Merge pull request #641 from FriederikeHanssen/estimatelib

Fix duplicate substrings in tools and skip_tools
nf-core · Jul 17, 2022 · 28aa979 · 28aa979
2 parents d2388d1 + 211e62d
commit 28aa979
Show file tree

Hide file tree

Showing 9 changed files with 176 additions and 92 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -51,6 +51,7 @@ jobs:
           - "save_bam_mapped"
           - "save_output_as_bam"
           - "skip_markduplicates"
+          - "skip_qc"
           - "split_fastq"
           - "strelka"
           - "strelkabp"

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -134,6 +134,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#618](https://github.com/nf-core/sarek/pull/618) - Fix issue with tiddit [#621](https://github.com/nf-core/sarek/issues/621)
 - [#618](https://github.com/nf-core/sarek/pull/618) - Fix channel issue with `targets.bed` in prepare_intervals
 - [#634](https://github.com/nf-core/sarek/pull/634) - Fix issue with samtools/mosdepth plots in multiqc_report
+- [#641](https://github.com/nf-core/sarek/pull/641) - Fix issue with duplicate substring in tools and skip_tools
 
 ### Deprecated
 

diff --git a/conf/modules.config b/conf/modules.config
diff --git a/subworkflows/local/annotate.nf b/subworkflows/local/annotate.nf
@@ -18,23 +18,23 @@ workflow ANNOTATE {
     vep_cache_version
     vep_cache
     vep_extra_files
-    
+
     main:
     ch_reports   = Channel.empty()
     ch_vcf_ann   = Channel.empty()
     ch_tab_ann   = Channel.empty()
     ch_json_ann  = Channel.empty()
     ch_versions  = Channel.empty()
 
-    if (tools.contains('merge') || tools.contains('snpeff')) {
+    if (tools.split(',').contains('merge') || tools.split(',').contains('snpeff')) {
         ANNOTATION_SNPEFF(vcf, snpeff_db, snpeff_cache)
 
         ch_reports  = ch_reports.mix(ANNOTATION_SNPEFF.out.reports)
         ch_vcf_ann  = ch_vcf_ann.mix(ANNOTATION_SNPEFF.out.vcf_tbi)
         ch_versions = ch_versions.mix(ANNOTATION_SNPEFF.out.versions.first())
     }
 
-    if (tools.contains('merge')) {
+    if (tools.split(',').contains('merge')) {
         vcf_ann_for_merge = ANNOTATION_SNPEFF.out.vcf_tbi.map{ meta, vcf, tbi -> [meta, vcf] }
         ANNOTATION_MERGE(vcf_ann_for_merge, fasta, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
 
@@ -43,7 +43,7 @@ workflow ANNOTATE {
         ch_versions = ch_versions.mix(ANNOTATION_MERGE.out.versions.first())
     }
 
-    if (tools.contains('vep')) {
+    if (tools.split(',').contains('vep')) {
         ANNOTATION_ENSEMBLVEP(vcf, fasta, vep_genome, vep_species, vep_cache_version, vep_cache, vep_extra_files)
 
         ch_reports   = ch_reports.mix(ANNOTATION_ENSEMBLVEP.out.reports)

diff --git a/subworkflows/local/germline_variant_calling.nf b/subworkflows/local/germline_variant_calling.nf
@@ -42,6 +42,7 @@ workflow GERMLINE_VARIANT_CALLING {
     strelka_vcf         = Channel.empty()
     tiddit_vcf          = Channel.empty()
 
+    println tools
     // Remap channel with intervals
     cram_recalibrated_intervals = cram_recalibrated.combine(intervals)
         .map{ meta, cram, crai, intervals, num_intervals ->
@@ -65,7 +66,7 @@ workflow GERMLINE_VARIANT_CALLING {
             cram, crai, bed_new, tbi_new]
         }
 
-    if(params.tools.contains('mpileup')){
+    if(tools.split(',').contains('mpileup')){
         cram_intervals_no_index = cram_recalibrated_intervals
             .map { meta, cram, crai, intervals ->
                 [meta, cram, intervals]
@@ -79,7 +80,7 @@ workflow GERMLINE_VARIANT_CALLING {
 
     // CNVKIT
 
-    if(tools.contains('cnvkit')){
+    if(tools.split(',').contains('cnvkit')){
         cram_recalibrated_cnvkit_germline = cram_recalibrated
             .map{ meta, cram, crai ->
                 [meta, [], cram]
@@ -94,15 +95,15 @@ workflow GERMLINE_VARIANT_CALLING {
     }
 
