Fix intervals with dot

CHANGELOG.md

@@ -34,6 +34,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#1381](https://github.com/nf-core/sarek/pull/1381) - Swap NGSCheckMate bed file for GATK.GRCh37 to one without the `chr` prefix
 - [#1383](https://github.com/nf-core/sarek/pull/1383) - Fix `--three_prime_clip_r{1,2}` parameter documentation
 - [#1390](https://github.com/nf-core/sarek/pull/1390) - Fix badges in README
+- [#1403](https://github.com/nf-core/sarek/pull/1403) - Fix intervals usage with dot in chromosome names
 
 ### Removed
 

conf/modules/deepvariant.config

@@ -17,7 +17,7 @@ process {
 
     withName: 'DEEPVARIANT' {
         ext.args   = { params.wes ?  "--model_type WES" : "--model_type WGS" }
-        ext.prefix = { meta.num_intervals <= 1 ? "${meta.id}.deepvariant" : "${meta.id}.deepvariant.${intervals.simpleName}" }
+        ext.prefix = { meta.num_intervals <= 1 ? "${meta.id}.deepvariant" : "${meta.id}.deepvariant.${intervals.baseName}" }
         ext.when   = { params.tools && params.tools.split(',').contains('deepvariant') }
         publishDir = [
             mode: params.publish_dir_mode,

conf/modules/freebayes.config

@@ -27,7 +27,7 @@ process {
     withName: 'FREEBAYES' {
         ext.args   = { '--min-alternate-fraction 0.1 --min-mapping-quality 1' }
         //To make sure no naming conflicts ensure with module BCFTOOLS_SORT & the naming being correct in the output folder
-        ext.prefix = { meta.num_intervals <= 1 ? "${meta.id}" : "${meta.id}.${target_bed.simpleName}" }
+        ext.prefix = { meta.num_intervals <= 1 ? "${meta.id}" : "${meta.id}.${target_bed.baseName}" }
         ext.when   = { params.tools && params.tools.split(',').contains('freebayes') }
         publishDir = [
             enabled: false

conf/modules/haplotypecaller.config

@@ -17,7 +17,7 @@ process {
 
     withName: 'GATK4_HAPLOTYPECALLER' {
         ext.args   = { params.joint_germline ? "-ERC GVCF" : "" }
-        ext.prefix = { meta.num_intervals <= 1 ? ( params.joint_germline ? "${meta.id}.haplotypecaller.g" : "${meta.id}.haplotypecaller" ) : ( params.joint_germline ? "${meta.id}.haplotypecaller.${intervals.simpleName}.g" :"${meta.id}.haplotypecaller.${intervals.simpleName}" ) }
+        ext.prefix = { meta.num_intervals <= 1 ? ( params.joint_germline ? "${meta.id}.haplotypecaller.g" : "${meta.id}.haplotypecaller" ) : ( params.joint_germline ? "${meta.id}.haplotypecaller.${intervals.baseName}.g" :"${meta.id}.haplotypecaller.${intervals.baseName}" ) }
         ext.when   = { params.tools && params.tools.split(',').contains('haplotypecaller') }
         publishDir = [
             mode: params.publish_dir_mode,

conf/modules/mpileup.config

@@ -24,7 +24,7 @@ process {
     withName: 'BCFTOOLS_MPILEUP' {
         ext.args2  = { '--multiallelic-caller' }
         ext.args3  = { "-i 'count(GT==\"RR\")==0'" } // only report non homozygous reference variants
-        ext.prefix = { meta.num_intervals <= 1 ? "${meta.id}.bcftools" : "${meta.id}_${intervals.simpleName}.bcftools" }
+        ext.prefix = { meta.num_intervals <= 1 ? "${meta.id}.bcftools" : "${meta.id}_${intervals.baseName}.bcftools" }
         ext.when   = { params.tools && params.tools.split(',').contains('mpileup') }
         publishDir = [
             mode: params.publish_dir_mode,

conf/modules/mutect2.config

@@ -18,7 +18,7 @@ process {
 
         withName: 'GATK4_MUTECT2' {
             ext.args   = { params.ignore_soft_clipped_bases ? "--dont-use-soft-clipped-bases true --f1r2-tar-gz ${task.ext.prefix}.f1r2.tar.gz" : "--f1r2-tar-gz ${task.ext.prefix}.f1r2.tar.gz" }
-            ext.prefix = { meta.num_intervals <= 1 ? "${meta.id}.mutect2" : "${meta.id}.mutect2.${intervals.simpleName}" }
+            ext.prefix = { meta.num_intervals <= 1 ? "${meta.id}.mutect2" : "${meta.id}.mutect2.${intervals.baseName}" }
             ext.when   = { params.tools && params.tools.split(',').contains('mutect2') }
             publishDir = [
                 mode: params.publish_dir_mode,
@@ -91,7 +91,7 @@ process {
         }
 
