv - md5sum: 2a2d3d4842befd4def39156463859ee3 - - path: results/csv/recalibrated.csv - md5sum: 2d29d9e53894dcce96a1b5beb6ef3312 - - path: results/multiqc - - path: results/preprocessing/mapped/test/test.sorted.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/mapped/test/test.sorted.cram.crai - # binary changes md5sums on reruns. - - path: results/preprocessing/markduplicates/test/test.md.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/markduplicates/test/test.md.cram.crai - # binary changes md5sums on reruns. - - path: results/preprocessing/recal_table/test/test.recal.table - md5sum: 4ac774bf5f1157e77426fd82f5ac0fbe - - path: results/preprocessing/recalibrated/test/test.recal.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/recalibrated/test/test.recal.cram.crai - # binary changes md5sums on reruns. - - path: results/reports/fastqc/test-test_L1 - - path: results/reports/markduplicates/test/test.md.cram.metrics - contains: ["test 8547 767 84 523391 3882 0 0 0.385081", "1.0 767 767"] - - path: results/reports/mosdepth/test/test.md.mosdepth.global.dist.txt - md5sum: 76fa71922a3f748e507c2364c531dfcb - - path: results/reports/mosdepth/test/test.md.mosdepth.region.dist.txt - md5sum: abc5df85e302b79985627888870882da - - path: results/reports/mosdepth/test/test.md.mosdepth.summary.txt - md5sum: d536456436eb275159b8c6af83213d80 - - path: results/reports/mosdepth/test/test.md.regions.bed.gz - md5sum: 38fe39894abe62e38f8ac214cba64f2b - - path: results/reports/mosdepth/test/test.md.regions.bed.gz.csi - md5sum: b1c2a861f64e20a94108a6de3b76c582 - - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt - md5sum: 76fa71922a3f748e507c2364c531dfcb - - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt - md5sum: abc5df85e302b79985627888870882da - - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt - md5sum: d536456436eb275159b8c6af83213d80 - - path: results/reports/mosdepth/test/test.recal.regions.bed.gz - md5sum: 38fe39894abe62e38f8ac214cba64f2b - - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi - md5sum: b1c2a861f64e20a94108a6de3b76c582 - - path: results/reports/samtools/test/test.md.cram.stats - # conda changes md5sums for test. - - path: results/reports/samtools/test/test.recal.cram.stats - # conda changes md5sums for test. - - path: results/reports/bcftools/strelka/test/test.strelka.variants.bcftools_stats.txt - # conda changes md5sums for test. - - path: results/reports/vcftools/strelka/test/test.strelka.variants.FILTER.summary - md5sum: dd87f507da7de20d5318841af312493b - - path: results/reports/vcftools/strelka/test/test.strelka.variants.TsTv.count - md5sum: fa27f678965b7cba6a92efcd039f802a - - path: results/reports/vcftools/strelka/test/test.strelka.variants.TsTv.qual - md5sum: bc68ae4e688e9fb772b457069e604883 - - path: results/variant_calling/strelka/test/test.strelka.genome.vcf.gz - # binary changes md5sums on reruns. - - path: results/variant_calling/strelka/test/test.strelka.genome.vcf.gz.tbi - # binary changes md5sums on reruns. - - path: results/variant_calling/strelka/test/test.strelka.variants.vcf.gz - # binary changes md5sums on reruns. - - path: results/variant_calling/strelka/test/test.strelka.variants.vcf.gz.tbi - - path: results/strelka - should_exist: false -- name: Run save_output_as_bam - command: nextflow run main.nf -profile test --save_output_as_bam - tags: - - default_extended - - preprocessing - - save_output_as_bam - - variant_calling - files: - - path: results/csv/markduplicates.csv - md5sum: 6004ab16b63012e336f6251396a983c5 - - path: results/csv/markduplicates_no_table.csv - md5sum: 8a145eca178cfd02403d60122b9d3960 - - path: results/csv/recalibrated.csv - md5sum: 2dfbcaaeaaf4937c51c5c310f1c77614 - - path: results/multiqc - - path: results/preprocessing/markduplicates/test/test.md.bam.bai - # conda changes md5sums for test. - - path: results/preprocessing/markduplicates/test/test.md.bam - # conda changes md5sums for test. - - path: results/preprocessing/recal_table/test/test.recal.table - md5sum: 4ac774bf5f1157e77426fd82f5ac0fbe - - path: results/preprocessing/recalibrated/test/test.recal.bam - # binary changes md5sums on reruns. - - path: results/preprocessing/recalibrated/test/test.recal.bam.bai - # binary changes md5sums on reruns. - - path: results/reports/fastqc/test-test_L1 - - path: results/reports/markduplicates/test/test.md.cram.metrics - contains: ["test 8547 767 84 523391 3882 0 0 0.385081", "1.0 767 767"] - - path: results/reports/mosdepth/test/test.md.mosdepth.global.dist.txt - md5sum: 76fa71922a3f748e507c2364c531dfcb - - path: results/reports/mosdepth/test/test.md.mosdepth.region.dist.txt - md5sum: abc5df85e302b79985627888870882da - - path: results/reports/mosdepth/test/test.md.mosdepth.summary.txt - md5sum: d536456436eb275159b8c6af83213d80 - - path: results/reports/mosdepth/test/test.md.regions.bed.gz - md5sum: 38fe39894abe62e38f8ac214cba64f2b - - path: results/reports/mosdepth/test/test.md.regions.bed.gz.csi - md5sum: b1c2a861f64e20a94108a6de3b76c582 - - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt - md5sum: 76fa71922a3f748e507c2364c531dfcb - - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt - md5sum: abc5df85e302b79985627888870882da - - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt - md5sum: d536456436eb275159b8c6af83213d80 - - path: results/reports/mosdepth/test/test.recal.regions.bed.gz - md5sum: 38fe39894abe62e38f8ac214cba64f2b - - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi - md5sum: b1c2a861f64e20a94108a6de3b76c582 - - path: results/reports/samtools/test/test.md.cram.stats - # conda changes md5sums for test. - - path: results/reports/samtools/test/test.recal.cram.stats - # conda changes md5sums for test. - - path: results/reports/bcftools/strelka/test/test.strelka.variants.bcftools_stats.txt - # conda changes md5sums for test. - - path: results/reports/vcftools/strelka/test/test.strelka.variants.FILTER.summary - md5sum: dd87f507da7de20d5318841af312493b - - path: results/reports/vcftools/strelka/test/test.strelka.variants.TsTv.count - md5sum: fa27f678965b7cba6a92efcd039f802a - - path: results/reports/vcftools/strelka/test/test.strelka.variants.TsTv.qual - md5sum: bc68ae4e688e9fb772b457069e604883 - - path: results/variant_calling/strelka/test/test.strelka.genome.vcf.gz - # binary changes md5sums on reruns. - - path: results/variant_calling/strelka/test/test.strelka.genome.vcf.gz.tbi - # binary changes md5sums on reruns. - - path: results/variant_calling/strelka/test/test.strelka.variants.vcf.gz - # binary changes md5sums on reruns. - - path: results/variant_calling/strelka/test/test.strelka.variants.vcf.gz.tbi - - path: results/strelka - should_exist: false -- name: Run default pipeline with skipping Markduplicates - command: nextflow run main.nf -profile test,skip_markduplicates - tags: - - default_extended - - preprocessing - - skip_markduplicates - files: - - path: results/csv/mapped.csv - md5sum: 3bee45ccf65e301ce09ee4eed8f26933 - - path: results/csv/recalibrated.csv - md5sum: 2d29d9e53894dcce96a1b5beb6ef3312 - - path: results/multiqc - - path: results/preprocessing/mapped/test/test.sorted.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/mapped/test/test.sorted.cram.crai - # binary changes md5sums on reruns. - - path: results/preprocessing/recal_table/test/test.recal.table - md5sum: 8de213f4c00fac61a1102633760493df - - path: results/preprocessing/recalibrated/test/test.recal.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/recalibrated/test/test.recal.cram.crai - # binary changes md5sums on reruns. - - path: results/reports/fastqc/test-test_L1 - - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt - md5sum: 48aa760b024d7c0ddd5a66f89a1cb544 - - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt - md5sum: 71e938314bba70f978271b2b56cb7ad3 - - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt - md5sum: 0786d56af0672eaef44b29f4ed5c12cb - - path: results/reports/mosdepth/test/test.recal.regions.bed.gz - md5sum: b8719430e56a58f734884bb422a7b8fa - - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi - md5sum: e3235323f455414ee3acc7144e659caf - - path: results/reports/mosdepth/test/test.sorted.mosdepth.global.dist.txt - md5sum: 48aa760b024d7c0ddd5a66f89a1cb544 - - path: results/reports/mosdepth/test/test.sorted.mosdepth.region.dist.txt - md5sum: 71e938314bba70f978271b2b56cb7ad3 - - path: results/reports/mosdepth/test/test.sorted.mosdepth.summary.txt - md5sum: 0786d56af0672eaef44b29f4ed5c12cb - - path: results/reports/mosdepth/test/test.sorted.regions.bed.gz - md5sum: b8719430e56a58f734884bb422a7b8fa - - path: results/reports/mosdepth/test/test.sorted.regions.bed.gz.csi - md5sum: e3235323f455414ee3acc7144e659caf - - path: results/reports/samtools/test/test.recal.cram.stats - # conda changes md5sums for test. - - path: results/reports/samtools/test/test.sorted.cram.stats - # conda changes md5sums for test. - - path: results/csv/markduplicates.csv - should_exist: false - - path: results/csv/markduplicates_no_table.csv - should_exist: false - - path: results/preprocessing/mapped/test/test.bam - should_exist: false - - path: results/preprocessing/mapped/test/test.sorted.bam - should_exist: false -- name: Run default pipeline with skipping Markduplicates with save_mapped - command: nextflow run main.nf -profile test,skip_markduplicates --save_mapped - tags: - - default_extended - - preprocessing - - save_mapped - files: - - path: results/csv/mapped.csv - md5sum: 3bee45ccf65e301ce09ee4eed8f26933 - - path: results/csv/recalibrated.csv - md5sum: 2d29d9e53894dcce96a1b5beb6ef3312 - - path: results/multiqc - - path: results/preprocessing/mapped/test/test.sorted.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/mapped/test/test.sorted.cram.crai - # binary changes md5sums on reruns. - - path: results/preprocessing/recal_table/test/test.recal.table - md5sum: 8de213f4c00fac61a1102633760493df - - path: results/preprocessing/recalibrated/test/test.recal.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/recalibrated/test/test.recal.cram.crai - # binary changes md5sums on reruns. - - path: results/reports/fastqc/test-test_L1 - - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt - md5sum: 48aa760b024d7c0ddd5a66f89a1cb544 - - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt - md5sum: 71e938314bba70f978271b2b56cb7ad3 - - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt - md5sum: 0786d56af0672eaef44b29f4ed5c12cb - - path: results/reports/mosdepth/test/test.recal.regions.bed.gz - md5sum: b8719430e56a58f734884bb422a7b8fa - - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi - md5sum: e3235323f455414ee3acc7144e659caf - - path: results/reports/mosdepth/test/test.sorted.mosdepth.global.dist.txt - md5sum: 48aa760b024d7c0ddd5a66f89a1cb544 - - path: results/reports/mosdepth/test/test.sorted.mosdepth.region.dist.txt - md5sum: 71e938314bba70f978271b2b56cb7ad3 - - path: results/reports/mosdepth/test/test.sorted.mosdepth.summary.txt - md5sum: 0786d56af0672eaef44b29f4ed5c12cb - - path: results/reports/mosdepth/test/test.sorted.regions.bed.gz - md5sum: b8719430e56a58f734884bb422a7b8fa - - path: results/reports/mosdepth/test/test.sorted.regions.bed.gz.csi - md5sum: e3235323f455414ee3acc7144e659caf - - path: results/reports/samtools/test/test.recal.cram.stats - # conda changes md5sums for test. - - path: results/reports/samtools/test/test.sorted.cram.stats - # conda changes md5sums for test. - - path: results/csv/markduplicates.csv - should_exist: false - - path: results/csv/markduplicates_no_table.csv - should_exist: false - - path: results/preprocessing/mapped/test/test.bam - should_exist: false -- name: Run default pipeline with skipping Markduplicates with save_mapped & save_output_as_bam - command: nextflow run main.nf -profile test,skip_markduplicates --save_mapped --save_output_as_bam - tags: - - default_extended - - preprocessing - - save_output_as_bam - files: - - path: results/csv/mapped.csv - md5sum: 7f21bf40d3fbc248ee2ea3fdf0f7cdb2 - - path: results/csv/recalibrated.csv - md5sum: 2dfbcaaeaaf4937c51c5c310f1c77614 - - path: results/multiqc - - path: results/preprocessing/mapped/test/test.sorted.bam - # binary changes md5sums on reruns. - - path: results/preprocessing/mapped/test/test.sorted.bam.bai - # binary changes md5sums on reruns. - - path: results/preprocessing/recal_table/test/test.recal.table - md5sum: 8de213f4c00fac61a1102633760493df - - path: results/preprocessing/recalibrated/test/test.recal.bam - # binary changes md5sums on reruns. - - path: results/preprocessing/recalibrated/test/test.recal.bam.bai - # binary changes md5sums on reruns. - - path: results/reports/fastqc/test-test_L1 - - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt - md5sum: 48aa760b024d7c0ddd5a66f89a1cb544 - - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt - md5sum: 71e938314bba70f978271b2b56cb7ad3 - - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt - md5sum: 0786d56af0672eaef44b29f4ed5c12cb - - path: results/reports/mosdepth/test/test.recal.regions.bed.gz - md5sum: b8719430e56a58f734884bb422a7b8fa - - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi - md5sum: e3235323f455414ee3acc7144e659caf - - path: results/reports/mosdepth/test/test.sorted.mosdepth.global.dist.txt - md5sum: 48aa760b024d7c0ddd5a66f89a1cb544 - - path: results/reports/mosdepth/test/test.sorted.mosdepth.region.dist.txt - md5sum: 71e938314bba70f978271b2b56cb7ad3 - - path: results/reports/mosdepth/test/test.sorted.mosdepth.summary.txt - md5sum: 0786d56af0672eaef44b29f4ed5c12cb - - path: results/reports/mosdepth/test/test.sorted.regions.bed.gz - md5sum: b8719430e56a58f734884bb422a7b8fa - - path: results/reports/mosdepth/test/test.sorted.regions.bed.gz.csi - md5sum: e3235323f455414ee3acc7144e659caf - - path: results/reports/samtools/test/test.recal.cram.stats - # conda changes md5sums for test. - - path: results/reports/samtools/test/test.sorted.cram.stats - # conda changes md5sums for test. - - path: results/csv/markduplicates.csv - should_exist: false - - path: results/csv/markduplicates_no_table.csv - should_exist: false - - path: results/preprocessing/mapped/test/test.bam - should_exist: false -- name: Run default pipeline with skipping all QC steps - command: nextflow run main.nf -profile test --skip_tools fastqc,markduplicates_report,mosdepth,multiqc,samtools - tags: - - default_extended - - preprocessing - - skip_qc - - variant_calling - files: - - path: results/csv/markduplicates.csv - md5sum: 0d6120bb99e92f6810343270711ca53e - - path: results/csv/markduplicates_no_table.csv - md5sum: 2a2d3d4842befd4def39156463859ee3 - - path: results/csv/recalibrated.csv - md5sum: 2d29d9e53894dcce96a1b5beb6ef3312 - - path: results/preprocessing/markduplicates/test/test.md.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/markduplicates/test/test.md.cram.crai - # binary changes md5sums on reruns. - - path: results/preprocessing/recal_table/test/test.recal.table - md5sum: 4ac774bf5f1157e77426fd82f5ac0fbe - - path: results/preprocessing/recalibrated/test/test.recal.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/recalibrated/test/test.recal.cram.crai - # binary changes md5sums on reruns. - - path: results/multiqc - should_exist: false - - path: results/reports/fastqc - should_exist: false - - path: results/reports/markduplicates - should_exist: false - - path: results/reports/mosdepth - should_exist: false - - path: results/reports/samtools - should_exist: false - - path: results/reports/bcftools/strelka/test/test.strelka.variants.bcftools_stats.txt - # conda changes md5sums for test. - - path: results/reports/vcftools/strelka/test/test.strelka.variants.FILTER.summary - md5sum: dd87f507da7de20d5318841af312493b - - path: results/reports/vcftools/strelka/test/test.strelka.variants.TsTv.count - md5sum: fa27f678965b7cba6a92efcd039f802a - - path: results/reports/vcftools/strelka/test/test.strelka.variants.TsTv.qual - md5sum: bc68ae4e688e9fb772b457069e604883 - - path: results/variant_calling/strelka/test/test.strelka.genome.vcf.gz - # binary changes md5sums on reruns. - - path: results/variant_calling/strelka/test/test.strelka.genome.vcf.gz.tbi - # binary changes md5sums on reruns. - - path: results/variant_calling/strelka/test/test.strelka.variants.vcf.gz - # binary changes md5sums on reruns. - - path: results/variant_calling/strelka/test/test.strelka.variants.vcf.gz.tbi - - path: results/strelka - should_exist: false -- name: Run default pipeline for tumor normal pair - command: nextflow run main.nf -profile test,pair - tags: - - default_extended - - preprocessing - - tumor_normal_pair - files: - - path: results/csv/markduplicates.csv - md5sum: e8e587ac25253ff7ab8f1cc66d410c98 - - path: results/csv/markduplicates_no_table.csv - md5sum: 617574c9b607e5daaf4ad56d48982247 - - path: results/csv/recalibrated.csv - md5sum: 008dff17e2a0d96ef9c1cae12fcab6ab - - path: results/multiqc - - path: results/preprocessing/markduplicates/test/test.md.