     // DEEPVARIANT
-    if(tools.contains('deepvariant')){
+    if(tools.split(',').contains('deepvariant')){
         RUN_DEEPVARIANT(cram_recalibrated_intervals, dict, fasta, fasta_fai)
 
         deepvariant_vcf = Channel.empty().mix(RUN_DEEPVARIANT.out.deepvariant_vcf,RUN_DEEPVARIANT.out.deepvariant_gvcf)
         ch_versions     = ch_versions.mix(RUN_DEEPVARIANT.out.versions)
     }
 
     // FREEBAYES
-    if (tools.contains('freebayes')){
+    if (tools.split(',').contains('freebayes')){
         // Remap channel for Freebayes
         cram_recalibrated_intervals_freebayes = cram_recalibrated_intervals
             .map{ meta, cram, crai, intervals ->
@@ -115,7 +116,7 @@ workflow GERMLINE_VARIANT_CALLING {
     }
 
     // HAPLOTYPECALLER
-    if (tools.contains('haplotypecaller')){
+    if (tools.split(',').contains('haplotypecaller')){
         RUN_HAPLOTYPECALLER(cram_recalibrated_intervals,
                         fasta,
                         fasta_fai,
@@ -131,7 +132,7 @@ workflow GERMLINE_VARIANT_CALLING {
     }
 
     // MANTA
-    if (tools.contains('manta')){
+    if (tools.split(',').contains('manta')){
         RUN_MANTA_GERMLINE (cram_recalibrated_intervals_gz_tbi,
                         dict,
                         fasta,
@@ -142,7 +143,7 @@ workflow GERMLINE_VARIANT_CALLING {
     }
 
     // STRELKA
-    if (tools.contains('strelka')){
+    if (tools.split(',').contains('strelka')){
         RUN_STRELKA_SINGLE(cram_recalibrated_intervals_gz_tbi,
                 dict,
                 fasta,
@@ -153,7 +154,7 @@ workflow GERMLINE_VARIANT_CALLING {
     }
 
     //TIDDIT
-    if (tools.contains('tiddit')){
+    if (tools.split(',').contains('tiddit')){
         RUN_TIDDIT(cram_recalibrated,
                 fasta,
                 bwa)

diff --git a/subworkflows/local/pair_variant_calling.nf b/subworkflows/local/pair_variant_calling.nf
@@ -75,7 +75,7 @@ workflow PAIR_VARIANT_CALLING {
 
         }
 
-    if (tools.contains('ascat')){
+    if (tools.split(',').contains('ascat')){
 
         RUN_ASCAT_SOMATIC(  cram_pair,
                             allele_files,
@@ -89,7 +89,7 @@ workflow PAIR_VARIANT_CALLING {
 
     }
 
-    if (tools.contains('controlfreec')){
+    if (tools.split(',').contains('controlfreec')){
         cram_normal_intervals_no_index = cram_pair_intervals
                     .map {meta, normal_cram, normal_crai, tumor_cram, tumor_crai, intervals ->
                             [meta, normal_cram, intervals]
@@ -124,7 +124,7 @@ workflow PAIR_VARIANT_CALLING {
         ch_versions = ch_versions.mix(RUN_CONTROLFREEC_SOMATIC.out.versions)
     }
 
-    if (tools.contains('cnvkit')){
+    if (tools.split(',').contains('cnvkit')){
         cram_pair_cnvkit_somatic = cram_pair
             .map{meta, normal_cram, normal_crai, tumor_cram, tumor_crai ->
                 [meta, tumor_cram, normal_cram]
@@ -137,14 +137,14 @@ workflow PAIR_VARIANT_CALLING {
                             [])
     }
 
-    if (tools.contains('freebayes')){
+    if (tools.split(',').contains('freebayes')){
         RUN_FREEBAYES_SOMATIC(cram_pair_intervals, dict, fasta, fasta_fai)
 
         freebayes_vcf = RUN_FREEBAYES_SOMATIC.out.freebayes_vcf
         ch_versions   = ch_versions.mix(RUN_FREEBAYES_SOMATIC.out.versions)
     }
 
-    if (tools.contains('manta')) {
+    if (tools.split(',').contains('manta')) {
         RUN_MANTA_SOMATIC(  cram_pair_intervals_gz_tbi,
                             dict,
                             fasta,
@@ -156,9 +156,9 @@ workflow PAIR_VARIANT_CALLING {
         ch_versions                          = ch_versions.mix(RUN_MANTA_SOMATIC.out.versions)
     }
 