         withName: 'GETPILEUPSUMMARIES.*' {
-            ext.prefix = { meta.num_intervals <= 1 ? "${meta.id}.mutect2" : "${meta.id}.mutect2.${intervals.simpleName}" }
+            ext.prefix = { meta.num_intervals <= 1 ? "${meta.id}.mutect2" : "${meta.id}.mutect2.${intervals.baseName}" }
             publishDir = [
                 mode: params.publish_dir_mode,
                 path: { "${params.outdir}/variant_calling/" },

conf/modules/recalibrate.config

@@ -16,7 +16,7 @@
 process {
 
     withName: 'GATK4_APPLYBQSR|GATK4SPARK_APPLYBQSR' {
-        ext.prefix       = { meta.num_intervals <= 1 ? "${meta.id}.recal" : "${meta.id}_${intervals.simpleName}.recal" }
+        ext.prefix       = { meta.num_intervals <= 1 ? "${meta.id}.recal" : "${meta.id}_${intervals.baseName}.recal" }
         publishDir       = [
             mode: params.publish_dir_mode,
             path: { "${params.outdir}/preprocessing/" },

conf/modules/sentieon_dnascope.config

@@ -16,7 +16,7 @@
 process {
 
     withName: 'SENTIEON_DNASCOPE' {
-        ext.prefix       = { meta.num_intervals <= 1 ? "${meta.id}.dnascope" : "${meta.id}.dnascope.${intervals.simpleName}" }
+        ext.prefix       = { meta.num_intervals <= 1 ? "${meta.id}.dnascope" : "${meta.id}.dnascope.${intervals.baseName}" }
         ext.when         = { params.tools && params.tools.split(',').contains('sentieon_dnascope') }
         publishDir       = [
             mode: params.publish_dir_mode,

conf/modules/sentieon_haplotyper.config

@@ -16,7 +16,7 @@
 process {
 
     withName: 'SENTIEON_HAPLOTYPER' {
-        ext.prefix       = { meta.num_intervals <= 1 ? "${meta.id}.haplotyper" : "${meta.id}.haplotyper.${intervals.simpleName}" }
+        ext.prefix       = { meta.num_intervals <= 1 ? "${meta.id}.haplotyper" : "${meta.id}.haplotyper.${intervals.baseName}" }
         ext.when         = { params.tools && params.tools.split(',').contains('sentieon_haplotyper') }
         publishDir       = [
             mode: params.publish_dir_mode,

conf/modules/strelka.config

@@ -17,7 +17,7 @@ process {
 
     withName: 'STRELKA_.*' {
         ext.args   = { params.wes ? '--exome' : '' }
-        ext.prefix = { meta.num_intervals <= 1 ? "${meta.id}.strelka" : "${meta.id}.strelka.${target_bed.simpleName}" }
+        ext.prefix = { meta.num_intervals <= 1 ? "${meta.id}.strelka" : "${meta.id}.strelka.${target_bed.baseName}" }
         ext.when   = { params.tools && params.tools.split(',').contains('strelka') }
         publishDir = [
             mode: params.publish_dir_mode,

subworkflows/local/bam_joint_calling_germline_gatk/main.nf

@@ -37,7 +37,7 @@ workflow BAM_JOINT_CALLING_GERMLINE_GATK {
     // Rename based on num_intervals, group all samples by their interval_name/interval_file and restructure for channel
     // Group by [0, 3] to avoid a list of metas and make sure that any intervals
     gendb_input = input
-        .map{ meta, gvcf, tbi, intervals -> [ [ id:'joint_variant_calling', intervals_name:intervals.simpleName, num_intervals:meta.num_intervals ], gvcf, tbi, intervals ] }
+        .map{ meta, gvcf, tbi, intervals -> [ [ id:'joint_variant_calling', intervals_name:intervals.baseName, num_intervals:meta.num_intervals ], gvcf, tbi, intervals ] }
         .groupTuple(by:3) //join on interval file
         .map{ meta_list, gvcf, tbi, intervals ->
             // meta is now a list of [meta1, meta2] but they are all the same. So take the first element.

