sort annotsv VCFs (#114)

* sort annotsv VCFs

* changelog

* add missing contig to header

* use fai instead of contig addition

* revert last commit

* small fix in reheader

* small fix in reheader

* small fix in reheader

Author: nvnieuwk

CHANGELOG.md

@@ -28,6 +28,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 1. Fail the pipeline when the sex determination failed. This will now prompt the user to add the sex to the samplesheet so the pipeline doesn't do any wrong assumptions
 2. Fixed the Jasmine module output VCFs being empty when no variants have been merged. This file now contains the header of one of the input VCFs
+3. AnnotSV VCF files are now sorted before trying to combine it with the VEP output.
 
 ## v0.2.0 - [19 July 2024] - Mighty Manneken Pis
 

conf/modules.config

@@ -221,10 +221,15 @@ process {
     }
 
     withName: "^.*VCF_ANNOTATE_VEP_ANNOTSV:BCFTOOLS_CONCAT\$" {
-        ext.prefix = "annotsv_annotated"
+        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:ENSEMBLVEP_VEP\$" {
         ext.prefix = {"${meta.id}.vep"}
         ext.args = {[

modules/local/bcftools/consensus_reheader/main.nf

@@ -23,7 +23,7 @@ process BCFTOOLS_CONSENSUS_REHEADER {
     def add_additional = additional_headers ?
     """
     cat <<-EOF >> ${prefix}.temp.txt
-    ${additional_headers.join("\t\n")}
+    ${additional_headers.join("\n    ")}
     EOF
     """ : ""
 

subworkflows/local/vcf_annotate_vep_annotsv/main.nf

@@ -11,6 +11,7 @@ include { TABIX_TABIX as TABIX_ANNOTSV              } from '../../../modules/nf-
 include { TABIX_TABIX as TABIX_VEP                  } from '../../../modules/nf-core/tabix/tabix/main'
 include { BCFTOOLS_FILTER                           } from '../../../modules/nf-core/bcftools/filter/main'
 include { BCFTOOLS_CONCAT                           } from '../../../modules/nf-core/bcftools/concat/main'
+include { BCFTOOLS_SORT                             } from '../../../modules/nf-core/bcftools/sort/main'
 
 workflow VCF_ANNOTATE_VEP_ANNOTSV {
     take:
@@ -79,7 +80,8 @@ workflow VCF_ANNOTATE_VEP_ANNOTSV {
         }
 
     def val_additional_headers = [
-        '##INFO=<ID=BNDrescue,Number=0,Type=Flag,Description="The other BND of this pair can be recovered"'
+        '##INFO=<ID=BNDrescue,Number=0,Type=Flag,Description="The other BND of this pair can be recovered"',
+        '##contig=<ID=M,length=16569,assembly=GRCh38>'
     ]
 
     BCFTOOLS_CONSENSUS_REHEADER(
@@ -104,13 +106,13 @@ workflow VCF_ANNOTATE_VEP_ANNOTSV {
     )
     ch_versions = ch_versions.mix(BCFTOOLS_CONCAT.out.versions.first())
 
-    TABIX_ANNOTSV(
+    BCFTOOLS_SORT(
         BCFTOOLS_CONCAT.out.vcf
     )
-    ch_versions = ch_versions.mix(TABIX_ANNOTSV.out.versions.first())
+    ch_versions = ch_versions.mix(BCFTOOLS_SORT.out.versions.first())
 
-    def ch_annotsv_output = BCFTOOLS_CONCAT.out.vcf
-        .join(TABIX_ANNOTSV.out.tbi, failOnDuplicate:true, failOnMismatch:true)
+    def ch_annotsv_output = BCFTOOLS_SORT.out.vcf
+        .join(BCFTOOLS_SORT.out.tbi, failOnDuplicate:true, failOnMismatch:true)
 
     ENSEMBLVEP_VEP(
         ch_vcfs,