allow to input existing genomicsdb

nf-core · Jun 17, 2023 · bc204e1 · bc204e1
1 parent 58f9d99
commit bc204e1
Show file tree

Hide file tree

Showing 4 changed files with 14 additions and 12 deletions.
diff --git a/nextflow.config b/nextflow.config
@@ -69,6 +69,7 @@ params {
     ignore_soft_clipped_bases   = false // no --dont-use-soft-clipped-bases for GATK Mutect2
     wes                         = false // Set to true, if data is exome/targeted sequencing data. Used to use correct models in various variant callers
     joint_germline              = false // g.vcf & joint germline calling are not run by default if HaplotypeCaller is selected
+    genomicsdb_workspace        = null  // GenomicsDB Workspace 
 
     // Annotation
     vep_out_format      = 'vcf'

diff --git a/subworkflows/local/bam_joint_calling_germline_gatk/main.nf b/subworkflows/local/bam_joint_calling_germline_gatk/main.nf
@@ -25,6 +25,7 @@ workflow BAM_JOINT_CALLING_GERMLINE_GATK {
     resource_snps_vcf
     resource_snps_tbi
     known_snps_vqsr
+    genomicsdb_workspace
 
     main:
     versions = Channel.empty()
@@ -36,10 +37,12 @@ workflow BAM_JOINT_CALLING_GERMLINE_GATK {
     gendb_input = input
         .map{ meta, gvcf, tbi, intervals -> [ [ id:'joint_variant_calling', intervals_name:intervals.simpleName, num_intervals:meta.num_intervals ], gvcf, tbi, intervals ] }
         .groupTuple(by:[0, 3])
-        .map{ meta, gvcf, tbi, intervals -> [ meta, gvcf, tbi, intervals, [], [] ] }
+        .map{ meta, gvcf, tbi, intervals -> [ meta, gvcf, tbi, intervals, [] ] }
+        .combine(genomicsdb_workspace)
 
     // Convert all sample vcfs into a genomicsdb workspace using genomicsdbimport
-    GATK4_GENOMICSDBIMPORT(gendb_input, false, false, false)
+    // If genomicsdb_workspace, then the boolean will evaluate to true, hacky work-around for the module
+    GATK4_GENOMICSDBIMPORT(gendb_input, false, genomicsdb_workspace, false)
 
     genotype_input = GATK4_GENOMICSDBIMPORT.out.genomicsdb.map{ meta, genomicsdb -> [ meta, genomicsdb, [], [], [] ] }
 

diff --git a/subworkflows/local/bam_variant_calling_germline_all/main.nf b/subworkflows/local/bam_variant_calling_germline_all/main.nf
@@ -36,6 +36,7 @@ workflow BAM_VARIANT_CALLING_GERMLINE_ALL {
     known_sites_snps_tbi
     known_snps_vqsr
     joint_germline                    // boolean: [mandatory] [default: false] joint calling of germline variants
+    genomicsdb_workspace
 
     main:
     versions = Channel.empty()
@@ -141,7 +142,8 @@ workflow BAM_VARIANT_CALLING_GERMLINE_ALL {
                 known_indels_vqsr,
                 known_sites_snps,
                 known_sites_snps_tbi,
-                known_snps_vqsr)
+                known_snps_vqsr,
+                genomicsdb_workspace)
 
             vcf_haplotypecaller = BAM_JOINT_CALLING_GERMLINE_GATK.out.genotype_vcf
             versions = versions.mix(BAM_JOINT_CALLING_GERMLINE_GATK.out.versions)

diff --git a/workflows/sarek.nf b/workflows/sarek.nf
@@ -128,12 +128,6 @@ if (params.tools && (params.tools.split(',').contains('ascat') || params.tools.s
     }
 }
 
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    IMPORT LOCAL MODULES/SUBWORKFLOWS
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-*/
-
 // Initialize file channels based on params, defined in the params.genomes[params.genome] scope
 ascat_alleles      = params.ascat_alleles      ? Channel.fromPath(params.ascat_alleles).collect()     : Channel.empty()
 ascat_loci         = params.ascat_loci         ? Channel.fromPath(params.ascat_loci).collect()        : Channel.empty()
@@ -161,8 +155,9 @@ vep_genome         = params.vep_genome         ?: Channel.empty()
 vep_species        = params.vep_species        ?: Channel.empty()
 
 // Initialize files channels based on params, not defined within the params.genomes[params.genome] scope
-snpeff_cache       = params.snpeff_cache       ? Channel.fromPath(params.snpeff_cache).collect()      : []
-vep_cache          = params.vep_cache          ? Channel.fromPath(params.vep_cache).collect()         : []
+genomicsdb_workspace = params.genomicsdb_workspace ? Channel.fromPath(params.genomicsdb_workspace).collect() : []
+snpeff_cache         = params.snpeff_cache         ? Channel.fromPath(params.snpeff_cache).collect()         : []
+vep_cache            = params.vep_cache            ? Channel.fromPath(params.vep_cache).collect()            : []
 
 vep_extra_files = []
 
@@ -936,7 +931,8 @@ workflow SAREK {
             known_sites_snps,
             known_sites_snps_tbi,
             known_snps_vqsr,
-            params.joint_germline)
+            params.joint_germline,
+            genomicsdb_workspace)
 
         // TUMOR ONLY VARIANT CALLING
         BAM_VARIANT_CALLING_TUMOR_ONLY_ALL(