-    if (tools.contains('strelka')) {
+    if (tools.split(',').contains('strelka')) {
 
-        if (tools.contains('manta')) {
+        if (tools.split(',').contains('manta')) {
             cram_pair_strelka = cram_pair.join(manta_candidate_small_indels_vcf)
                                         .join(manta_candidate_small_indels_vcf_tbi)
                                         .combine(intervals_bed_gz_tbi)
@@ -188,15 +188,15 @@ workflow PAIR_VARIANT_CALLING {
         ch_versions = ch_versions.mix(RUN_STRELKA_SOMATIC.out.versions)
     }
 
-    if (tools.contains('msisensorpro')) {
+    if (tools.split(',').contains('msisensorpro')) {
 
         cram_pair_msisensor = cram_pair.combine(intervals_bed_combined)
         MSISENSORPRO_MSI_SOMATIC(cram_pair_msisensor, fasta, msisensorpro_scan)
         ch_versions = ch_versions.mix(MSISENSORPRO_MSI_SOMATIC.out.versions)
         msisensorpro_output = msisensorpro_output.mix(MSISENSORPRO_MSI_SOMATIC.out.output_report)
     }
 
-    if (tools.contains('mutect2')) {
+    if (tools.split(',').contains('mutect2')) {
         cram_pair_mutect2 = cram_pair_intervals.map{ meta, normal_cram, normal_crai, tumor_cram, tumor_crai, intervals ->
                                 [meta, [normal_cram, tumor_cram], [normal_crai, tumor_crai], intervals]
                             }
@@ -216,7 +216,7 @@ workflow PAIR_VARIANT_CALLING {
     }
 
     //TIDDIT
-    if (tools.contains('tiddit')){
+    if (tools.split(',').contains('tiddit')){
         cram_normal = cram_pair.map{meta, normal_cram, normal_crai, tumor_cram, tumor_crai ->
             [meta, normal_cram, normal_crai]
         }

diff --git a/subworkflows/local/tumor_variant_calling.nf b/subworkflows/local/tumor_variant_calling.nf
@@ -66,7 +66,7 @@ workflow TUMOR_ONLY_VARIANT_CALLING {
             cram, crai, bed_new, tbi_new]
         }
 
-    if (tools.contains('mpileup') || tools.contains('controlfreec')){
+    if (tools.split(',').contains('mpileup') || tools.split(',').contains('controlfreec')){
         cram_intervals_no_index = cram_recalibrated_intervals.map { meta, cram, crai, intervals ->
                                                                     [meta, cram, intervals]
                                                                     }
@@ -75,7 +75,7 @@ workflow TUMOR_ONLY_VARIANT_CALLING {
         ch_versions = ch_versions.mix(RUN_MPILEUP.out.versions)
     }
 
-    if (tools.contains('controlfreec')){
+    if (tools.split(',').contains('controlfreec')){
         controlfreec_input = RUN_MPILEUP.out.mpileup
                                 .map{ meta, pileup_tumor ->
                                     [meta, [], pileup_tumor, [], [], [], []]
@@ -93,7 +93,7 @@ workflow TUMOR_ONLY_VARIANT_CALLING {
         ch_versions = ch_versions.mix(RUN_CONTROLFREEC_TUMORONLY.out.versions)
     }
 
-    if(tools.contains('cnvkit')){
+    if(tools.split(',').contains('cnvkit')){
         cram_recalibrated_cnvkit_tumoronly = cram_recalibrated
             .map{ meta, cram, crai ->
                 [meta, cram, []]
@@ -108,7 +108,7 @@ workflow TUMOR_ONLY_VARIANT_CALLING {
         ch_versions = ch_versions.mix(RUN_CNVKIT_TUMORONLY.out.versions)
     }
 
-    if (tools.contains('freebayes')){
+    if (tools.split(',').contains('freebayes')){
         // Remap channel for Freebayes
         cram_recalibrated_intervals_freebayes = cram_recalibrated_intervals
             .map{ meta, cram, crai, intervals ->
@@ -121,7 +121,7 @@ workflow TUMOR_ONLY_VARIANT_CALLING {
         ch_versions   = ch_versions.mix(RUN_FREEBAYES.out.versions)
     }
 
