Add StrVCTVRE scoring (#120)

* rework annotation structure

* bump changelog

* add StrVCTVRE

* pre-commit

* add tests

* run new test

* remove failing ci test

* first linting fixes

* fix nf-core lint

* fix vcfanno usage when no valid toml is present

* bump nf-core version

* fix vcf_annotate tests

Author: nvnieuwk

.github/workflows/ci.yml

@@ -48,7 +48,8 @@ jobs:
           - "bam_variant_calling_qdnaseq"
           - "bam_variant_calling_smoove"
           - "bam_variant_calling_wisecondorx"
-          - "vcf_annotate_vep_annotsv"
+          # - "vcf_annotate_vep_annotsv"
+          - "vcf_annotate"
           - "vcf_annotate_vcfanno"
           - "vcf_concat_bcftools"
           - "vcf_merge_callers_jasmine"

.github/workflows/linting_comment.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download lint results
-        uses: dawidd6/action-download-artifact@20319c5641d495c8a52e688b7dc5fada6c3a9fbc # v8
+        uses: dawidd6/action-download-artifact@ac66b43f0e6a346234dd65d4d0c8fbb31cb316e5 # v11
         with:
           workflow: linting.yml
           workflow_conclusion: completed
@@ -21,7 +21,7 @@ jobs:
         run: echo "pr_number=$(cat linting-logs/PR_number.txt)" >> $GITHUB_OUTPUT
 
       - name: Post PR comment
-        uses: marocchino/sticky-pull-request-comment@331f8f5b4215f0445d3c07b4967662a32a2d3e31 # v2
+        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728 # v2
         with:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           number: ${{ steps.pr_number.outputs.pr_number }}

.github/workflows/template_version_comment.yml

@@ -10,6 +10,10 @@ lint:
     - assets/nf-core-structural_logo_light.png
     - docs/images/nf-core-structural_logo_light.png
     - docs/images/nf-core-structural_logo_dark.png
+    - .github/workflows/nf-test.yml
+    - .github/actions/get-shards/action.yml
+    - .github/actions/nf-test/action.yml
+    - tests/default.nf.test
   files_unchanged:
     - LICENSE
     - .github/PULL_REQUEST_TEMPLATE.md
@@ -24,7 +28,7 @@ lint:
     - manifest.name
     - manifest.homePage
   multiqc_config: false
-nf_core_version: 3.2.0
+nf_core_version: 3.3.2
 repository_type: pipeline
 template:
   author: nvnieuwk

.nf-core.yml

@@ -1 +1,6 @@
 printWidth: 120
+tabWidth: 4
+overrides:
+  - files: "*.{md,yml,yaml,html,css,scss,js,cff}"
+    options:
+      tabWidth: 2

.prettierrc.yml

@@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 2. Added the `--bedpe` parameter. This makes the pipeline output BEDPE files alongside the VCF files.
 3. Added parallelization on SV type to the delly flow
 4. Added a `--gtf` parameter for annotation of gene and transcript overlap using `gatk SVAnnotate`.
+5. Added `StrVCTVRE` as a new annotation tool
 
 ### `Changes`
 
@@ -26,6 +27,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 10. Removed the `--delly_sv_types` parameter.
 11. Moved all `wisecondorx` and `qdnaseq` outputs to a separate directory in each sample output.
 12. Bumped all annotation modules to the latest versions
+13. Reworked the annotation structure to a per tool structure. Specify the annotations tools you want to run with `--annotate_tools`. This parameter takes a comma-separated list of tool names (options: `vep`, `vcfanno`, `svannotate`, `strvctvre` or `all` (=> all tools))
 
 ### `Fixed`
 

CHANGELOG.md

@@ -206,31 +206,31 @@ process {
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     */
 
-    withName: "^.*VCF_ANNOTATE_VEP_ANNOTSV:BCFTOOLS_FILTER\$" {
-        ext.prefix = {"${meta.id}.filter"}
-        ext.args = "-e 'GT=\"ref\"' --output-type z"
-    }
+    // withName: "^.*VCF_ANNOTATE_VEP_ANNOTSV:BCFTOOLS_FILTER\$" {
+    //     ext.prefix = {"${meta.id}.filter"}
+    //     ext.args = "-e 'GT=\"ref\"' --output-type z"
+    // }
 
-    withName: "^.*VCF_ANNOTATE_VEP_ANNOTSV:ANNOTSV_ANNOTSV\$" {
-        ext.args = {[
-            "-SVminSize 20",
-            "-vcf 1",
-            meta.hpo ? "-hpo ${meta.hpo}" : ""
-        ].join(" ")}
-        ext.prefix = {"${meta.id}.annot"}
-    }
+    // withName: "^.*VCF_ANNOTATE_VEP_ANNOTSV:ANNOTSV_ANNOTSV\$" {
+    //     ext.args = {[
+    //         "-SVminSize 20",
+    //         "-vcf 1",
+    //         meta.hpo ? "-hpo ${meta.hpo}" : ""
+    //     ].join(" ")}
+    //     ext.prefix = {"${meta.id}.annot"}
+    // }
 
