Merge branch 'dev' into full-tests

Author: ggabernet

.github/workflows/ci.yml

@@ -56,6 +56,7 @@ jobs:
           - "strelkabp"
           - "targeted"
           - "tiddit"
+          - "trimming"
           - "tumor_normal_pair"
           - "variantcalling_channel"
 

CHANGELOG.md

@@ -31,8 +31,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#576](https://github.com/nf-core/sarek/pull/576) - Add modules and subworkflows for `cnvkit` germline mode
 - [#582](https://github.com/nf-core/sarek/pull/582) - Added option `--vep_out_format` for setting the format of the output-file from VEP to `json`, `tab` or `vcf` (default)
 - [#594](https://github.com/nf-core/sarek/pull/594) - Add parameter `--save_output_as_bam` to allow output of result files in BAM format
-- [#600](https://github.com/nf-core/sarek/pull/600) - Added description for UMI related params in schema
 - [#597](https://github.com/nf-core/sarek/pull/597) - Added tiddit for tumor variant calling
+- [#600](https://github.com/nf-core/sarek/pull/600) - Added description for UMI related params in schema
 - [#604](https://github.com/nf-core/sarek/pull/604) - Added full size tests WGS 30x NA12878
 
 ### Changed
@@ -70,6 +70,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#581](https://github.com/nf-core/sarek/pull/581) - `TIDDIT` is updated to `3.1.0`
 - [#593](https://github.com/nf-core/sarek/pull/593) - update `ensembl-vep` cache version and module
 - [#600](https://github.com/nf-core/sarek/pull/600) - Remove `TODO` in awsfulltest
+- [#608](https://github.com/nf-core/sarek/pull/608) - Prevent candidate VCFs from getting published in manta
 
 ### Fixed
 

assets/multiqc_config.yml

@@ -18,10 +18,10 @@ export_plots: true
 run_modules:
   - custom_content
   - fastqc
-  - cutadapt
+  - fastp
   - picard
   - samtools
-  - qualimap
+  - mosdepth
   - gatk
   - bcftools
   - vcftools
@@ -33,19 +33,15 @@ module_order:
       name: "FastQC (raw)"
       path_filters_exclude:
         - "*_val_*.zip"
-  - cutadapt:
-      name: "Cutadapt"
-  - fastqc:
-      name: "FastQC (trimmed)"
-      path_filters:
-        - "*_val_*.zip"
+  - fastp:
+      name: "FastP (Read preprocessing)"
   - picard:
       name: "GATK4 MarkDuplicates"
       info: " metrics generated either by GATK4 MarkDuplicates or EstimateLibraryComplexity (with --use_gatk_spark)."
   - samtools:
       name: "Samtools Flagstat"
-  - qualimap:
-      name: "Qualimap"
+  - mosdepth:
+      name: "Mosdepth"
   - gatk:
       name: "GATK4 BQSR"
   - bcftools:

conf/modules.config

@@ -193,23 +193,29 @@ process {
     }
 
 // TRIMMING
-    withName: 'TRIMGALORE' {
-        ext.args         = '--fastqc'
-        publishDir       = [
-            [
-                path: { "${params.outdir}/reports/trimgalore/${meta.id}/fastqc" },
-                mode: params.publish_dir_mode,
-                pattern: "*{html,zip}"
-            ],
+
+    withName: FASTP {
+        ext.args = [ "",
+            params.trim_fastq              ?: "--disable_adapter_trimming",
+            params.clip_r1 > 0             ? "--trim_front1 ${params.clip_r1}" : "", // Remove bp from the 5' end of read 1.
+            params.three_prime_clip_r1 > 0 ? "--trim_tail1 ${params.three_prime_clip_r1}" : "", // Remove bp from the 3' end of read 1 AFTER adapter/quality trimming has been performed.
+            params.clip_r2   > 0           ? "--trim_front2 ${params.clip_r2}" : "", //Remove bp from the 5' end of read 2.
+            params.three_prime_clip_r2 > 0 ? "--trim_tail2 ${params.three_prime_clip_r2}" : "", // Remove bp from the 3' end of read 2 AFTER adapter/quality trimming has been performed.
+            params.trim_nextseq            ? "--trim_poly_g" : "", // Apply the --nextseq=X option, to trim based on quality after removing poly-G tails.
+            params.split_fastq > 0         ? "--split_by_lines ${params.split_fastq * 4}" : "",
+
+        ].join(" ").trim()
+        publishDir = [
             [
-                path: { "${params.outdir}/trimgalore/${meta.id}" },
+                path: { "${params.outdir}/reports/fastp/${meta.sample}" },
                 mode: params.publish_dir_mode,
-                pattern: "*fq.gz"
+                pattern: "*.{html,json,log}"
             ],
             [
-                path: { "${params.outdir}/reports/trimgalore/${meta.id}" },
+                enabled: params.save_trimmed || params.save_split_fastqs,
+                path: { "${params.outdir}/preprocessing/${meta.sample}/fastp" },
                 mode: params.publish_dir_mode,
-                pattern: "*txt"
+                pattern: "*.fastp.fastq.gz"
             ]
         ]
     }
@@ -239,19 +245,6 @@ process {
         ext.prefix       = {"${meta.id}_unsorted_tagged"}
     }
 
