Merge pull request #601 from WackerO/tidditpair

Tiddit pair VC

Author: FriederikeHanssen

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
 
 ### Changed
 

conf/modules.config

@@ -1076,6 +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')) }

modules.json

@@ -219,6 +219,9 @@
             "strelka/somatic": {
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
             },
+            "svdb/merge": {
+                "git_sha": "313d76e00525c8e975dabce0c34973fd53c3f4dd"
+            },
             "tabix/bgziptabix": {
                 "git_sha": "49b18b1639f4f7104187058866a8fab33332bdfe"
             },

modules/nf-core/modules/svdb/merge/main.nf

@@ -40,7 +40,6 @@ workflow GERMLINE_VARIANT_CALLING {
     manta_vcf           = Channel.empty()
     strelka_vcf         = Channel.empty()
     tiddit_vcf          = Channel.empty()
-    mpileup             = Channel.empty()
 
     // Remap channel with intervals
     cram_recalibrated_intervals = cram_recalibrated.combine(intervals)

modules/nf-core/modules/svdb/merge/meta.yml

@@ -10,26 +10,30 @@ include { RUN_STRELKA_SOMATIC                       } from '../nf-core/variantca
 include { RUN_CNVKIT_SOMATIC                        } from '../nf-core/variantcalling/cnvkit/somatic/main.nf'
 include { RUN_MPILEUP as RUN_MPILEUP_NORMAL         } from '../nf-core/variantcalling/mpileup/main'
 include { RUN_MPILEUP as RUN_MPILEUP_TUMOR          } from '../nf-core/variantcalling/mpileup/main'
+include { RUN_TIDDIT as RUN_TIDDIT_NORMAL           } from '../nf-core/variantcalling/tiddit/main.nf'
+include { RUN_TIDDIT as RUN_TIDDIT_TUMOR            } from '../nf-core/variantcalling/tiddit/main.nf'
+include { SVDB_MERGE                                } from '../../modules/nf-core/modules/svdb/merge/main.nf'
 
 workflow PAIR_VARIANT_CALLING {
     take:
         tools                         // Mandatory, list of tools to apply
         cram_pair                     // channel: [mandatory] cram
+        bwa                           // channel: [optional] bwa
+        chr_files
         dbsnp                         // channel: [mandatory] dbsnp
         dbsnp_tbi                     // channel: [mandatory] dbsnp_tbi
         dict                          // channel: [mandatory] dict
         fasta                         // channel: [mandatory] fasta
         fasta_fai                     // channel: [mandatory] fasta_fai
+        germline_resource             // channel: [optional]  germline_resource
+        germline_resource_tbi         // channel: [optional]  germline_resource_tbi
         intervals                     // channel: [mandatory] intervals/target regions
         intervals_bed_gz_tbi          // channel: [mandatory] intervals/target regions index zipped and indexed
         intervals_bed_combined        // channel: [mandatory] intervals/target regions in one file unzipped
+        mappability
         msisensorpro_scan             // channel: [optional]  msisensorpro_scan
-        germline_resource             // channel: [optional]  germline_resource
-        germline_resource_tbi         // channel: [optional]  germline_resource_tbi
         panel_of_normals              // channel: [optional]  panel_of_normals
         panel_of_normals_tbi          // channel: [optional]  panel_of_normals_tbi
-        chr_files
-        mappability
 
     main:
 
@@ -41,6 +45,7 @@ workflow PAIR_VARIANT_CALLING {
     strelka_vcf          = Channel.empty()
     msisensorpro_output  = Channel.empty()
     mutect2_vcf          = Channel.empty()
+    tiddit_vcf           = Channel.empty()
 
     // Remap channel with intervals
     cram_pair_intervals = cram_pair.combine(intervals)
@@ -157,7 +162,7 @@ workflow PAIR_VARIANT_CALLING {
                             fasta,
                             fasta_fai)
 
-        strelka_vcf  = Channel.empty().mix(RUN_STRELKA_SOMATIC.out.strelka_vcf)
+        strelka_vcf = Channel.empty().mix(RUN_STRELKA_SOMATIC.out.strelka_vcf)
         ch_versions = ch_versions.mix(RUN_STRELKA_SOMATIC.out.versions)
     }
 
@@ -188,14 +193,35 @@ workflow PAIR_VARIANT_CALLING {
         ch_versions = ch_versions.mix(GATK_TUMOR_NORMAL_SOMATIC_VARIANT_CALLING.out.versions)
     }
 