-    withName: "^.*VCF_ANNOTATE_VEP_ANNOTSV:BCFTOOLS_CONCAT\$" {
-        ext.prefix = "annotsv_annotated_unsorted"
-        ext.args = "--output-type z --naive-force"
-    }
+    // withName: "^.*VCF_ANNOTATE_VEP_ANNOTSV:BCFTOOLS_CONCAT\$" {
+    //     ext.prefix = "annotsv_annotated_unsorted"
+    //     ext.args = "--output-type z --naive-force"
+    // }
 
-    withName: "^.*VCF_ANNOTATE_VEP_ANNOTSV:BCFTOOLS_SORT\$" {
-        ext.prefix = "annotsv_annotated"
-        ext.args = "--output-type z --write-index=tbi"
-    }
+    // withName: "^.*VCF_ANNOTATE_VEP_ANNOTSV:BCFTOOLS_SORT\$" {
+    //     ext.prefix = "annotsv_annotated"
+    //     ext.args = "--output-type z --write-index=tbi"
+    // }
 
-    withName: "^.*VCF_ANNOTATE_VEP_ANNOTSV:ENSEMBLVEP_VEP\$" {
+    withName: "^.*VCF_ANNOTATE:ENSEMBLVEP_VEP\$" {
         ext.prefix = {"${meta.id}.vep"}
         ext.args = {[
             // specify we use VCF files
@@ -259,10 +259,14 @@ process {
         ext.args = "-ends"
     }
 
-    withName: "^.*GATK4_SVANNOTATE\$" {
+    withName: "^.*VCF_ANNOTATE:GATK4_SVANNOTATE\$" {
         ext.prefix = {"${meta.id}.${meta.variant_type}.svannotate"}
     }
 
+    withName: "^.*VCF_ANNOTATE:TABIX_BGZIPTABIX\$" {
+        ext.prefix = {"${meta.id}.${meta.variant_type}.strvctvre"}
+    }
+
     /*
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
         SV AND CNV FILTERING

assets/vcfanno/annotsv.toml assets/vcfanno_unused/annotsv.tomlassets/vcfanno/annotsv.toml renamed to assets/vcfanno_unused/annotsv.toml

@@ -43,7 +43,7 @@ params {
     genomes_ignore = true
     genome = 'GRCh38'
     vep_cache = null
-    annotsv_annotations = null
+    // annotsv_annotations = null
 
     concat_output = true
 

conf/modules.config

@@ -32,11 +32,13 @@ params.dict                     = getGenomeAttribute('dict')
 params.gtf                      = getGenomeAttribute('gtf')
 params.vep_cache                = getGenomeAttribute('vep_cache')
 // params.bwa                      = getGenomeAttribute('bwa')
-params.annotsv_annotations      = getGenomeAttribute('annotsv_annotations')
+// params.annotsv_annotations      = getGenomeAttribute('annotsv_annotations')
 params.expansionhunter_catalog  = getGenomeAttribute('expansionhunter_catalog')
 params.qdnaseq_male             = getGenomeAttribute("qdnaseq_male_${params.qdnaseq_bin_size.toInteger() / 1000}kbp".toString())
 params.qdnaseq_female           = getGenomeAttribute("qdnaseq_female_${params.qdnaseq_bin_size.toInteger() / 1000}kbp".toString())
 params.wisecondorx_reference    = getGenomeAttribute('wisecondorx_reference')
+params.strvctvre_phylop         = getGenomeAttribute('strvctvre_phylop')
+params.strvctvre_data           = getGenomeAttribute('strvctvre_data')
 
 
 /*
@@ -90,9 +92,9 @@ workflow {
         params.qdnaseq_male,
         params.wisecondorx_reference,
         params.vep_cache,
-        params.annotsv_annotations,
-        params.annotsv_candidate_genes,
-        params.annotsv_gene_transcripts,
+        // params.annotsv_annotations,
+        // params.annotsv_candidate_genes,
+        // params.annotsv_gene_transcripts,
         params.vcfanno_lua,
         params.vcfanno_resources,
         params.vcfanno_toml,
@@ -101,6 +103,8 @@ workflow {
         "${projectDir}/assets/svync",
         "${projectDir}/assets/bedgovcf",
         "${projectDir}/assets/vcfanno",
+        params.strvctvre_phylop,
+        params.strvctvre_data,
 
         // booleans
         params.annotate,
@@ -116,7 +120,8 @@ workflow {
         params.vep_assembly,
         params.vep_cache_version,
         params.filter,
-        params.outdir
+        params.outdir,
+        params.annotate_tools ? params.annotate_tools.tokenize(",") : []
     )
     //
     // SUBWORKFLOW: Run completion tasks