Rename the threshold variables [ci skip]

bin/fastq_stats.py

@@ -30,7 +30,7 @@
             if m:
                 mapped_p = float(m[1])
 
-    if int(wgsmetrics.loc[0, 'MEDIAN_COVERAGE']) >= args['median_coverage_cutoff']:
+    if int(wgsmetrics.loc[0, 'MEDIAN_COVERAGE']) >= args['cutoff_median_coverage']:
         coverage_threshold_met = 1
     else:
         coverage_threshold_met = 0

bin/sample_stats.py

@@ -16,12 +16,12 @@
     parser.add_argument('--wgsmetrics_file', dest='wgsmetrics_file', required=True, metavar='wgsmetrics_file', type=str, help='The WGS metrics file')
     parser.add_argument('--ntmfraction_file', dest='ntmfraction_file', required=True, metavar='ntmfraction_file', type=str, help='The NTM fraction file')
 
-    parser.add_argument('--median_coverage_cutoff', metavar='median_coverage_cutoff', default=10, type=float, help='The median coverage cutoff threshold')
-    parser.add_argument('--breadth_of_coverage_cutoff', metavar='breadth_of_coverage_cutoff', default=0.9, type=float, help='The breadth of coverage cutoff threshold')
-    parser.add_argument('--ntm_fraction_cutoff', metavar='ntm_fraction_cutoff', default=0.2, type=float, help='The NTM fraction cutoff threshold')
+    parser.add_argument('--cutoff_median_coverage', metavar='cutoff_median_coverage', default=10, type=float, help='The median coverage cutoff threshold')
+    parser.add_argument('--cutoff_breadth_of_coverage', metavar='cutoff_breadth_of_coverage', default=0.9, type=float, help='The breadth of coverage cutoff threshold')
+    parser.add_argument('--cutoff_ntm_fraction', metavar='cutoff_ntm_fraction', default=0.2, type=float, help='The NTM fraction cutoff threshold')
 
 ## NOTE: This is computed by the multiple_infection_filter script
-#    parser.add_argument('--rel_abundance_cutoff', metavar='rel_abundance_cutoff', default=0.8, type=float, help='The relative abundance cutoff threshold')
+#    parser.add_argument('--cutoff_rel_abundance', metavar='cutoff_rel_abundance', default=0.8, type=float, help='The relative abundance cutoff threshold')
 
     args = vars(parser.parse_args())
 
@@ -46,17 +46,17 @@
             if m:
                 mapped_p = float(m[1])
 
-    if int(wgsmetrics.loc[0, 'MEDIAN_COVERAGE']) >= args['median_coverage_cutoff']:
+    if int(wgsmetrics.loc[0, 'MEDIAN_COVERAGE']) >= args['cutoff_median_coverage']:
         coverage_threshold_met = 1
     else:
         coverage_threshold_met = 0
 
-    if float(wgsmetrics.loc[0, 'PCT_1X']) >= args['breadth_of_coverage_cutoff']:
+    if float(wgsmetrics.loc[0, 'PCT_1X']) >= args['cutoff_breadth_of_coverage']:
         breadth_of_coverage_threshold_met = 1
     else:
         breadth_of_coverage_threshold_met = 0
 
-    if ntm_fraction <= args['ntm_fraction_cutoff']:
+    if ntm_fraction <= args['cutoff_ntm_fraction']:
         ntm_fraction_threshold_met = 1
     else:
         ntm_fraction_threshold_met = 0

bin/variant_table_to_fasta.py

@@ -11,7 +11,7 @@ def main(args):
         for idx, l in enumerate(table_file):
             l = l.strip().split('\t')
             l = [i.replace('*', '-').replace('.', '-') for i in l]
-            if l.count('-')/len(l) < (1-args.site_representation_cutoff):
+            if l.count('-')/len(l) < (1-args.cutoff_site_representation):
                 table.append(l)
             else:
                 pass
@@ -24,7 +24,7 @@ def main(args):
 parser = argparse.ArgumentParser(description='tbprofiler script',formatter_class=argparse.ArgumentDefaultsHelpFormatter)
 parser.add_argument('table', type=str, help='The input table to convert (stdin if empty)')
 parser.add_argument('output_fasta', type=str, help='The output fasta file')
-parser.add_argument('site_representation_cutoff', type=float, help='Minimum fraction of samples that need to have a call at a site before it is considered')
+parser.add_argument('cutoff_site_representation', type=float, help='Minimum fraction of samples that need to have a call at a site before it is considered')
 parser.set_defaults(func=main)
 args = parser.parse_args()
 args.func(args)

default_params.config

@@ -24,23 +24,23 @@ ref_gvcf_tbi =  "${projectDir}/resources/ref_gvcfs/LineagesAndOutgroupV2.g.vcf.g
 //  ##### QC THRESHOLDS #####
 