-// SPLIT FASTQ
-
-    withName: 'SEQKIT_SPLIT2' {
-        ext.args         = { "--by-size ${params.split_fastq}" }
-        ext.when         = { params.split_fastq > 1 }
-        publishDir       = [
-            enabled: params.save_split_fastqs,
-            mode: params.publish_dir_mode,
-            path: { "${params.outdir}/preprocessing/${meta.sample}/seqkit" },
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-        ]
-    }
-
 // MAPPING
     if (params.step == 'mapping') {
         withName: ".*GATK4_MAPPING:BWAMEM1_MEM" {
@@ -272,12 +265,12 @@ process {
             // However if it's skipped, reads need to be coordinate-sorted
             // Only name sort if Spark for Markduplicates + duplicate marking is not skipped
             ext.args2        = { params.use_gatk_spark && params.use_gatk_spark.contains('markduplicates') && (!params.skip_tools || (params.skip_tools && !params.skip_tools.contains('markduplicates'))) ? '-n' : '' }
-            ext.prefix       = { params.split_fastq > 1 ? "${meta.id}".concat('.').concat(reads.get(0).name.findAll(/part_([0-9]+)?/).last()) : "" }
+            ext.prefix       = { params.split_fastq > 1 ? "${meta.id}".concat('.').concat(reads.get(0).name.tokenize('.')[0]) : "" }
             publishDir       = [
                 mode: params.publish_dir_mode,
-                path: { "${params.outdir}/preprocessing/${meta.id}/" },
+                path: { "${params.outdir}/preprocessing/" },
                 pattern: "*bam",
-                saveAs: { (params.save_bam_mapped || (params.skip_tools && params.skip_tools.contains('markduplicates'))) && (meta.size * meta.numLanes == 1) ? "mapped/${it}" : null }
+                saveAs: { (params.save_bam_mapped || (params.skip_tools && params.skip_tools.contains('markduplicates'))) && (meta.size * meta.numLanes == 1) ? "${meta.id}/mapped/${it}" : null }
             ]
         }
 
@@ -479,28 +472,18 @@ process {
         ]
     }
 
-    withName: 'DEEPTOOLS_BAMCOVERAGE' {
-        ext.when         = { !(params.skip_tools && params.skip_tools.contains('deeptools')) }
-        publishDir       = [
-            mode: params.publish_dir_mode,
-            path: { "${params.outdir}/reports/deeptools/${meta.id}" },
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
-        ]
-    }
-
-    withName: 'QUALIMAP_BAMQCCRAM' {
-        ext.args         = '--paint-chromosome-limits --genome-gc-distr HUMAN -skip-duplicated --skip-dup-mode 0 -outformat HTML'
+    withName: 'MOSDEPTH' {
+        ext.args = { !params.wes ? "-n --fast-mode --by 500" : ""}
         ext.prefix       = { "${meta.id}.mapped" }
-        ext.when         = { !(params.skip_tools && params.skip_tools.contains('bamqc')) }
-        publishDir       = [
+        publishDir = [
             mode: params.publish_dir_mode,
-            path: { "${params.outdir}/reports/qualimap/${meta.id}" },
-            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+            path: { "${params.outdir}/reports/mosdepth/${meta.id}" },
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
     }
 
     if (params.step == 'mapping' || params.step == 'markduplicates'|| params.step == 'prepare_recalibration'|| params.step == 'recalibrate') {
-        withName: 'NFCORE_SAREK:SAREK:CRAM_QC:QUALIMAP_BAMQCCRAM' {
+        withName: 'NFCORE_SAREK:SAREK:CRAM_QC:MOSDEPTH' {
             ext.prefix       = { "${meta.id}.recal" }
         }
 
