Merge branch 'dev' of https://github.com/nf-core/sarek into mpileup2

nf-core · Jun 17, 2022 · 2f909ce · 2f909ce
2 parents 303854d + 7ba61bd
commit 2f909ce
Show file tree

Hide file tree

Showing 27 changed files with 679 additions and 218 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -33,27 +33,28 @@ jobs:
         test:
           - "aligner"
           - "annotation"
-          - "default"
           - "cnvkit"
           - "controlfreec"
           - "deepvariant"
+          - "default"
           - "freebayes"
           - "gatk4_spark"
           - "haplotypecaller"
           - "manta"
           - "markduplicates"
-          - "mutect2"
           - "msisensorpro"
-          # - 'save_bam_mapped'
+          - "mutect2"
           - "prepare_recalibration"
           - "recalibrate"
-          - "variantcalling_channel"
+          # - 'save_bam_mapped'
           - "skip_markduplicates"
+          - "split_fastq"
           - "strelka"
           - "strelkabp"
-          - "split_fastq"
           - "targeted"
+          - "tiddit"
           - "tumor_normal_pair"
+          - "variantcalling_channel"
 
     steps:
       - name: Check out pipeline code

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -27,7 +27,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#538](https://github.com/nf-core/sarek/pull/538) - Add param `--seq_platform`, default: `ILLUMINA`
 - [#545](https://github.com/nf-core/sarek/pull/545) - Add modules and subworkflows for `cnvkit` tumor_only mode
 - [#540](https://github.com/nf-core/sarek/pull/540) - Add modules and subworkflows for `cnvkit` somatic mode
+- [#557](https://github.com/nf-core/sarek/pull/557) - Add `Haplotypecaller` single sample mode together with `CNNScoreVariants` and `FilterVariantTranches`
 - [#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)
 
 ### Changed
 
@@ -59,6 +61,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#572](https://github.com/nf-core/sarek/pull/572) - Adjusted subway map svg for firefox compatibility
 - [#578](https://github.com/nf-core/sarek/pull/578) - Updated module deeptools/bamcoverage
 - [#585](https://github.com/nf-core/sarek/pull/585) - Remove explicit BAM to CRAM conversion after MarkduplicatesSpark; tool does it internally
+- [#581](https://github.com/nf-core/sarek/pull/581) - `TIDDIT` is updated to `3.1.0`
 
 ### Fixed
 
@@ -86,6 +89,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#567](https://github.com/nf-core/sarek/pull/567) - Fix interval name resolving during scatter/gather by moving logic to modules.config causing name to be correctly resolved on process execution; also fixed duplicate naming when variant callers produce multiple vcf files by adding field `type` to `meta` map
 - [#585](https://github.com/nf-core/sarek/pull/585) - Fix Spark usage for GATK4 modules
 - [#587](https://github.com/nf-core/sarek/pull/587) - Fix issue with VEP extra files
+- [#581](https://github.com/nf-core/sarek/pull/581) - `TIDDIT` is back
 - [#590](https://github.com/nf-core/sarek/pull/590) - Fix empty folders during scatter/gather
 
 ### Deprecated

diff --git a/conf/modules.config b/conf/modules.config
@@ -111,7 +111,7 @@ process {
     }
 
     withName: 'TABIX_KNOWN_INDELS' {
-        ext.when         = { !params.known_indels_tbi && params.known_indels && (params.step == 'mapping' || params.step == "markduplicates" || params.step == 'prepare_recalibration') }
+        ext.when         = { !params.known_indels_tbi && params.known_indels && (params.step == 'mapping' || params.step == "markduplicates" || params.step == 'prepare_recalibration' || (params.tools && params.tools.contains('haplotypecaller')) ) }
         publishDir       = [
             enabled: params.save_reference,
             mode: params.publish_dir_mode,
@@ -549,18 +549,20 @@ process{
     }
 