subworkflows/local/bam_joint_calling_germline_sentieon/main.nf

@@ -33,7 +33,7 @@ workflow BAM_JOINT_CALLING_GERMLINE_SENTIEON {
     versions = Channel.empty()
 
     sentieon_input = input
-        .map{ meta, gvcf, tbi, intervals -> [ [ id:'joint_variant_calling', intervals_name:intervals.simpleName, num_intervals:meta.num_intervals ], gvcf, tbi, intervals ] }
+        .map{ meta, gvcf, tbi, intervals -> [ [ id:'joint_variant_calling', intervals_name:intervals.baseName, num_intervals:meta.num_intervals ], gvcf, tbi, intervals ] }
         .groupTuple(by:[0, 3])
 
     SENTIEON_GVCFTYPER(sentieon_input, fasta, fai, dbsnp, dbsnp_tbi)

subworkflows/local/bam_variant_calling_haplotypecaller/main.nf

@@ -29,7 +29,7 @@ workflow BAM_VARIANT_CALLING_HAPLOTYPECALLER {
     cram_intervals = cram.combine(intervals)
         // Move num_intervals to meta map
         // Add interval_name to allow correct merging with interval files
-        .map{ meta, cram, crai, intervals, num_intervals -> [ meta + [ interval_name:intervals.simpleName, num_intervals:num_intervals, variantcaller:'haplotypecaller' ], cram, crai, intervals, [] ] }
+        .map{ meta, cram, crai, intervals, num_intervals -> [ meta + [ interval_name:intervals.baseName, num_intervals:num_intervals, variantcaller:'haplotypecaller' ], cram, crai, intervals, [] ] }
 
     GATK4_HAPLOTYPECALLER(cram_intervals, fasta, fasta_fai, dict.map{ meta, dict -> [ dict ] }, dbsnp, dbsnp_tbi)
 

subworkflows/local/bam_variant_calling_sentieon_haplotyper/main.nf

@@ -34,7 +34,7 @@ workflow BAM_VARIANT_CALLING_SENTIEON_HAPLOTYPER {
         .map{ meta, cram, crai, intervals, num_intervals -> [
             meta + [
                 num_intervals:num_intervals,
-                intervals_name:intervals.simpleName,
+                intervals_name:intervals.baseName,
                 variantcaller:'sentieon_haplotyper'],
             cram,
             crai,

subworkflows/local/prepare_genome/main.nf

@@ -123,7 +123,7 @@ workflow PREPARE_GENOME {
     hashtable                = DRAGMAP_HASHTABLE.out.hashmap.map{ meta, index -> [index] }.collect()  // path: dragmap/*
     dbsnp_tbi                = TABIX_DBSNP.out.tbi.map{ meta, tbi -> [tbi] }.collect()                // path: dbsnb.vcf.gz.tbi
     dict                     = GATK4_CREATESEQUENCEDICTIONARY.out.dict                                // path: genome.fasta.dict
-    fasta_fai                = SAMTOOLS_FAIDX.out.fai.map{ meta, fai -> [fai] }                       // path: genome.fasta.fai
+    fasta_fai                = SAMTOOLS_FAIDX.out.fai.map{ meta, fai -> [fai] }.flatten().first()     // path: genome.fasta.fai
     germline_resource_tbi    = TABIX_GERMLINE_RESOURCE.out.tbi.map{ meta, tbi -> [tbi] }.collect()    // path: germline_resource.vcf.gz.tbi
     known_snps_tbi           = TABIX_KNOWN_SNPS.out.tbi.map{ meta, tbi -> [tbi] }.collect()           // path: {known_indels*}.vcf.gz.tbi
     known_indels_tbi         = TABIX_KNOWN_INDELS.out.tbi.map{ meta, tbi -> [tbi] }.collect()         // path: {known_indels*}.vcf.gz.tbi

workflows/sarek.nf

@@ -324,7 +324,7 @@ workflow SAREK {
     // Built from the fasta file:
     dict       = params.dict        ? Channel.fromPath(params.dict).map{ it -> [ [id:'dict'], it ] }.collect()
                                     : PREPARE_GENOME.out.dict
-    fasta_fai  = params.fasta_fai   ? Channel.fromPath(params.fasta_fai).collect()
+    fasta_fai  = params.fasta_fai   ? Channel.fromPath(params.fasta_fai).first()
                                     : PREPARE_GENOME.out.fasta_fai
     bwa        = params.bwa         ? Channel.fromPath(params.bwa).collect()
                                     : PREPARE_GENOME.out.bwa