 //The median coverage required to process the sample
-median_coverage_cutoff = 10
+cutoff_median_coverage = 10
 
 //The breadth of coverage required to process the sample
-breadth_of_coverage_cutoff = 0.90
+cutoff_breadth_of_coverage = 0.90
 
 //The relative abundunce of the majority strain required to process the sample
-rel_abundance_cutoff = 0.80
+cutoff_rel_abundance = 0.80
 
 //The maximum fraction of NTM DNA allowed to process the sample
-ntm_fraction_cutoff = 0.20
+cutoff_ntm_fraction = 0.20
 
 // The minimum fraction of samples that need to have a call at a site before the site is considered in phylogeny
-site_representation_cutoff = 0.95
+cutoff_site_representation = 0.95
 
 
 // p-value below which binominal strand bias is considered significant
-strand_bias_cutoff = 0.05
+cutoff_strand_bias = 0.05
 
 // ##### Partial workflows #####
 

modules/gatk/variants_to_table.nf

@@ -22,7 +22,7 @@ process GATK_VARIANTS_TO_TABLE {
 
         variant_table_to_fasta.py !{joint_name}.!{prefix}.table \
             !{joint_name}.!{prefix}.fa \
-            !{params.site_representation_cutoff}
+            !{params.cutoff_site_representation}
         '''
 
     stub:

modules/utils/multiple_infection_filter.nf

@@ -13,7 +13,7 @@ process UTILS_MULTIPLE_INFECTION_FILTER {
     script:
 
         """
-        multiple_infection_filter.py per_sample_results ${params.rel_abundance_cutoff}
+        multiple_infection_filter.py per_sample_results ${params.cutoff_rel_abundance}
         """
 
     stub: 

modules/utils/reformat_lofreq.nf

@@ -17,7 +17,7 @@ process UTILS_REFORMAT_LOFREQ {
             ${sampleName}.lofreq.reformat.vcf
 
         reduce_strand_bias.py \\
-            ${params.strand_bias_cutoff} \\
+            ${params.cutoff_strand_bias} \\
             ${sampleName}.lofreq.reformat.vcf  \\
             ${sampleName}.lofreq.reformat.corrected.vcf 
         """

modules/utils/sample_stats.nf

@@ -16,9 +16,9 @@ process UTILS_SAMPLE_STATS {
             --samtoolsstats_file ${samtoolsStats} \\
             --wgsmetrics_file ${wgsMetrics} \\
             --ntmfraction_file ${ntmFraction} \\
-            --median_coverage_cutoff ${params.median_coverage_cutoff} \\
-            --breadth_of_coverage_cutoff ${params.breadth_of_coverage_cutoff} \\
-            --ntm_fraction_cutoff ${params.ntm_fraction_cutoff}
+            --cutoff_median_coverage ${params.cutoff_median_coverage} \\
+            --cutoff_breadth_of_coverage ${params.cutoff_breadth_of_coverage} \\
+            --cutoff_ntm_fraction ${params.cutoff_ntm_fraction}
         """
 
 }

params/params.yaml

@@ -12,19 +12,19 @@ vcf_name : "joint"
 #  ##### QC THRESHOLDS #####
 
 #The median coverage required to process the sample
-median_coverage_cutoff : 10
+cutoff_median_coverage : 10
 
 #The breadth of coverage required to process the sample
-breadth_of_coverage_cutoff : 0.90
+cutoff_breadth_of_coverage : 0.90
 
 #The relative abundunce of the majority strain required to process the sample
-rel_abundance_cutoff : 0.80
+cutoff_rel_abundance : 0.80
 
 #The maximum fraction of NTM DNA allowed to process the sample
-ntm_fraction_cutoff : 0.20
+cutoff_ntm_fraction : 0.20
 
 # The minimum fraction of samples that need to have a call at a site before the site is considered in phylogeny
-site_representation_cutoff : 0.95
+cutoff_site_representation : 0.95
 
 
 # ##### Partial workflows #####