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/markduplicates/test/test.md.cram.crai - # binary changes md5sums on reruns. - - path: results/preprocessing/recal_table/test/test.recal.table - md5sum: 4ac774bf5f1157e77426fd82f5ac0fbe - - path: results/preprocessing/recalibrated/test/test.recal.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/recalibrated/test/test.recal.cram.crai - # binary changes md5sums on reruns. - - path: results/preprocessing/markduplicates/test2/test2.md.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/markduplicates/test2/test2.md.cram.crai - # binary changes md5sums on reruns. - - path: results/preprocessing/recal_table/test2/test2.recal.table - md5sum: 0626cd4337eab79b38b5bc5c95e0c003 - - path: results/preprocessing/recalibrated/test2/test2.recal.cram - # binary changes md5sums on reruns. - - path: results/preprocessing/recalibrated/test2/test2.recal.cram.crai - # binary changes md5sums on reruns. - - path: results/reports/fastqc/test-test_L1 - - path: results/reports/fastqc/test2-test_L1 - - path: results/reports/markduplicates/test/test.md.cram.metrics - contains: ["test 8547 767 84 523391 3882 0 0 0.385081", "1.0 767 767"] - - path: results/reports/markduplicates/test2/test2.md.cram.metrics - contains: ["test2 10103 880 35 523579 4837 2 0 0.408076 193306", "1.0 1 876 876", "100.0 80.515303 0 0"] - - path: results/reports/mosdepth/test/test.md.mosdepth.global.dist.txt - md5sum: 76fa71922a3f748e507c2364c531dfcb - - path: results/reports/mosdepth/test/test.md.mosdepth.region.dist.txt - md5sum: abc5df85e302b79985627888870882da - - path: results/reports/mosdepth/test/test.md.mosdepth.summary.txt - md5sum: d536456436eb275159b8c6af83213d80 - - path: results/reports/mosdepth/test/test.md.regions.bed.gz - md5sum: 38fe39894abe62e38f8ac214cba64f2b - - path: results/reports/mosdepth/test/test.md.regions.bed.gz.csi - md5sum: b1c2a861f64e20a94108a6de3b76c582 - - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt - md5sum: 76fa71922a3f748e507c2364c531dfcb - - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt - md5sum: abc5df85e302b79985627888870882da - - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt - md5sum: d536456436eb275159b8c6af83213d80 - - path: results/reports/mosdepth/test/test.recal.regions.bed.gz - md5sum: 38fe39894abe62e38f8ac214cba64f2b - - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi - md5sum: b1c2a861f64e20a94108a6de3b76c582 - - path: results/reports/mosdepth/test2/test2.md.mosdepth.global.dist.txt - md5sum: 2020cf6dfc7ddca020c921dd9f0549b7 - - path: results/reports/mosdepth/test2/test2.md.mosdepth.region.dist.txt - md5sum: 38ff8b38c33b9231f047fea8ea830aae - - path: results/reports/mosdepth/test2/test2.md.mosdepth.summary.txt - md5sum: 8b991358768cade225470a07cd34f573 - - path: results/reports/mosdepth/test2/test2.md.regions.bed.gz - md5sum: 5d67bc6ea9f077abb4fdac3b087c6387 - - path: results/reports/mosdepth/test2/test2.md.regions.bed.gz.csi - md5sum: d5f1c9389ecf52ba839e834780a94549 - - path: results/reports/mosdepth/test2/test2.recal.mosdepth.global.dist.txt - md5sum: 2020cf6dfc7ddca020c921dd9f0549b7 - - path: results/reports/mosdepth/test2/test2.recal.mosdepth.region.dist.txt - md5sum: 38ff8b38c33b9231f047fea8ea830aae - - path: results/reports/mosdepth/test2/test2.recal.mosdepth.summary.txt - md5sum: 8b991358768cade225470a07cd34f573 - - path: results/reports/mosdepth/test2/test2.recal.regions.bed.gz - md5sum: 5d67bc6ea9f077abb4fdac3b087c6387 - - path: results/reports/mosdepth/test2/test2.recal.regions.bed.gz.csi - md5sum: d5f1c9389ecf52ba839e834780a94549 - - path: results/reports/samtools/test/test.md.cram.stats - # conda changes md5sums for test. - - path: results/reports/samtools/test/test.recal.cram.stats - # conda changes md5sums for test. - - path: results/reports/samtools/test2/test2.md.cram.stats - # conda changes md5sums for test. - - path: results/reports/samtools/test2/test2.recal.cram.stats - # conda changes md5sums for test. - - path: results/preprocessing/mapped/ - should_exist: false diff --git a/tests/test_save_mapped.yml b/tests/test_save_mapped.yml new file mode 100644 index 0000000000..a49422665c --- /dev/null +++ b/tests/test_save_mapped.yml @@ -0,0 +1,76 @@ +- name: Run save_mapped + command: nextflow run main.nf -profile test --save_mapped + tags: + - default_extended + - preprocessing + - save_mapped + - save_mapped_only + - variant_calling + files: + - path: results/csv/mapped.csv + md5sum: 3bee45ccf65e301ce09ee4eed8f26933 + - path: results/csv/markduplicates.csv + md5sum: 0d6120bb99e92f6810343270711ca53e + - path: results/csv/markduplicates_no_table.csv + md5sum: 2a2d3d4842befd4def39156463859ee3 + - path: results/csv/recalibrated.csv + md5sum: 2d29d9e53894dcce96a1b5beb6ef3312 + - path: results/multiqc + - path: results/preprocessing/mapped/test/test.sorted.