MAINT: refactored conpair code

modules/conpairFilter.nf

@@ -5,6 +5,9 @@ process conpairFilter {
     path concordance
     path contamination
     path samples_path
+    val concordance_threshold
+    val contamination_threshold_samples
+    val contamination_threshold_match
 
 
     output:
@@ -16,6 +19,6 @@ process conpairFilter {
     script:
     outfile = "sample_paths_contamination_filtered.txt"
     """
-    conpair_contamination_filter.py --samples_path ${samples_path} --concordance_path ${concordance} --contamination_path ${contamination} --concordance_threshold ${params.concordance_threshold} --contamination_threshold_samples ${params.contamination_threshold_samples} --contamination_threshold_match ${params.contamination_threshold_match} --outfile ${outfile}
+    conpair_contamination_filter.py --samples_path ${samples_path} --concordance_path ${concordance} --contamination_path ${contamination} --concordance_threshold ${concordance_threshold} --contamination_threshold_samples ${contamination_threshold_samples} --contamination_threshold_match ${contamination_threshold_match} --outfile ${outfile}
     """
 }

modules/conpairPileup.nf

@@ -4,14 +4,17 @@ process conpairPileup {
     input:
     tuple val(match_normal_id), val(sample_id), path(bam), path(bai)
     path(marker_bed)
+    path(reference_genome)
+    path(reference_genome_dict)
+    path(reference_genome_idx)
 
     output:
     tuple val(match_normal_id), val(sample_id), path(pileup)
 
     script:
     pileup = "${sample_id}.pileup"
     """
-    gatk --java-options -Xmx10g Pileup -R ${params.reference_genome} -I ${bam} -L ${marker_bed} -O ${pileup} -verbose -RF NotDuplicateReadFilter -RF CigarContainsNoNOperator -RF MatchingBasesAndQualsReadFilter
+    gatk --java-options -Xmx10g Pileup -R ${reference_genome} -I ${bam} -L ${marker_bed} -O ${pileup} -verbose -RF NotDuplicateReadFilter -RF CigarContainsNoNOperator -RF MatchingBasesAndQualsReadFilter
     """
 
 }

modules/validate.nf

@@ -17,6 +17,8 @@ validParams = [
     marker_txt: 'path',
     vcfilter_config: '',
     reference_genome: 'path',
+    reference_genome_dict: 'path',
+    reference_genome_idx: 'path',
     high_depth_region: 'path',
     phylogenetics: 'boolean',
     with_topology: '',

nextflow.config

@@ -23,6 +23,8 @@ params {
     marker_txt = ""
     vcfilter_config = ""
     reference_genome = ""
+    reference_genome_dict = ""
+    reference_genome_idx = ""
     high_depth_region = ""
     phylogenetics = true
     phylogenetics_outdir_basename = ""

workflows/conpair_filter_with_match_normal.nf

@@ -20,13 +20,13 @@ workflow CONPAIR_FILTER_WITH_MATCH_NORMAL {
     sample_pileup_input_ch = Channel.of(sample_paths)
             .splitCsv( header: true, sep : '\t' )
             .map { row -> tuple( row.match_normal_id, row.sample_id, row.bam, row.bai ) }
-    pileup_sample = conpairPileupSample(sample_pileup_input_ch, marker_bed)
+    pileup_sample = conpairPileupSample(sample_pileup_input_ch, marker_bed, params.reference_genome, params.reference_genome_dict, params.reference_genome_idx)
     // normal
     match_pileup_input_ch = Channel.of(sample_paths)
             .splitCsv( header: true, sep : '\t' )
             .map { row -> tuple( row.match_normal_id, row.match_normal_id, row.bam_match, row.bai_match ) }
             .unique()
-    pileup_match = conpairPileupMatch(match_pileup_input_ch, marker_bed)
+    pileup_match = conpairPileupMatch(match_pileup_input_ch, marker_bed, params.reference_genome, params.reference_genome_dict, params.reference_genome_idx)
 
     // Concordance between sample and match normal
     concordance_input_ch = pileup_sample.combine(pileup_match)
@@ -41,7 +41,7 @@ workflow CONPAIR_FILTER_WITH_MATCH_NORMAL {
         .collectFile( name: 'conpair_out/contamination.txt', newLine: true )
 
     // Filtering contamination based on concordance and contamination
-    (sample_paths_conpaired, conpair_log, concordance_path, contamination_path) = conpairFilter(concordance_output_ch, contamination_output_ch, params.sample_paths)
+    (sample_paths_conpaired, conpair_log, concordance_path, contamination_path) = conpairFilter(concordance_output_ch, contamination_output_ch, params.sample_paths, params.concordance_threshold, params.contamination_threshold_samples, params.contamination_threshold_match)
 
 
     emit: