Nfdata updates

conf/modules/rank_variants.config

@@ -95,10 +95,7 @@ process {
     }
 
     withName: '.*RANK_VARIANTS_SNV:BCFTOOLS_SORT' {
-        ext.when = false
-    }
-
-    withName: '.*RANK_VARIANTS_SNV:TABIX_BGZIP' {
+        ext.args = "--output-type z"
         ext.prefix = { "${meta.id}_snv_ranked_${meta.set}" }
         publishDir = [
             path: { "${params.outdir}/rank_and_filter" },
@@ -107,6 +104,10 @@ process {
         ]
     }
 
+    withName: '.*RANK_VARIANTS_SNV:TABIX_BGZIP' {
+        ext.when = false
+    }
+
     withName: '.*RANK_VARIANTS_SNV:TABIX_TABIX' {
         publishDir = [
             path: { "${params.outdir}/rank_and_filter" },
@@ -147,10 +148,7 @@ process {
     }
 
     withName: '.*RANK_VARIANTS_MT:BCFTOOLS_SORT' {
-        ext.when = false
-    }
-
-    withName: '.*RANK_VARIANTS_MT:TABIX_BGZIP' {
+        ext.args = "--output-type z"
         ext.prefix = { "${meta.id}_mt_ranked_${meta.set}" }
         publishDir = [
             path: { "${params.outdir}/rank_and_filter" },
@@ -159,6 +157,10 @@ process {
         ]
     }
 
+    withName: '.*RANK_VARIANTS_MT:TABIX_BGZIP' {
+        ext.when = false
+    }
+
     withName: '.*RANK_VARIANTS_MT:TABIX_TABIX' {
         publishDir = [
             path: { "${params.outdir}/rank_and_filter" },

modules/local/create_hgncids_file/main.nf

@@ -28,11 +28,14 @@ process CREATE_HGNCIDS_FILE {
                 for line in input:
                     if not line.startswith("#") and line.strip():
                         spl = line.strip().split("\\t")
-                        output.write(spl[3]+"\\n")
+                        output.write("HGNC:" + spl[3] + "\\n")
             else:
                 for line in input:
-                    if not line.startswith("#"):
-                        output.write(line)
+                    if not line.startswith("#") and line.strip():
+                        hgnc_id = line.strip()
+                        if not hgnc_id.startswith("HGNC:"):
+                            hgnc_id = "HGNC:" + hgnc_id
+                        output.write(hgnc_id + "\\n")
     CODE
 
     cat <<-END_VERSIONS > versions.yml

modules/local/fix_expansionhunter_header/main.nf

@@ -0,0 +1,62 @@
+process BCFTOOLS_FIXEXPANSIONHUNTERHEADER {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "bioconda::bcftools=1.20"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bcftools:1.20--h8b25389_0':
+        'biocontainers/bcftools:1.20--h8b25389_0' }"
+
+    input:
+    tuple val(meta), path(vcf)
+
+    output:
+    tuple val(meta), path("*.vcf"), emit: vcf
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    # Create header file with missing INFO and FORMAT fields from ExpansionHunter
+    cat > expansionhunter_headers.txt << 'EOF'
+    ##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant">
+    ##INFO=<ID=REF,Number=1,Type=Integer,Description="Reference copy number">
+    ##INFO=<ID=REPID,Number=1,Type=String,Description="Repeat identifier from the variant catalog">
+    ##INFO=<ID=RL,Number=1,Type=Integer,Description="Reference length in bp">
+    ##INFO=<ID=RU,Number=1,Type=String,Description="Repeat unit in the reference orientation">
+    ##FORMAT=<ID=SO,Number=1,Type=String,Description="Type of reads that support the allele; can be SPANNING, FLANKING, or INREPEAT">
+    ##FORMAT=<ID=REPCN,Number=1,Type=String,Description="Number of repeat units spanned by the allele">
+    ##FORMAT=<ID=REPCI,Number=1,Type=String,Description="Confidence interval for REPCN">
+    ##FORMAT=<ID=ADSP,Number=1,Type=String,Description="Number of spanning reads consistent with the allele">
+    ##FORMAT=<ID=ADFL,Number=1,Type=String,Description="Number of flanking reads consistent with the allele">
+    ##FORMAT=<ID=ADIR,Number=1,Type=String,Description="Number of in-repeat reads consistent with the allele">
+    EOF
+
+    # Add missing headers to VCF
+    bcftools annotate \\
+        -h expansionhunter_headers.txt \\
+        $args \\
+        -o ${prefix}.vcf \\
+        $vcf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.vcf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')
+    END_VERSIONS
+    """
+}

subworkflows/local/call_repeat_expansions.nf

@@ -2,6 +2,7 @@
 // Run ExpansionHunter and Stranger
 //
 
+include { BCFTOOLS_FIXEXPANSIONHUNTERHEADER            } from '../../modules/local/fix_expansionhunter_header/main'
 include { BCFTOOLS_NORM as SPLIT_MULTIALLELICS_EXP     } from '../../modules/nf-core/bcftools/norm/main'
 include { BCFTOOLS_REHEADER as BCFTOOLS_REHEADER_EXP   } from '../../modules/nf-core/bcftools/reheader/main'
 include { EXPANSIONHUNTER                              } from '../../modules/nf-core/expansionhunter/main'
@@ -38,7 +39,11 @@ workflow CALL_REPEAT_EXPANSIONS {
             EXPANSIONHUNTER.out.vcf.map{ meta, vcf -> [ meta, vcf, [], [] ]},
             ch_genome_fai
         )
-        RENAMESAMPLE_EXP ( BCFTOOLS_REHEADER_EXP.out.vcf )
+
+        // Fix missing INFO headers from ExpansionHunter
+        BCFTOOLS_FIXEXPANSIONHUNTERHEADER ( BCFTOOLS_REHEADER_EXP.out.vcf )
+
+        RENAMESAMPLE_EXP ( BCFTOOLS_FIXEXPANSIONHUNTERHEADER.out.vcf )
         TABIX_EXP_RENAME ( RENAMESAMPLE_EXP.out.vcf )
 
         // Split multi allelelic
@@ -68,6 +73,8 @@ workflow CALL_REPEAT_EXPANSIONS {
         ch_versions = ch_versions.mix(SVDB_MERGE_REPEATS.out.versions.first())
         ch_versions = ch_versions.mix(SAMTOOLS_SORT.out.versions.first())
         ch_versions = ch_versions.mix(SAMTOOLS_INDEX.out.versions.first())
+        ch_versions = ch_versions.mix(BCFTOOLS_FIXEXPANSIONHUNTERHEADER.out.versions.first())
+
 
 emit:
         vcf      = SVDB_MERGE_REPEATS.out.vcf  // channel: [ val(meta), path(vcf) ]