     // HAPLOTYPECALLER
-    withName: 'MERGE_HAPLOTYPECALLER' {
-        ext.prefix       = {"${meta.id}.g"}
+    withName: 'MERGE_HAPLOTYPECALLER.*' {
+        ext.prefix       = { params.joint_germline ? "${meta.id}.g" : "${meta.id}" }
         publishDir       = [
-            enabled: !params.no_intervals,
             mode: params.publish_dir_mode,
             path: { "${params.outdir}/variant_calling/${meta.id}/haplotypecaller" },
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
+    withName: 'MERGE_HAPLOTYPECALLER_FILTERED' {
+        ext.prefix       = { "${meta.id}.filtered" }
+    }
     withName: 'HAPLOTYPECALLER' {
         ext.args         = { params.joint_germline ? "-ERC GVCF" : "" }
-        ext.prefix       = { meta.num_intervals <= 1 ? "${meta.id}.g" : "${meta.id}_${intervals.simpleName}.g" }
+        ext.prefix       = { meta.num_intervals <= 1 ? ( params.joint_germline ? "${meta.id}.g" : "${meta.id}" ) : ( params.joint_germline ? "${meta.id}_${intervals.simpleName}.g" :"${meta.id}_${intervals.simpleName}" ) }
         ext.when         = { params.tools && params.tools.contains('haplotypecaller') }
         publishDir       = [
             mode: params.publish_dir_mode,
@@ -569,10 +571,26 @@ process{
             saveAs: { meta.num_intervals > 1 ? null : "haplotypecaller/${it}" }
         ]
     }
+    withName: 'CNNSCOREVARIANTS' {
+        ext.prefix       = { meta.num_intervals <= 1 ?  "${meta.id}" : "${meta.id}_${intervals.simpleName}" }
+        publishDir       = [
+            enabled: false
+        ]
+    }
+    withName: 'FILTERVARIANTTRANCHES' {
+        ext.args         = { "--info-key CNN_1D" }
+        ext.prefix       = { meta.num_intervals <= 1 ? "${meta.id}" : "${meta.id}_${intervals.simpleName}" }
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/variant_calling/${meta.id}/"},
+            pattern: "*{vcf.gz,vcf.gz.tbi}",
+            saveAs: { meta.num_intervals > 1 ? null : "haplotypecaller/${it}" }
+        ]
+    }
+
     withName: 'GENOTYPEGVCFS' {
         ext.when         = { params.tools && params.tools.contains('haplotypecaller') && params.joint_germline}
         publishDir       = [
-            enabled: params.generate_gvcf,
             mode: params.publish_dir_mode,
             path: { "${params.outdir}/variant_calling/${meta.id}/haplotypecaller"},
             pattern: "*{vcf.gz,vcf.gz.tbi}"
@@ -634,12 +652,24 @@ process{
         ]
     }
 
-    // withName: 'TIDDIT_SV' {
-    //     publishDir       = [
-    //         mode: params.publish_dir_mode,
-    //         path: { "${params.outdir}/variant_calling/${meta.id}/tiddit" }
-    //     ]
-    // }
+    //TIDDIT
+    withName: 'TIDDIT_SV' {
+        ext.when         = { params.tools && params.tools.contains('tiddit') }
+        ext.args         = { bwa_index ? "" : "--skip_assembly" }
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/variant_calling/${meta.id}/tiddit" },
+            pattern: "*tab",
+        ]
+    }
+    withName : 'TABIX_BGZIP_TIDDIT_SV' {
+        ext.prefix       = { "${meta.id}.vcf" }
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/variant_calling/${meta.id}/tiddit" },
+            pattern: "*{vcf.gz,vcf.gz.tbi}"
+        ]
+    }
 
 // TUMOR_VARIANT_CALLING
 
@@ -1042,18 +1072,30 @@ process{
             (params.vep_dbnsfp && params.dbnsfp)                                  ? '--plugin dbNSFP,dbNSFP.gz,rs_dbSNP,HGVSc_VEP,HGVSp_VEP,1000Gp3_EAS_AF,1000Gp3_AMR_AF,LRT_score,GERP++_RS,gnomAD_exomes_AF' : '',
             (params.vep_loftee)                                                   ? '--plugin LoF,loftee_path:/opt/conda/envs/nf-core-vep-104.3/share/ensembl-vep-104.3-0'                                      : '',
             (params.vep_spliceai && params.spliceai_snv && params.spliceai_indel) ? '--plugin SpliceAI,snv=spliceai_scores.raw.snv.hg38.vcf.gz,indel=spliceai_scores.raw.indel.hg38.vcf.gz'                     : '',
-            (params.vep_spliceregion)                                             ? '--plugin SpliceRegion'                                                                                                     : ''
+            (params.vep_spliceregion)                                             ? '--plugin SpliceRegion'                                                                                                     : '',
+            (params.vep_out_format)                                               ? "--${params.vep_out_format}"                                                                                                : '--vcf'
         ].join(' ').trim()
         if (!params.vep_cache)    container = { params.vep_genome ? "nfcore/vep:104.3.${params.vep_genome}" : "nfcore/vep:104.3.${params.genome}" }
         publishDir       = [
-            mode: params.publish_dir_mode,
-            path: { "${params.outdir}/reports/EnsemblVEP/${meta.id}/${meta.variantcaller}" },
-            pattern: "*html"
+            [
+                mode: params.publish_dir_mode,
+                path: { "${params.outdir}/reports/EnsemblVEP/${meta.id}/${meta.variantcaller}" },
+                pattern: "*html"
+            ],
+            [
+                mode: params.publish_dir_mode,
+                path: { "${params.outdir}/annotation/${meta.id}/${meta.variantcaller}" },
+                pattern: "*{json,tab}"
+            ]
         ]
     }
 