-    // if (tools.contains('tiddit')) {
-    // }
+    //TIDDIT
+    if (tools.contains('tiddit')){
+        cram_normal = cram_pair.map{meta, normal_cram, normal_crai, tumor_cram, tumor_crai ->
+            [meta, normal_cram, normal_crai]
+        }
+        cram_tumor = cram_pair.map{meta, normal_cram, normal_crai, tumor_cram, tumor_crai ->
+            [meta, tumor_cram, tumor_crai]
+        }
+
+        RUN_TIDDIT_NORMAL(cram_normal, fasta, bwa)
+        RUN_TIDDIT_TUMOR(cram_tumor, fasta, bwa)
+        SVDB_MERGE(RUN_TIDDIT_NORMAL.out.tiddit_vcf.join(RUN_TIDDIT_TUMOR.out.tiddit_vcf)
+                                                    .map{meta, vcf_normal, vcf_tumor ->
+                                                        [meta, [vcf_normal, vcf_tumor]]
+                                                    }, false)
+        tiddit_vcf = SVDB_MERGE.out.vcf
+
+        ch_versions = ch_versions.mix(RUN_TIDDIT_NORMAL.out.versions)
+        ch_versions = ch_versions.mix(RUN_TIDDIT_TUMOR.out.versions)
+        ch_versions = ch_versions.mix(SVDB_MERGE.out.versions)
+    }
 
     emit:
     freebayes_vcf
     manta_vcf
     msisensorpro_output
     mutect2_vcf
     strelka_vcf
+    tiddit_vcf
+
     versions    = ch_versions
 }

subworkflows/local/germline_variant_calling.nf

@@ -70,6 +70,23 @@
     - path: results/variant_calling/sample1/cnvkit/test.paired_end.recalibrated.sorted.cns
     - path: results/variant_calling/sample1/cnvkit/test.paired_end.recalibrated.sorted.call.cns
 
+- name: Run variant calling on somatic sample with tiddit
+  command: nextflow run main.nf -profile test,tools_somatic,docker --tools tiddit -c ./tests/nextflow.config
+  tags:
+    - tiddit
+    - somatic
+    - variant_calling
+  files:
+    - path: results/variant_calling/sample3/tiddit/sample3.ploidies.tab
+    - path: results/variant_calling/sample3/tiddit/sample3.vcf.gz
+    - path: results/variant_calling/sample3/tiddit/sample3.vcf.gz.tbi
+    - path: results/variant_calling/sample4_vs_sample3/tiddit/sample4_vs_sample3.normal.vcf.gz
+    - path: results/variant_calling/sample4_vs_sample3/tiddit/sample4_vs_sample3.normal.vcf.gz.tbi
+    - path: results/variant_calling/sample4_vs_sample3/tiddit/sample4_vs_sample3.tumor.vcf.gz
+    - path: results/variant_calling/sample4_vs_sample3/tiddit/sample4_vs_sample3.tumor.vcf.gz.tbi
+    - path: results/variant_calling/sample4_vs_sample3/tiddit/sample4_vs_sample3_sv_merge.vcf
+    - path: results/variant_calling/sample4_vs_sample3/tiddit/sample4_vs_sample3.ploidies.tab
+
 - name: Run variant calling on germline sample with tiddit
   command: nextflow run main.nf -profile test,tools_germline,docker --tools tiddit -c ./tests/nextflow.config
   tags:

subworkflows/local/pair_variant_calling.nf

@@ -833,21 +833,22 @@ workflow SAREK {
         PAIR_VARIANT_CALLING(
             params.tools,
             cram_variant_calling_pair,
+            [],
+            chr_files,
             dbsnp,
             dbsnp_tbi,
             dict,
             fasta,
             fasta_fai,
+            germline_resource,
+            germline_resource_tbi,
             intervals,
             intervals_bed_gz_tbi,
             intervals_bed_combined,
+            mappability,
             msisensorpro_scan,
-            germline_resource,
-            germline_resource_tbi,
             pon,
-            pon_tbi,
-            chr_files,
-            mappability
+            pon_tbi
         )
 
         // Gather vcf files for annotation and QC
@@ -866,6 +867,7 @@ workflow SAREK {
         vcf_to_annotate = vcf_to_annotate.mix(PAIR_VARIANT_CALLING.out.mutect2_vcf)
         vcf_to_annotate = vcf_to_annotate.mix(PAIR_VARIANT_CALLING.out.manta_vcf)
         vcf_to_annotate = vcf_to_annotate.mix(PAIR_VARIANT_CALLING.out.strelka_vcf)
+        vcf_to_annotate = vcf_to_annotate.mix(PAIR_VARIANT_CALLING.out.tiddit_vcf)
 
         // Gather used softwares versions
         ch_versions = ch_versions.mix(GERMLINE_VARIANT_CALLING.out.versions)