Varlociraptor integration

CHANGELOG.md

@@ -20,6 +20,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [1934](https://github.com/nf-core/sarek/pull/1934) - Add sentieon TNscope for tumour/normal variant calling
 - [1938](https://github.com/nf-core/sarek/pull/1938) - Add checks for uniqueness of sample ids and lane ids
 - [1939](https://github.com/nf-core/sarek/pull/1939) - Modify config to add readgroups to fq2bam
+- [1940](https://github.com/nf-core/sarek/pull/1940) - Add varlociraptor for variant calling
 - [1953](https://github.com/nf-core/sarek/pull/1953) - Update freebayes and add QUAL filtering
 
 ### Changed
@@ -51,17 +52,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | `ensemblvep`                           | 113.0       | 113.4       |
 | `fastp`                                | 0.23.4      | 0.24.0      |
 | `fgbio`                                | 2.2.1       | 2.4.0       |
-| `freebayes`                            | 1.3.6.      | 1.3.10      |
+| `freebayes`                            | 1.3.6       | 1.3.10      |
 | `gatk4`                                | 4.5.0.0     | 4.6.1.0     |
 | `mosdepth`                             | 0.3.8       | 0.3.10      |
 | `MuSE`                                 |             | 2.1.2       |
 | `MultiQC`                              | 1.25.1      | 1.30        |
+| `rbt`                                  |             | 0.42.2      |
 | `samtools` (in `BWAMEM1_MEM`)          | 1.2         | 1.21        |
 | `samtools` (in `BWAMEM2_MEM`)          | 1.19.2      | 1.21        |
 | `samtools` (in `GATK4_MARKDUPLICATES`) | 1.19.2      | 1.21        |
 | `sentieon`                             | 202308.03   | 202503      |
 | `tabix`                                | 1.2         | 1.21        |
+| `varlociraptor`                        |             | 8.7.3       |
 | `vcflib`                               |             | 1.0.14      |
+| `yte`                                  |             | 1.9.0       |
 
 ### Parameters
 
@@ -176,8 +180,10 @@ Akkatjåkkå is another glacier.
 
 ### Parameters
 
-| Params | Status |
-| ------ | ------ |
+| Params                         | Status |
+| ------------------------------ | ------ |
+| `--varlocriator_scenario_file` | New    |
+| `--varlocriator_chunk_size`    | New    |
 
 ## [3.5.0](https://github.com/nf-core/sarek/releases/tag/3.5.0) - Áhkájiegna
 

CITATIONS.md

@@ -146,6 +146,10 @@
 
   > Eisfeldt J, Vezzi F, Olason P, et al.: TIDDIT, an efficient and comprehensive structural variant caller for massive parallel sequencing data. F1000Res. 2017 May 10;6:664. doi: 10.12688/f1000research.11168.2. eCollection 2017. PubMed PMID: 28781756; PubMed Central PMCID: PMC5521161.
 
+- [Varlociraptor](https://pubmed.ncbi.nlm.nih.gov/32345333/)
+
+  > Köster, J., Dijkstra, L.J., Marschall, T. et al. Varlociraptor: enhancing sensitivity and controlling false discovery rate in somatic indel discovery. Genome Biol 21, 98 (2020). https://doi.org/10.1186/s13059-020-01993-6
+
 - [VCFTools](https://pubmed.ncbi.nlm.nih.gov/21653522/)
 
   > Danecek P, Auton A, Abecasis G, et al.: The variant call format and VCFtools. Bioinformatics. 2011 Aug 1;27(15):2156-8. doi: 10.1093/bioinformatics/btr330. Epub 2011 Jun 7. PubMed PMID: 21653522; PubMed Central PMCID: PMC3137218.

assets/varlociraptor_somatic_with_priors.yte.yaml

@@ -0,0 +1,34 @@
+species:
+  heterozygosity: 0.001
+  germline-mutation-rate: 1e-3
+  ploidy:
+    male:
+      all: 2
+      X: 1
+      Y: 1
+    female:
+      all: 2
+      X: 2
+      Y: 0
+  genome-size: 3.5e9
+
+samples:
+  tumor:
+    sex: ?sex_string
+    somatic-effective-mutation-rate: 1e-6
+    inheritance:
+      clonal:
+        from: normal
+        somatic: true
+    contamination:
+      by: normal
+      fraction: 0.1
+  normal:
+    sex: ?sex_string
+    somatic-effective-mutation-rate: 1e-10
+
+events:
+  somatic_tumor_high: "normal:0.0 & tumor:[0.1,1.0]"
+  somatic_tumor_low: "normal:0.0 & tumor:]0.0,0.1["
+  somatic_normal: "normal:]0.0,0.5["
+  germline: "normal:0.5 | normal:1.0"