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/mapped/test/test.sorted.cram.crai + # binary changes md5sums on reruns. + - path: results/preprocessing/markduplicates/test/test.md.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/markduplicates/test/test.md.cram.crai + # binary changes md5sums on reruns. + - path: results/preprocessing/recal_table/test/test.recal.table + md5sum: 4ac774bf5f1157e77426fd82f5ac0fbe + - path: results/preprocessing/recalibrated/test/test.recal.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/recalibrated/test/test.recal.cram.crai + # binary changes md5sums on reruns. + - path: results/reports/fastqc/test-test_L1 + - path: results/reports/markduplicates/test/test.md.cram.metrics + contains: ["test 8547 767 84 523391 3882 0 0 0.385081", "1.0 767 767"] + - path: results/reports/mosdepth/test/test.md.mosdepth.global.dist.txt + md5sum: 76fa71922a3f748e507c2364c531dfcb + - path: results/reports/mosdepth/test/test.md.mosdepth.region.dist.txt + md5sum: abc5df85e302b79985627888870882da + - path: results/reports/mosdepth/test/test.md.mosdepth.summary.txt + md5sum: d536456436eb275159b8c6af83213d80 + - path: results/reports/mosdepth/test/test.md.regions.bed.gz + md5sum: 38fe39894abe62e38f8ac214cba64f2b + - path: results/reports/mosdepth/test/test.md.regions.bed.gz.csi + md5sum: b1c2a861f64e20a94108a6de3b76c582 + - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt + md5sum: 76fa71922a3f748e507c2364c531dfcb + - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt + md5sum: abc5df85e302b79985627888870882da + - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt + md5sum: d536456436eb275159b8c6af83213d80 + - path: results/reports/mosdepth/test/test.recal.regions.bed.gz + md5sum: 38fe39894abe62e38f8ac214cba64f2b + - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi + md5sum: b1c2a861f64e20a94108a6de3b76c582 + - path: results/reports/samtools/test/test.md.cram.stats + # conda changes md5sums for test. + - path: results/reports/samtools/test/test.recal.cram.stats + # conda changes md5sums for test. + - path: results/reports/bcftools/strelka/test/test.strelka.variants.bcftools_stats.txt + # conda changes md5sums for test. + - path: results/reports/vcftools/strelka/test/test.strelka.variants.FILTER.summary + md5sum: dd87f507da7de20d5318841af312493b + - path: results/reports/vcftools/strelka/test/test.strelka.variants.TsTv.count + md5sum: fa27f678965b7cba6a92efcd039f802a + - path: results/reports/vcftools/strelka/test/test.strelka.variants.TsTv.qual + md5sum: bc68ae4e688e9fb772b457069e604883 + - path: results/variant_calling/strelka/test/test.strelka.genome.vcf.gz + # binary changes md5sums on reruns. + - path: results/variant_calling/strelka/test/test.strelka.genome.vcf.gz.tbi + # binary changes md5sums on reruns. + - path: results/variant_calling/strelka/test/test.strelka.variants.vcf.gz + # binary changes md5sums on reruns. + - path: results/variant_calling/strelka/test/test.strelka.variants.vcf.gz.tbi + - path: results/strelka + should_exist: false diff --git a/tests/test_save_output_as_bam_only.yml b/tests/test_save_output_as_bam_only.yml new file mode 100644 index 0000000000..374cdeb69e --- /dev/null +++ b/tests/test_save_output_as_bam_only.yml @@ -0,0 +1,70 @@ +- name: Run save_output_as_bam + command: nextflow run main.nf -profile test --save_output_as_bam + tags: + - default_extended + - preprocessing + - save_output_as_bam + - save_output_as_bam_only + - variant_calling + files: + - path: results/csv/markduplicates.csv + md5sum: 6004ab16b63012e336f6251396a983c5 + - path: results/csv/markduplicates_no_table.csv + md5sum: 8a145eca178cfd02403d60122b9d3960 + - path: results/csv/recalibrated.csv + md5sum: 2dfbcaaeaaf4937c51c5c310f1c77614 + - path: results/multiqc + - path: results/preprocessing/markduplicates/test/test.md.bam.bai + # conda changes md5sums for test. + - path: results/preprocessing/markduplicates/test/test.md.bam + # conda changes md5sums for test. + - path: results/preprocessing/recal_table/test/test.recal.table + md5sum: 4ac774bf5f1157e77426fd82f5ac0fbe + - path: results/preprocessing/recalibrated/test/test.recal.bam + # binary changes md5sums on reruns. + - path: results/preprocessing/recalibrated/test/test.recal.bam.bai + # binary changes md5sums on reruns. + - path: results/reports/fastqc/test-test_L1 + - path: results/reports/markduplicates/test/test.md.cram.metrics + contains: ["test 8547 767 84 523391 3882 0 0 0.385081", "1.0 767 767"] + - path: results/reports/mosdepth/test/test.md.mosdepth.global.dist.txt + md5sum: 76fa71922a3f748e507c2364c531dfcb + - path: results/reports/mosdepth/test/test.md.mosdepth.region.dist.txt + md5sum: abc5df85e302b79985627888870882da + - path: results/reports/mosdepth/test/test.md.mosdepth.summary.txt + md5sum: d536456436eb275159b8c6af83213d80 + - path: results/reports/mosdepth/test/test.md.regions.bed.gz + md5sum: 38fe39894abe62e38f8ac214cba64f2b + - path: results/reports/mosdepth/test/test.md.regions.bed.gz.csi + md5sum: b1c2a861f64e20a94108a6de3b76c582 + - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt + md5sum: 76fa71922a3f748e507c2364c531dfcb + - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt + md5sum: abc5df85e302b79985627888870882da + - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt + md5sum: d536456436eb275159b8c6af83213d80 + - path: results/reports/mosdepth/test/test.recal.regions.bed.gz + md5sum: 38fe39894abe62e38f8ac214cba64f2b + - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi + md5sum: b1c2a861f64e20a94108a6de3b76c582 + - path: results/reports/samtools/test/test.md.cram.stats + # conda changes md5sums for test. + - path: results/reports/samtools/test/test.recal.cram.stats + # conda changes md5sums for test. + - path: results/reports/bcftools/strelka/test/test.strelka.variants.bcftools_stats.txt + # conda changes md5sums for test. + - path: results/reports/vcftools/strelka/test/test.strelka.variants.FILTER.summary + md5sum: dd87f507da7de20d5318841af312493b + - path: results/reports/vcftools/strelka/test/test.strelka.variants.TsTv.count + md5sum: fa27f678965b7cba6a92efcd039f802a + - path: results/reports/vcftools/strelka/test/test.strelka.variants.TsTv.qual + md5sum: bc68ae4e688e9fb772b457069e604883 + - path: results/variant_calling/strelka/test/test.strelka.genome.vcf.gz + # binary changes md5sums on reruns. + - path: results/variant_calling/strelka/test/test.strelka.genome.vcf.gz.tbi + # binary changes md5sums on reruns. + - path: results/variant_calling/strelka/test/test.strelka.variants.vcf.gz + # binary changes md5sums on reruns. + - path: results/variant_calling/strelka/test/test.strelka.variants.vcf.gz.tbi + - path: results/strelka + should_exist: false diff --git a/tests/test_skip_all_qc.yml b/tests/test_skip_all_qc.yml new file mode 100644 index 0000000000..c65758c000 --- /dev/null +++ b/tests/test_skip_all_qc.yml @@ -0,0 +1,52 @@ +- name: Run default pipeline with skipping all QC steps + command: nextflow run main.nf -profile test --skip_tools fastqc,markduplicates_report,mosdepth,multiqc,samtools + tags: + - default_extended + - preprocessing + - skip_all_qc + - skip_qc + - variant_calling + files: + - path: results/csv/markduplicates.csv + md5sum: 0d6120bb99e92f6810343270711ca53e + - path: results/csv/markduplicates_no_table.csv + md5sum: 2a2d3d4842befd4def39156463859ee3 + - path: results/csv/recalibrated.csv + md5sum: 2d29d9e53894dcce96a1b5beb6ef3312 + - path: results/preprocessing/markduplicates/test/test.md.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/markduplicates/test/test.md.cram.crai + # binary changes md5sums on reruns. + - path: results/preprocessing/recal_table/test/test.recal.table + md5sum: 4ac774bf5f1157e77426fd82f5ac0fbe + - path: results/preprocessing/recalibrated/test/test.recal.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/recalibrated/test/test.recal.cram.crai + # binary changes md5sums on reruns. + - path: results/multiqc + should_exist: false + - path: results/reports/fastqc + should_exist: false + - path: results/reports/markduplicates + should_exist: false + - path: results/reports/mosdepth + should_exist: false + - path: results/reports/samtools + should_exist: false + - path: results/reports/bcftools/strelka/test/test.strelka.variants.bcftools_stats.txt + # conda changes md5sums for test. + - path: results/reports/vcftools/strelka/test/test.strelka.variants.FILTER.summary + md5sum: dd87f507da7de20d5318841af312493b + - path: results/reports/vcftools/strelka/test/test.strelka.variants.TsTv.count + md5sum: fa27f678965b7cba6a92efcd039f802a + - path: results/reports/vcftools/strelka/test/test.strelka.variants.TsTv.qual + md5sum: bc68ae4e688e9fb772b457069e604883 + - path: results/variant_calling/strelka/test/test.strelka.genome.vcf.gz + # binary changes md5sums on reruns. + - path: results/variant_calling/strelka/test/test.strelka.genome.vcf.gz.tbi + # binary changes md5sums on reruns. + - path: results/variant_calling/strelka/test/test.strelka.variants.vcf.gz + # binary changes md5sums on reruns. + - path: results/variant_calling/strelka/test/test.strelka.variants.vcf.gz.tbi + - path: results/strelka + should_exist: false diff --git a/tests/test_skip_markduplicates.yml b/tests/test_skip_markduplicates.yml new file mode 100644 index 0000000000..f98e1077d2 --- /dev/null +++ b/tests/test_skip_markduplicates.yml @@ -0,0 +1,163 @@ +- name: Run default pipeline with skipping Markduplicates + command: nextflow run main.nf -profile test,skip_markduplicates + tags: + - default_extended + - preprocessing + - skip_markduplicates + files: + - path: results/csv/mapped.csv + md5sum: 3bee45ccf65e301ce09ee4eed8f26933 + - path: results/csv/recalibrated.csv + md5sum: 2d29d9e53894dcce96a1b5beb6ef3312 + - path: results/multiqc + - path: results/preprocessing/mapped/test/test.sorted.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/mapped/test/test.sorted.cram.crai + # binary changes md5sums on reruns. + - path: results/preprocessing/recal_table/test/test.recal.table + md5sum: 8de213f4c00fac61a1102633760493df + - path: results/preprocessing/recalibrated/test/test.recal.