Merge branch 'dev' into add_vep_112_option

nf-core · Sep 25, 2024 · e583e15 · e583e15
2 parents 5e177a2 + 39e473d
commit e583e15
Show file tree

Hide file tree

Showing 6 changed files with 31 additions and 9 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -11,6 +11,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Changed`
 
+- Report only variants above 5% heteroplasmy in the clinical vcf file for mitochondria [#616](https://github.com/nf-core/raredisease/pull/616)
+
 ### `Fixed`
 
 - Allow for VEP version 112 to be used and set it to default [#617](https://github.com/nf-core/raredisease/pull/617)

diff --git a/README.md b/README.md
@@ -56,6 +56,7 @@ On release, automated continuous integration tests run the pipeline on a full-si
 **2. Alignment:**
 
 - [Bwa-mem2](https://github.com/bwa-mem2/bwa-mem2)
+- [BWA-MEME](https://github.com/kaist-ina/BWA-MEME)
 - [BWA](https://github.com/lh3/bwa)
 - [Sentieon DNAseq](https://support.sentieon.com/manual/DNAseq_usage/dnaseq/)
 

diff --git a/conf/modules/generate_clinical_set.config b/conf/modules/generate_clinical_set.config
@@ -50,10 +50,16 @@ process {
 process {
     withName: '.*:GENERATE_CLINICAL_SET_MT:ENSEMBLVEP_FILTERVEP' {
         ext.when   = !params.skip_vep_filter
-        ext.prefix = { "${meta.id}_mt_${meta.set}" }
+        ext.prefix = { "${meta.id}_mt_filtervep_${meta.set}" }
         ext.args   = { "--filter \"HGNC_ID in ${feature_file}\"" }
     }
 
+    withName: '.*:GENERATE_CLINICAL_SET_MT:BCFTOOLS_FILTER' {
+        ext.when   = !params.skip_vep_filter
+        ext.prefix = { "${meta.id}_mt_${meta.set}" }
+        ext.args   = { "-Oz -i 'AF>0.05'" }
+    }
+
     withName: '.*:GENERATE_CLINICAL_SET_MT:TABIX_BGZIP' {
         ext.when   = !params.skip_vep_filter
         ext.prefix = { "${meta.id}_mt_${meta.set}" }

diff --git a/docs/output.md b/docs/output.md
@@ -529,7 +529,7 @@ We recommend using vcfanno to annotate SNVs with precomputed CADD scores (files
 <summary>Output files</summary>
 
 - `rank_and_filter/`
-  - `<case_id>_mt_ranked_clinical.vcf.gz`: file containing clinically relevant mitochondrial SNVs.
+  - `<case_id>_mt_ranked_clinical.vcf.gz`: file containing clinically relevant mitochondrial SNVs, and only contains variants less than 5%VAF by default.
   - `<case_id>_mt_ranked_clinical.vcf.gz.tbi`: index of the file containing clinically relevant mitochondrial SNVs.
   - `<case_id>_mt_ranked_research.vcf.gz`: file containing mitochondrial SNV annotations with their rank scores.
   - `<case_id>_mt_ranked_research.vcf.gz.tbi`: index of the file containing mitochondrial SNV annotations with their rank scores.

diff --git a/subworkflows/local/generate_clinical_set.nf b/subworkflows/local/generate_clinical_set.nf
@@ -5,11 +5,13 @@
 include { ENSEMBLVEP_FILTERVEP } from '../../modules/nf-core/ensemblvep/filtervep'
 include { TABIX_BGZIP          } from '../../modules/nf-core/tabix/bgzip'
 include { TABIX_TABIX          } from '../../modules/nf-core/tabix/tabix'
+include { BCFTOOLS_FILTER      } from '../../modules/nf-core/bcftools/filter'
 
 workflow GENERATE_CLINICAL_SET {
     take:
         ch_vcf      // channel: [mandatory] [ val(meta), path(vcf) ]
         ch_hgnc_ids // channel: [mandatory] [ val(hgnc_ids) ]
+        val_ismt    // value: if mitochondria, set to true
 
     main:
         ch_versions = Channel.empty()
@@ -28,16 +30,23 @@ workflow GENERATE_CLINICAL_SET {
         .output
         .set { ch_filtervep_out }
 
-        TABIX_BGZIP( ch_filtervep_out )
+        if (val_ismt) {
+            BCFTOOLS_FILTER (ch_filtervep_out)
+            ch_clinical = BCFTOOLS_FILTER.out.vcf
+            ch_versions = ch_versions.mix( BCFTOOLS_FILTER.out.versions )
+        } else {
+            TABIX_BGZIP( ch_filtervep_out )
+            ch_clinical = TABIX_BGZIP.out.output
+            ch_versions = ch_versions.mix( TABIX_BGZIP.out.versions )
+        }
 
         ch_clin_research_vcf.research
-            .mix( TABIX_BGZIP.out.output )
+            .mix( ch_clinical )
             .set { ch_clin_research_split }
 
         TABIX_TABIX( ch_clin_research_split )
 
         ch_versions = ch_versions.mix( ENSEMBLVEP_FILTERVEP.out.versions )
-        ch_versions = ch_versions.mix( TABIX_BGZIP.out.versions )
         ch_versions = ch_versions.mix( TABIX_TABIX.out.versions )
 
     emit:

diff --git a/workflows/raredisease.nf b/workflows/raredisease.nf
@@ -550,7 +550,8 @@ workflow RAREDISEASE {
 
             GENERATE_CLINICAL_SET_SNV(
                 ch_snv_annotate.vcf_ann,
-                ch_hgnc_ids
+                ch_hgnc_ids,
+                false
             )
             ch_versions = ch_versions.mix(GENERATE_CLINICAL_SET_SNV.out.versions)
 
@@ -602,7 +603,8 @@ workflow RAREDISEASE {
 
             GENERATE_CLINICAL_SET_MT(
                 ch_mt_annotate.vcf_ann,
-                ch_hgnc_ids
+                ch_hgnc_ids,
+                true
             )
             ch_versions = ch_versions.mix(GENERATE_CLINICAL_SET_MT.out.versions)
 
@@ -677,7 +679,8 @@ workflow RAREDISEASE {
 
             GENERATE_CLINICAL_SET_SV(
                 ch_sv_annotate.vcf_ann,
-                ch_hgnc_ids
+                ch_hgnc_ids,
+                false
             )
             ch_versions = ch_versions.mix(GENERATE_CLINICAL_SET_SV.out.versions)
 
@@ -738,7 +741,8 @@ workflow RAREDISEASE {
 
             GENERATE_CLINICAL_SET_ME(
                 ANNOTATE_MOBILE_ELEMENTS.out.vcf,
-                ch_hgnc_ids
+                ch_hgnc_ids,
+                false
             )
             ch_versions = ch_versions.mix( GENERATE_CLINICAL_SET_ME.out.versions )