+    withName: 'NFCORE_SAREK:SAREK:ANNOTATE:ANNOTATION_ENSEMBLVEP:ENSEMBLVEP' {
+        ext.prefix      = {"${meta.id}_VEP"}
+    }
+
     withName: ".*:ANNOTATION_MERGE:ENSEMBLVEP" {
-        // Output file will have format *_snpEff_VEP.ann.vcf
+        // Output file will have format *_snpEff_VEP.ann.vcf, *_snpEff_VEP.ann.json or *_snpEff_VEP.ann.tab
         ext.prefix       = { "${vcf.baseName.minus(".ann.vcf")}_VEP" }
     }
 

diff --git a/conf/test.config b/conf/test.config
@@ -115,10 +115,10 @@ profiles {
     tools_germline {
         params.input               = "${baseDir}/tests/csv/3.0/recalibrated_germline.csv"
         params.dbsnp               = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
+        params.known_indels        = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
         params.fasta               = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
         params.intervals           = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
         params.step                = 'variant_calling'
-        params.joint_germline      = true
         params.wes                 = true
 
         params.nucleotides_per_second = 20

diff --git a/modules.json b/modules.json
@@ -67,7 +67,7 @@
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
             },
             "ensemblvep": {
-                "git_sha": "40dd662fd26c3eb3160b7c8cbbe9bff80bbe2c30"
+                "git_sha": "30f72e24822576c6f90a0bf9db678b403c70eccf"
             },
             "fastqc": {
                 "git_sha": "49b18b1639f4f7104187058866a8fab33332bdfe"
@@ -102,6 +102,9 @@
             "gatk4/calculatecontamination": {
                 "git_sha": "169b2b96c1167f89ab07127b7057c1d90a6996c7"
             },
+            "gatk4/cnnscorevariants": {
+                "git_sha": "5d72500d601432f5396e9022c3a709854197db1a"
+            },
             "gatk4/createsequencedictionary": {
                 "git_sha": "169b2b96c1167f89ab07127b7057c1d90a6996c7"
             },
@@ -111,6 +114,9 @@
             "gatk4/filtermutectcalls": {
                 "git_sha": "169b2b96c1167f89ab07127b7057c1d90a6996c7"
             },
+            "gatk4/filtervarianttranches": {
+                "git_sha": "175ea9b7f95a0e2fd3679f7a052c6dcb60b61a6e"
+            },
             "gatk4/gatherbqsrreports": {
                 "git_sha": "169b2b96c1167f89ab07127b7057c1d90a6996c7"
             },
@@ -226,7 +232,7 @@
                 "git_sha": "b3e9b88e80880f450ad79a95b2b7aa05e1de5484"
             },
             "tiddit/sv": {
-                "git_sha": "57cb730e78634673fb254a77606e014ce942734c"
+                "git_sha": "b689b8ed88a9f89eb2f7c75d3eb0bace77ade109"
             },
             "trimgalore": {
                 "git_sha": "85ec13ff1fc2196c5a507ea497de468101baabed"

diff --git a/modules/nf-core/modules/ensemblvep/Dockerfile b/modules/nf-core/modules/ensemblvep/Dockerfile
diff --git a/modules/nf-core/modules/ensemblvep/build.sh b/modules/nf-core/modules/ensemblvep/build.sh
diff --git a/modules/nf-core/modules/ensemblvep/environment.yml b/modules/nf-core/modules/ensemblvep/environment.yml
diff --git a/modules/nf-core/modules/ensemblvep/main.nf b/modules/nf-core/modules/ensemblvep/main.nf
diff --git a/modules/nf-core/modules/ensemblvep/meta.yml b/modules/nf-core/modules/ensemblvep/meta.yml