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/recalibrated/test/test.recal.cram.crai + # binary changes md5sums on reruns. + - path: results/reports/fastqc/test-test_L1 + - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt + md5sum: 48aa760b024d7c0ddd5a66f89a1cb544 + - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt + md5sum: 71e938314bba70f978271b2b56cb7ad3 + - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt + md5sum: 0786d56af0672eaef44b29f4ed5c12cb + - path: results/reports/mosdepth/test/test.recal.regions.bed.gz + md5sum: b8719430e56a58f734884bb422a7b8fa + - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi + md5sum: e3235323f455414ee3acc7144e659caf + - path: results/reports/mosdepth/test/test.sorted.mosdepth.global.dist.txt + md5sum: 48aa760b024d7c0ddd5a66f89a1cb544 + - path: results/reports/mosdepth/test/test.sorted.mosdepth.region.dist.txt + md5sum: 71e938314bba70f978271b2b56cb7ad3 + - path: results/reports/mosdepth/test/test.sorted.mosdepth.summary.txt + md5sum: 0786d56af0672eaef44b29f4ed5c12cb + - path: results/reports/mosdepth/test/test.sorted.regions.bed.gz + md5sum: b8719430e56a58f734884bb422a7b8fa + - path: results/reports/mosdepth/test/test.sorted.regions.bed.gz.csi + md5sum: e3235323f455414ee3acc7144e659caf + - path: results/reports/samtools/test/test.recal.cram.stats + # conda changes md5sums for test. + - path: results/reports/samtools/test/test.sorted.cram.stats + # conda changes md5sums for test. + - path: results/csv/markduplicates.csv + should_exist: false + - path: results/csv/markduplicates_no_table.csv + should_exist: false + - path: results/preprocessing/mapped/test/test.bam + should_exist: false + - path: results/preprocessing/mapped/test/test.sorted.bam + should_exist: false +- name: Run default pipeline with skipping Markduplicates with save_mapped + command: nextflow run main.nf -profile test,skip_markduplicates --save_mapped + tags: + - default_extended + - preprocessing + - save_mapped + - skip_markduplicates + files: + - path: results/csv/mapped.csv + md5sum: 3bee45ccf65e301ce09ee4eed8f26933 + - path: results/csv/recalibrated.csv + md5sum: 2d29d9e53894dcce96a1b5beb6ef3312 + - path: results/multiqc + - path: results/preprocessing/mapped/test/test.sorted.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/mapped/test/test.sorted.cram.crai + # binary changes md5sums on reruns. + - path: results/preprocessing/recal_table/test/test.recal.table + md5sum: 8de213f4c00fac61a1102633760493df + - path: results/preprocessing/recalibrated/test/test.recal.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/recalibrated/test/test.recal.cram.crai + # binary changes md5sums on reruns. + - path: results/reports/fastqc/test-test_L1 + - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt + md5sum: 48aa760b024d7c0ddd5a66f89a1cb544 + - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt + md5sum: 71e938314bba70f978271b2b56cb7ad3 + - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt + md5sum: 0786d56af0672eaef44b29f4ed5c12cb + - path: results/reports/mosdepth/test/test.recal.regions.bed.gz + md5sum: b8719430e56a58f734884bb422a7b8fa + - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi + md5sum: e3235323f455414ee3acc7144e659caf + - path: results/reports/mosdepth/test/test.sorted.mosdepth.global.dist.txt + md5sum: 48aa760b024d7c0ddd5a66f89a1cb544 + - path: results/reports/mosdepth/test/test.sorted.mosdepth.region.dist.txt + md5sum: 71e938314bba70f978271b2b56cb7ad3 + - path: results/reports/mosdepth/test/test.sorted.mosdepth.summary.txt + md5sum: 0786d56af0672eaef44b29f4ed5c12cb + - path: results/reports/mosdepth/test/test.sorted.regions.bed.gz + md5sum: b8719430e56a58f734884bb422a7b8fa + - path: results/reports/mosdepth/test/test.sorted.regions.bed.gz.csi + md5sum: e3235323f455414ee3acc7144e659caf + - path: results/reports/samtools/test/test.recal.cram.stats + # conda changes md5sums for test. + - path: results/reports/samtools/test/test.sorted.cram.stats + # conda changes md5sums for test. + - path: results/csv/markduplicates.csv + should_exist: false + - path: results/csv/markduplicates_no_table.csv + should_exist: false + - path: results/preprocessing/mapped/test/test.bam + should_exist: false +- name: Run default pipeline with skipping Markduplicates with save_mapped & save_output_as_bam + command: nextflow run main.nf -profile test,skip_markduplicates --save_mapped --save_output_as_bam + tags: + - default_extended + - preprocessing + - save_output_as_bam + - skip_markduplicates + files: + - path: results/csv/mapped.csv + md5sum: 7f21bf40d3fbc248ee2ea3fdf0f7cdb2 + - path: results/csv/recalibrated.csv + md5sum: 2dfbcaaeaaf4937c51c5c310f1c77614 + - path: results/multiqc + - path: results/preprocessing/mapped/test/test.sorted.bam + # binary changes md5sums on reruns. + - path: results/preprocessing/mapped/test/test.sorted.bam.bai + # binary changes md5sums on reruns. + - path: results/preprocessing/recal_table/test/test.recal.table + md5sum: 8de213f4c00fac61a1102633760493df + - path: results/preprocessing/recalibrated/test/test.recal.bam + # binary changes md5sums on reruns. + - path: results/preprocessing/recalibrated/test/test.recal.bam.bai + # binary changes md5sums on reruns. + - path: results/reports/fastqc/test-test_L1 + - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt + md5sum: 48aa760b024d7c0ddd5a66f89a1cb544 + - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt + md5sum: 71e938314bba70f978271b2b56cb7ad3 + - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt + md5sum: 0786d56af0672eaef44b29f4ed5c12cb + - path: results/reports/mosdepth/test/test.recal.regions.bed.gz + md5sum: b8719430e56a58f734884bb422a7b8fa + - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi + md5sum: e3235323f455414ee3acc7144e659caf + - path: results/reports/mosdepth/test/test.sorted.mosdepth.global.dist.txt + md5sum: 48aa760b024d7c0ddd5a66f89a1cb544 + - path: results/reports/mosdepth/test/test.sorted.mosdepth.region.dist.txt + md5sum: 71e938314bba70f978271b2b56cb7ad3 + - path: results/reports/mosdepth/test/test.sorted.mosdepth.summary.txt + md5sum: 