-    if (tools.contains('mutect2')) {
+    if (tools.split(',').contains('mutect2')) {
         GATK_TUMOR_ONLY_SOMATIC_VARIANT_CALLING(cram_recalibrated_intervals,
                                                 fasta,
                                                 fasta_fai,
@@ -135,7 +135,7 @@ workflow TUMOR_ONLY_VARIANT_CALLING {
         ch_versions = ch_versions.mix(GATK_TUMOR_ONLY_SOMATIC_VARIANT_CALLING.out.versions)
     }
 
-    if (tools.contains('manta')){
+    if (tools.split(',').contains('manta')){
         RUN_MANTA_TUMORONLY(cram_recalibrated_intervals_gz_tbi,
                             dict,
                             fasta,
@@ -145,7 +145,7 @@ workflow TUMOR_ONLY_VARIANT_CALLING {
         ch_versions = ch_versions.mix(RUN_MANTA_TUMORONLY.out.versions)
     }
 
-    if (tools.contains('strelka')) {
+    if (tools.split(',').contains('strelka')) {
         RUN_STRELKA_SINGLE(cram_recalibrated_intervals_gz_tbi,
                             dict,
                             fasta,
@@ -156,7 +156,7 @@ workflow TUMOR_ONLY_VARIANT_CALLING {
     }
 
         //TIDDIT
-    if (tools.contains('tiddit')){
+    if (tools.split(',').contains('tiddit')){
         RUN_TIDDIT(cram_recalibrated,
                 fasta,
                 bwa)

diff --git a/tests/test_skip_qc.yml b/tests/test_skip_qc.yml
@@ -0,0 +1,81 @@
+- name: Run default pipeline with skipping all QC steps
+  command: nextflow run main.nf -profile test,docker --skip_tools 'fastqc,markduplicates_report,mosdepth,multiqc,samtools'
+  tags:
+    - skip_qc
+    - preprocessing
+  files:
+    - path: results/multiqc
+      should_exist: false
+    - path: results/preprocessing/test/markduplicates/test.md.cram
+    - path: results/preprocessing/test/markduplicates/test.md.cram.crai
+    - path: results/preprocessing/test/recal_table/test.recal.table
+    - path: results/preprocessing/test/recalibrated/test.recal.cram
+    - path: results/preprocessing/test/recalibrated/test.recal.cram.crai
+    - path: results/csv/markduplicates.csv
+    - path: results/csv/markduplicates_no_table.csv
+    - path: results/csv/recalibrated.csv
+    - path: results/reports/fastqc/test-test_L1
+      should_exist: false
+    - path: results/reports/markduplicates/test/test.md.metrics
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.md.mosdepth.global.dist.txt
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.md.mosdepth.summary.txt
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.md.mosdepth.region.dist.txt
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.md.regions.bed.gz
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.recal.regions.bed.gz
+      should_exist: false
+    - path: results/reports/samtools_stats/test/test.md.cram.stats
+      should_exist: false
+    - path: results/reports/samtools_stats/test/test.recal.cram.stats
+      should_exist: false
+
+- name: Run spark pipeline with skipping all QC steps
+  command: nextflow run main.nf -profile test,use_gatk_spark,docker --skip_tools 'fastqc,markduplicates_report,mosdepth,multiqc,samtools'
+  tags:
+    - skip_qc
+    - preprocessing
+  files:
+    - path: results/multiqc
+      should_exist: false
+    - path: results/preprocessing/test/markduplicates/test.md.cram
+    - path: results/preprocessing/test/markduplicates/test.md.cram.crai
+    - path: results/preprocessing/test/recal_table/test.recal.table
+    - path: results/preprocessing/test/recalibrated/test.recal.cram
+    - path: results/preprocessing/test/recalibrated/test.recal.cram.crai
+    - path: results/csv/markduplicates.csv
+    - path: results/csv/markduplicates_no_table.csv
+    - path: results/csv/recalibrated.csv
+    - path: results/reports/fastqc/test-test_L1
+      should_exist: false
+    - path: results/reports/markduplicates/test/test.md.metrics
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.md.mosdepth.global.dist.txt
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.md.mosdepth.summary.txt
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.md.mosdepth.region.dist.txt
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.md.regions.bed.gz
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.recal.mosdepth.global.dist.txt
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.recal.mosdepth.summary.txt
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.recal.mosdepth.region.dist.txt
+      should_exist: false
+    - path: results/reports/mosdepth/test/test.recal.regions.bed.gz
+      should_exist: false
+    - path: results/reports/samtools_stats/test/test.md.cram.stats
+      should_exist: false
+    - path: results/reports/samtools_stats/test/test.recal.cram.stats
+      should_exist: false