Integration of VCF and BGEN for gene-based testing (#92)

* Added plink division on gene level test step * Integrate support for VCF for gene-level test * Adding control for chunking when call gene level test * Update tests for bgen files * Add gene-based bgen test * Clean up unuseful comments * Add gene-based module test --------- Co-authored-by: johsr <[email protected]> Co-authored-by: Lukas Forer <[email protected]> Co-authored-by: seppinho <[email protected]>
genepi · Dec 15, 2023 · 04d684e · 04d684e
1 parent 72bfd26
commit 04d684e
Show file tree

Hide file tree

Showing 19 changed files with 1,674 additions and 10 deletions.
diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy
@@ -78,9 +78,14 @@ class WorkflowMain {
             exit 1, "Invalid config file. The 'write-mask' option does not work when building masks with 'sum'."
         }
 
+        if(params.genotypes_association_chunk_size > 0 ) {
+            //&& genotypes_association_format != 'bgen' ) {
+            exit 1, " Chunking is currently not available for gene-based tests (param: genotypes_association_chunk_size=0)."
+        }
+
         //Check association file format for gene-based tests
-        if (genotypes_association_format != 'bed'){
-            exit 1, "File format " + genotypes_association_format + " currently not supported for gene-based tests. Please use 'bed' input instead. "
+        if (genotypes_association_format != 'vcf' && genotypes_association_format != "bgen"){
+            exit 1, "File format " + genotypes_association_format + " currently not supported for gene-based tests. Please use 'vcf' or 'bgen' input instead. "
         }
         } else {
             //Check if tests exists

diff --git a/modules/local/regenie/regenie_step2_run_gene_tests.nf b/modules/local/regenie/regenie_step2_run_gene_tests.nf
@@ -5,10 +5,11 @@ process REGENIE_STEP2_RUN_GENE_TESTS {
 
     input:
     path step1_out
-    tuple val(filename), path(genotyped_plink_file)
+    tuple val(filename), path(genotyped_plink_bim_file), path(genotyped_plink_bed_file), path(genotyped_plink_fam_file), val(range)
     val assoc_format
 	path phenotypes_file
     path covariates_file
+    path sample_file
     path regenie_gene_anno_file
     path regenie_gene_setlist_file
     path regenie_gene_masks_file
@@ -20,8 +21,9 @@ process REGENIE_STEP2_RUN_GENE_TESTS {
     path "${filename}_masks*"
 
     script:
-    def format = assoc_format == 'bed' ? "--bed" : '--bgen'
+    def format = assoc_format == 'bgen' ? "--bgen" : '--pgen'
     def extension = assoc_format == 'bgen' ? ".bgen" : ''
+    def bgen_sample = sample_file ? "--sample $sample_file" : ''
     def firthApprox = params.regenie_firth_approx ? "--approx" : ""
     def firth = params.regenie_firth ? "--firth $firthApprox" : ""
     def binaryTrait =  params.phenotypes_binary_trait ? "--bt $firth " : ""
@@ -65,6 +67,7 @@ process REGENIE_STEP2_RUN_GENE_TESTS {
         $predictions \
         $apply_rint \
         $geneTest \
+        $bgen_sample \
         $aaf \
         $maxAaf \
         $vcMACThr \