0786d56af0672eaef44b29f4ed5c12cb + - path: results/reports/mosdepth/test/test.sorted.regions.bed.gz + md5sum: b8719430e56a58f734884bb422a7b8fa + - path: results/reports/mosdepth/test/test.sorted.regions.bed.gz.csi + md5sum: e3235323f455414ee3acc7144e659caf + - path: results/reports/samtools/test/test.recal.cram.stats + # conda changes md5sums for test. + - path: results/reports/samtools/test/test.sorted.cram.stats + # conda changes md5sums for test. + - path: results/csv/markduplicates.csv + should_exist: false + - path: results/csv/markduplicates_no_table.csv + should_exist: false + - path: results/preprocessing/mapped/test/test.bam + should_exist: false diff --git a/tests/test_tumor_normal_pair.yml b/tests/test_tumor_normal_pair.yml new file mode 100644 index 0000000000..297a91a6d8 --- /dev/null +++ b/tests/test_tumor_normal_pair.yml @@ -0,0 +1,90 @@ +- name: Run default pipeline for tumor normal pair + command: nextflow run main.nf -profile test,pair + tags: + - default_extended + - preprocessing + - tumor_normal_pair + files: + - path: results/csv/markduplicates.csv + md5sum: e8e587ac25253ff7ab8f1cc66d410c98 + - path: results/csv/markduplicates_no_table.csv + md5sum: 617574c9b607e5daaf4ad56d48982247 + - path: results/csv/recalibrated.csv + md5sum: 008dff17e2a0d96ef9c1cae12fcab6ab + - path: results/multiqc + - path: results/preprocessing/markduplicates/test/test.md.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/markduplicates/test/test.md.cram.crai + # binary changes md5sums on reruns. + - path: results/preprocessing/recal_table/test/test.recal.table + md5sum: 4ac774bf5f1157e77426fd82f5ac0fbe + - path: results/preprocessing/recalibrated/test/test.recal.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/recalibrated/test/test.recal.cram.crai + # binary changes md5sums on reruns. + - path: results/preprocessing/markduplicates/test2/test2.md.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/markduplicates/test2/test2.md.cram.crai + # binary changes md5sums on reruns. + - path: results/preprocessing/recal_table/test2/test2.recal.table + md5sum: 0626cd4337eab79b38b5bc5c95e0c003 + - path: results/preprocessing/recalibrated/test2/test2.recal.cram + # binary changes md5sums on reruns. + - path: results/preprocessing/recalibrated/test2/test2.recal.cram.crai + # binary changes md5sums on reruns. + - path: results/reports/fastqc/test-test_L1 + - path: results/reports/fastqc/test2-test_L1 + - path: results/reports/markduplicates/test/test.md.cram.metrics + contains: ["test 8547 767 84 523391 3882 0 0 0.385081", "1.0 767 767"] + - path: results/reports/markduplicates/test2/test2.md.cram.metrics + contains: ["test2 10103 880 35 523579 4837 2 0 0.408076 193306", "1.0 1 876 876", "100.0 80.515303 0 0"] + - path: results/reports/mosdepth/test/test.md.mosdepth.global.dist.txt + md5sum: 76fa71922a3f748e507c2364c531dfcb + - path: results/reports/mosdepth/test/test.md.mosdepth.region.dist.txt + md5sum: abc5df85e302b79985627888870882da + - path: results/reports/mosdepth/test/test.md.mosdepth.summary.txt + md5sum: d536456436eb275159b8c6af83213d80 + - path: results/reports/mosdepth/test/test.md.regions.bed.gz + md5sum: 38fe39894abe62e38f8ac214cba64f2b + - path: results/reports/mosdepth/test/test.md.regions.bed.gz.csi + md5sum: b1c2a861f64e20a94108a6de3b76c582 + - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt + md5sum: 76fa71922a3f748e507c2364c531dfcb + - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt + md5sum: abc5df85e302b79985627888870882da + - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt + md5sum: d536456436eb275159b8c6af83213d80 + - path: results/reports/mosdepth/test/test.recal.regions.bed.gz + md5sum: 38fe39894abe62e38f8ac214cba64f2b + - path: results/reports/mosdepth/test/test.recal.regions.bed.gz.csi + md5sum: b1c2a861f64e20a94108a6de3b76c582 + - path: results/reports/mosdepth/test2/test2.md.mosdepth.global.dist.txt + md5sum: 2020cf6dfc7ddca020c921dd9f0549b7 + - path: results/reports/mosdepth/test2/test2.md.mosdepth.region.dist.txt + md5sum: 38ff8b38c33b9231f047fea8ea830aae + - path: results/reports/mosdepth/test2/test2.md.mosdepth.summary.txt + md5sum: 8b991358768cade225470a07cd34f573 + - path: results/reports/mosdepth/test2/test2.md.regions.bed.gz + md5sum: 5d67bc6ea9f077abb4fdac3b087c6387 + - path: results/reports/mosdepth/test2/test2.md.regions.bed.gz.csi + md5sum: d5f1c9389ecf52ba839e834780a94549 + - path: results/reports/mosdepth/test2/test2.recal.mosdepth.global.dist.txt + md5sum: 2020cf6dfc7ddca020c921dd9f0549b7 + - path: results/reports/mosdepth/test2/test2.recal.mosdepth.region.dist.txt + md5sum: 38ff8b38c33b9231f047fea8ea830aae + - path: results/reports/mosdepth/test2/test2.recal.mosdepth.summary.txt + md5sum: 8b991358768cade225470a07cd34f573 + - path: results/reports/mosdepth/test2/test2.recal.regions.bed.gz + md5sum: 5d67bc6ea9f077abb4fdac3b087c6387 + - path: results/reports/mosdepth/test2/test2.recal.regions.bed.gz.csi + md5sum: d5f1c9389ecf52ba839e834780a94549 + - path: results/reports/samtools/test/test.md.cram.stats + # conda changes md5sums for test. + - path: results/reports/samtools/test/test.recal.cram.stats + # conda changes md5sums for test. + - path: results/reports/samtools/test2/test2.md.cram.stats + # conda changes md5sums for test. + - path: results/reports/samtools/test2/test2.recal.cram.stats + # conda changes md5sums for test. + - path: results/preprocessing/mapped/ + should_exist: false