conf/modules/post_variant_calling.config

@@ -84,4 +84,143 @@ process {
                 pattern: "*.tbi"
         ]
     }
+
+    // VARLOCIRAPTOR ALL
+    withName: 'FILL_SCENARIO_FILE' {
+        ext.prefix = { "${meta.id}.scenario.varlociraptor" }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.id}/" },
+        ]
+    }
+
+    //
+    // VCF_VARLOCIRAPTOR_GERMLINE and VCF_VARLOCIRAPTOR_TUMOR_ONLY MODULES
+    //
+    withName: 'VARLOCIRAPTOR_ESTIMATEALIGNMENTPROPERTIES' {
+        ext.prefix = { "${meta.id}" }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.id}/" },
+        ]
+    }
+
+    withName: 'RBT_VCFSPLIT' {
+        ext.prefix = { "${meta.id}.${meta.variantcaller}.split" }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.id}/" },
+        ]
+    }
+
+    withName: 'VARLOCIRAPTOR_PREPROCESS' {
+        ext.prefix = { "${meta.id}.${meta.variantcaller}.preprocess.${meta.chunk}" }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.id}/" },
+        ]
+    }
+
+    withName: 'NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_GERMLINE:VARLOCIRAPTOR_CALLVARIANTS|NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_TUMOR_ONLY:VARLOCIRAPTOR_CALLVARIANTS' {
+        ext.prefix = { "${meta.id}.${meta.variantcaller}.call.${meta.chunk}" }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.id}/" },
+        ]
+    }
+
+    withName: 'NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_GERMLINE:SORT_CALLED_CHUNKS|NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_TUMOR_ONLY:SORT_CALLED_CHUNKS' {
+        ext.prefix = { "${meta.id}.${meta.variantcaller}.sort.${meta.chunk}" }
+        ext.args   = { '--output-type z --write-index=tbi' }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.id}/" },
+        ]
+    }
+
+    withName: 'NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_GERMLINE:MERGE_CALLED_CHUNKS|NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_TUMOR_ONLY:MERGE_CALLED_CHUNKS' {
+        ext.prefix = { "${meta.id}.${meta.variantcaller}.varlociraptor" }
+        ext.args   = { '--allow-overlaps --output-type z --write-index=tbi' }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/" },
+        ]
+    }
+
+    //
+    // VCF_VARLOCIRAPTOR_SOMATIC MODULES
+    //
+    withName: 'NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_SOMATIC:ALIGNMENTPROPERTIES_NORMAL' {
+        ext.prefix = { "${meta.normal_id}" }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.normal_id}/" },
+        ]
+    }
+
+    withName: 'NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_SOMATIC:VCFSPLIT_NORMAL' {
+        ext.prefix = { "${meta.normal_id}.${meta.variantcaller}.split" }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.normal_id}/" },
+        ]
+    }
+
+    withName: 'NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_SOMATIC:PREPROCESS_NORMAL' {
+        ext.prefix = { "${meta.normal_id}.${meta.variantcaller}.preprocess.${meta.chunk}" }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.normal_id}/" },
+        ]
+    }
+
+    withName: 'NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_SOMATIC:ALIGNMENTPROPERTIES_TUMOR' {
+        ext.prefix = { "${meta.tumor_id}" }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.tumor_id}/" },
+        ]
+    }
+
+    withName: 'NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_SOMATIC:VCFSPLIT_TUMOR' {
+        ext.prefix = { "${meta.tumor_id}.${meta.variantcaller}.split" }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.tumor_id}/" },
+        ]
+    }
+
+    withName: 'NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_SOMATIC:PREPROCESS_TUMOR' {
+        ext.prefix = { "${meta.tumor_id}.${meta.variantcaller}.preprocess.${meta.chunk}" }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.tumor_id}/" },
+        ]
+    }
+
+    withName: 'NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_SOMATIC:VARLOCIRAPTOR_CALLVARIANTS' {
+        ext.prefix = { "${meta.id}.${meta.variantcaller}.call.${meta.chunk}" }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.id}/" },
+        ]
+    }
+
+    withName: 'NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_SOMATIC:SORT_CALLED_CHUNKS' {
+        ext.prefix = { "${meta.id}.${meta.variantcaller}.sort.${meta.chunk}" }
+        ext.args   = { '--output-type z --write-index=tbi' }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/${meta.id}/" },
+        ]
+    }
+
+    withName: 'NFCORE_SAREK:SAREK:POST_VARIANTCALLING:VCF_VARLOCIRAPTOR_SOMATIC:MERGE_CALLED_CHUNKS' {
+        ext.prefix = { "${meta.id}.${meta.variantcaller}.varlociraptor" }
+        ext.args   = { '--allow-overlaps --output-type z --write-index=tbi' }
+        publishDir = [
+            mode: params.publish_dir_mode,
+                path: { "${params.outdir}/variant_calling/varlociraptor/" },
+        ]
+    }
 }