@@ -649,7 +632,7 @@ process{
         publishDir       = [
             mode: params.publish_dir_mode,
             path: { "${params.outdir}/variant_calling/${meta.id}/manta" },
-            pattern: "*{vcf.gz,vcf.gz.tbi}"
+            pattern: "*{diploid_sv,tumor_sv,somatic_sv}.{vcf.gz,vcf.gz.tbi}"
         ]
     }
     withName: 'MERGE_MANTA_DIPLOID' {
@@ -668,7 +651,7 @@ process{
         publishDir       = [
             mode: params.publish_dir_mode,
             path: { "${params.outdir}/variant_calling/${meta.id}/" },
-            pattern: "*{vcf.gz,vcf.gz.tbi}",
+            pattern: "*{diploid_sv,tumor_sv,somatic_sv}.{vcf.gz,vcf.gz.tbi}",
             saveAs: { meta.num_intervals > 1 ? null : "manta/${it}" }
         ]
     }
@@ -1093,6 +1076,24 @@ process{
         ext.prefix       = {"${meta.id}.somatic_snvs"}
     }
 
+    //TIDDIT
+    withName: 'NFCORE_SAREK:SAREK:PAIR_VARIANT_CALLING:RUN_TIDDIT_NORMAL:TABIX_BGZIP_TIDDIT_SV' {
+        ext.prefix       = {"${meta.id}.normal.vcf"}
+    }
+
+    withName: 'NFCORE_SAREK:SAREK:PAIR_VARIANT_CALLING:RUN_TIDDIT_TUMOR:TABIX_BGZIP_TIDDIT_SV' {
+        ext.prefix       = {"${meta.id}.tumor.vcf"}
+    }
+
+    //SVDB
+    withName: 'NFCORE_SAREK:SAREK:PAIR_VARIANT_CALLING:SVDB_MERGE' {
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/variant_calling/${meta.id}/tiddit" },
+            pattern: "*vcf"
+        ]
+    }
+
     // VCF QC
     withName: 'BCFTOOLS_STATS'{
         ext.when         = { !(params.skip_tools && params.skip_tools.contains('bcftools')) }
@@ -1146,6 +1147,7 @@ process{
     // VEP
     if (params.tools && (params.tools.contains('vep') || params.tools.contains('merge'))) {
         withName: 'ENSEMBLVEP' {
+            // If just VEP: <vcf prefix>_VEP.ann.vcf
             ext.prefix       = { "${vcf.baseName.minus(".vcf")}_VEP" }
             ext.args          = [
                 '--everything --filter_common --per_gene --total_length --offline --format vcf',
@@ -1171,16 +1173,10 @@ process{
         }
     }
 
-    if (params.tools && params.tools.contains('vep')) {
-        withName: 'NFCORE_SAREK:SAREK:ANNOTATE:ANNOTATION_ENSEMBLVEP:ENSEMBLVEP' {
-            ext.prefix      = {"${meta.id}_VEP"}
-        }
-    }
-
     // SNPEFF THEN VEP
     if (params.tools && params.tools.contains('merge')) {
         withName: ".*:ANNOTATION_MERGE:ENSEMBLVEP" {
-            // Output file will have format *_snpEff_VEP.ann.vcf, *_snpEff_VEP.ann.json or *_snpEff_VEP.ann.tab
+            // If megre: Output file will have format *_snpEff_VEP.ann.vcf, *_snpEff_VEP.ann.json or *_snpEff_VEP.ann.tab
             ext.prefix       = { "${vcf.baseName.minus(".ann.vcf")}_VEP" }
         }
     }