nf-core · peterpru · Jul 2, 2025 · Jul 4, 2025 · Aug 28, 2025
diff --git a/.nf-core.yml b/.nf-core.yml
@@ -18,4 +18,4 @@ template:
   name: raredisease
   org: nf-core
   outdir: .
-  version: 2.5.0
+  version: 2.5.1
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,12 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v2.5.1 - Fulliautomatix (patch) [2025-07-04]
+
+### `Changed`
+
+- Split multiallelics and remove duplicates after merging mitochondrial variants from multiple samples. [#697](https://github.com/nf-core/raredisease/pull/697)
+
 ## v2.5.0 - Fulliautomatix [2025-05-22]
 
 ### `Added`

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
@@ -2,9 +2,10 @@ custom_logo: "nf-core-raredisease_logo_light.png"
 custom_logo_url: https://github.com/nf-core/raredisease/
 custom_logo_title: "nf-core/raredisease"
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/raredisease/releases/tag/2.5.0" target="_blank">nf-core/raredisease</a>
-  analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/raredisease/2.5.0/docs/output" target="_blank">documentation</a>.
+  This report has been generated by the <a href="https://github.com/nf-core/raredisease/releases/tag/2.5.1"
+  target="_blank">nf-core/raredisease</a> analysis pipeline. For information about
+  how to interpret these results, please see the <a href="https://nf-co.re/raredisease/2.5.1/docs/output"
+  target="_blank">documentation</a>.
 
 report_section_order:
   "nf-core-raredisease-methods-description":

diff --git a/conf/modules/postprocess_MT_calls.config b/conf/modules/postprocess_MT_calls.config
@@ -44,6 +44,16 @@ process {
         ext.args2   = '-s 1 -b 2 -e 3'
     }
 
+    withName: '.*POSTPROCESS_MT_CALLS:SPLIT_MULTIALLELICS_MT2' {
+        ext.args = '--output-type z --multiallelics -both'
+        ext.prefix = { "${meta.id}_merged_split" }
+    }
+
+    withName: '.*POSTPROCESS_MT_CALLS:REMOVE_DUPLICATES_MT2' {
+        ext.args = '--output-type z --rm-dup none'
+        ext.prefix = { "${meta.id}_merged_split_rmdup" }
+    }
+
     withName: '.*POSTPROCESS_MT_CALLS:BCFTOOLS_ANNOTATE' {
         ext.args = "-c CHROM,FROM,TO,FOUND_IN --output-type z --include FILTER='\"PASS\"'"
         ext.prefix = { "${meta.id}_mitochondria" }

diff --git a/nextflow.config b/nextflow.config
@@ -440,7 +440,7 @@ manifest {
     mainScript      = 'main.nf'
     defaultBranch   = 'master'
     nextflowVersion = '!>=24.04.2'
-    version         = '2.5.0'
+    version         = '2.5.1'
     doi             = '10.5281/zenodo.7995798'
     doi             = ''
 }

diff --git a/ro-crate-metadata.json b/ro-crate-metadata.json
diff --git a/subworkflows/local/annotate_mt_snvs.nf b/subworkflows/local/annotate_mt_snvs.nf
@@ -26,7 +26,6 @@ workflow ANNOTATE_MT_SNVS {
         val_vep_genome         // string:  [mandatory] GRCh37 or GRCh38
         val_vep_cache_version  // string:  [mandatory] 107
         ch_vep_cache           // channel: [mandatory] [ path(cache) ]
-        ch_vep_cache           // channel: [mandatory] [ path(cache) ]
         ch_vep_extra_files     // channel: [mandatory] [ path(files) ]
 
     main:

diff --git a/subworkflows/local/generate_clinical_set.nf b/subworkflows/local/generate_clinical_set.nf
@@ -1,5 +1,5 @@
 //
-// Generarte clinical set of variants
+// Generate clinical set of variants
 //
 
 include { ENSEMBLVEP_FILTERVEP } from '../../modules/nf-core/ensemblvep/filtervep'
@@ -23,20 +23,24 @@ workflow GENERATE_CLINICAL_SET {
             }
             .set { ch_clin_research_vcf }
 
-        ENSEMBLVEP_FILTERVEP(
-            ch_clin_research_vcf.clinical,
-            ch_hgnc_ids
-        )
-        .output
-        .set { ch_filtervep_out }
+        ch_clinical = Channel.empty()
 
         if (val_ismt) {
-            BCFTOOLS_FILTER (ch_filtervep_out.map { meta, vcf -> return [meta, vcf, []]})
+            BCFTOOLS_FILTER (ch_clin_research_vcf.clinical.map { meta, vcf -> return [meta, vcf, []]})
             ch_clinical = BCFTOOLS_FILTER.out.vcf
             ch_versions = ch_versions.mix( BCFTOOLS_FILTER.out.versions )
         } else {
+            ENSEMBLVEP_FILTERVEP(
+                ch_clin_research_vcf.clinical, 
+                ch_hgnc_ids
+            )
+            .output
+            .set { ch_filtervep_out }
+
             TABIX_BGZIP( ch_filtervep_out )
             ch_clinical = TABIX_BGZIP.out.output
+
+            ch_versions = ch_versions.mix( ENSEMBLVEP_FILTERVEP.out.versions )
             ch_versions = ch_versions.mix( TABIX_BGZIP.out.versions )
         }
 
@@ -46,7 +50,6 @@ workflow GENERATE_CLINICAL_SET {
 
         TABIX_TABIX( ch_clin_research_split )
 
-        ch_versions = ch_versions.mix( ENSEMBLVEP_FILTERVEP.out.versions )
         ch_versions = ch_versions.mix( TABIX_TABIX.out.versions )
 
     emit:

diff --git a/subworkflows/local/postprocess_MT_calls/main.nf b/subworkflows/local/postprocess_MT_calls/main.nf
@@ -8,6 +8,10 @@ include { BCFTOOLS_NORM as SPLIT_MULTIALLELICS_MT               } from '../../..
 include { TABIX_TABIX as TABIX_TABIX_MT                         } from '../../../modules/nf-core/tabix/tabix/main'
 include { BCFTOOLS_NORM as REMOVE_DUPLICATES_MT                 } from '../../../modules/nf-core/bcftools/norm/main'
 include { TABIX_TABIX as TABIX_TABIX_MT2                        } from '../../../modules/nf-core/tabix/tabix/main'
+include { BCFTOOLS_NORM as SPLIT_MULTIALLELICS_MT2              } from '../../../modules/nf-core/bcftools/norm/main'
+include { TABIX_TABIX as TABIX_TABIX_MT3                        } from '../../../modules/nf-core/tabix/tabix/main'
+include { BCFTOOLS_NORM as REMOVE_DUPLICATES_MT2                } from '../../../modules/nf-core/bcftools/norm/main'
+include { TABIX_TABIX as TABIX_TABIX_MT4                        } from '../../../modules/nf-core/tabix/tabix/main'
 include { BCFTOOLS_MERGE as BCFTOOLS_MERGE_MT                   } from '../../../modules/nf-core/bcftools/merge/main'
 include { TABIX_TABIX as TABIX_TABIX_MERGE                      } from '../../../modules/nf-core/tabix/tabix/main'
 include { PICARD_LIFTOVERVCF                                    } from '../../../modules/nf-core/picard/liftovervcf/main'
@@ -25,7 +29,7 @@ workflow POSTPROCESS_MT_CALLS {
         ch_mtshift_backchain   // channel: [mandatory] [ val(meta), path(backchain) ]
         ch_case_info           // channel: [mandatory] [ val(case_info) ]
         ch_foundin_header      // channel: [mandatory] [ path(header) ]
-        ch_genome_chrsizes // channel: [mandatory] [ path(chrsizes) ]
+        ch_genome_chrsizes     // channel: [mandatory] [ path(chrsizes) ]
 
     main:
         ch_versions = Channel.empty()
@@ -103,6 +107,20 @@ workflow POSTPROCESS_MT_CALLS {
 
         TABIX_TABIX_MERGE(ch_addfoundintag_in)
 
+        ch_addfoundintag_in
+            .join(TABIX_TABIX_MERGE.out.tbi, failOnMismatch:true, failOnDuplicate:true)
+            .set { ch_in_split2 }
+
+        SPLIT_MULTIALLELICS_MT2 (ch_in_split2, ch_genome_fasta)
+        TABIX_TABIX_MT3(SPLIT_MULTIALLELICS_MT2.out.vcf)
+
+        // Removing duplicates and merging if there is more than one sample
+        SPLIT_MULTIALLELICS_MT2.out.vcf
+            .join(TABIX_TABIX_MT3.out.tbi, failOnMismatch:true, failOnDuplicate:true)
+            .set { ch_in_remdup2 }
+        REMOVE_DUPLICATES_MT2(ch_in_remdup2, ch_genome_fasta)
+        TABIX_TABIX_MT4(REMOVE_DUPLICATES_MT2.out.vcf)
+
         ch_genome_chrsizes.flatten().map{chromsizes ->
             return [[id:'mutect2'], chromsizes]
             }
@@ -112,8 +130,8 @@ workflow POSTPROCESS_MT_CALLS {
             .map{meta,bed,tbi -> return [bed, tbi]}
             .set{ch_varcallerbed}
 
-        ch_addfoundintag_in
-            .join(TABIX_TABIX_MERGE.out.tbi)
+        REMOVE_DUPLICATES_MT2.out.vcf
+            .join(TABIX_TABIX_MT4.out.tbi)
             .combine(ch_varcallerbed)
             .set { ch_annotate_in }