Merge pull request #263 from RoanKanninga/master

added new compareWith VKGL b38 script to tortilla

bin/compareWithVKGL_gatk4_b38.sh

@@ -10,14 +10,14 @@ function showHelp() {
 	#
 	cat <<EOH
 ===============================================================================================================
-Script to compare a vcf file with the VKGL data
+Script to compare a vcf file with the GIAB HC callset(HG002_GRCh38_1_22_v4.2.1) for the VKGL veldnorm
 Usage:
 	$(basename "${0}") OPTIONS
 Options:
 	-h   Show this help.
 	-i   inputFile
 	-t   workDir working directory (default= CURRENTDIR)
-	-b   which build, ucsc (chr1, chr2,chrX etc) or regular (1,2,X etc) default is regular
+	-b   which build, UCSC (chr1, chr2,chrX etc) or regular (1,2,X etc) default is UCSC
 	-o   outputFolder (default:\${workDir}/output/)
 
 ===============================================================================================================

bin/gvcf2bed2.py

@@ -169,7 +169,7 @@ def read_targets(bed,gVCF,outputFile):
 #   gVCF = cyvcf2.VCF(gVCF)
     content=[]
     with open(outputFile, "w") as ohandle:
-        ohandle.write(str("chr\tstart\tstop\tgene\tGQ_low\tGQ_medium\tGQ_high\tavgDp\tpercentage DP<20\tpercentage DP>20\tsummedDP\ttargetSize\tnumberBasesDPInCategoryLow\tnumberBasesZeroCoverage" + "\n" ))
+        ohandle.write(str("chr\tstart\tstop\tgene\tGQ_low\tGQ_medium\tGQ_high\tavgDp\tpercentage DP<10\tpercentage DP>10\tsummedDP\ttargetSize\tnumberBasesDPInCategoryLow\tnumberBasesZeroCoverage" + "\n" ))
         with open(bed)as f:
             for line in f:
                 content= line.strip().split()
@@ -223,7 +223,7 @@ def main():
     global dictGQThresholds
     global dictDPThresholds
     dictGQThresholds = {'low': 20, 'medium': 50, 'high': 50}
-    dictDPThresholds = {'low': 20}
+    dictDPThresholds = {'low': 10}
 
     parser = argparse.ArgumentParser(description=desc)
 
@@ -238,8 +238,8 @@ def main():
     parser.add_argument("-q", "--qualityThresholds", type=list, default=[20,50],
                         help="Genotype quality range per category low, medium, high. default: [20,50]"
                             "This results in GQ categories: low: 0 <-> 20, medium: 21 <-> 50, high: > 51")
-    parser.add_argument("-d", "--depthThresholds", type=list, default=[20],
-                        help="DepthThreshold, default=[20] this results in GQ categories: low: 0 <-> 20,high: > 20")
+    parser.add_argument("-d", "--depthThresholds", type=list, default=[10],
+                        help="DepthThreshold, default=[10] this results in GQ categories: low: 0 <-> 10,high: > 10")
     parser.add_argument("-b", "--bedfile", type=str,required=True,help="target bedfile to calculate percentage per quality threshold."
                         "Bedfile must contain colunms: chr \t start \t stop \t gene")
     parser.add_argument("-g", "--bedgraph", type=bool, default=True,

bin/tortilla.sh

@@ -9,17 +9,18 @@ cat <<EOH
 
 Script requires one initial argument:
 
-    -m|--makeSamplesheet          Go to tortilla_makeSamplesheet, for different make samplesheet options. (tortilla_makeSamplesheet.sh)
-    -b|--bamout                   Recreating the bam file for a certain region where the variant calling is based on (bamout.sh)
-    -c|--countCoverage            Counting coverage (avg,med,sd,percentage 10/20/30/50/100x coverage) per Gene and target based on the panel that is given (countCoverage.sh)
-    -v|--vcfCompare               Comparing 2 vcf files with eachother, this will output the differences + a vcf stats file (vcf-compare_2.0.sh)
-    -n|--validateNGS              Script to check the known SNPs back in the NGS_DNA_Verification (checkValidationNGS_DNA_v7.sh)
-    -cv|--compareWithVKGL         script that compares vcf files with the VKGL standard
-    -cv4|--compareWithVKGL_GATK4  same as compareWithVKGL but with gatk4 commands
-    -r|--revertBamToFastQ         go back from bam to fastq (paired end only)
-    -cc|--calculateCoverage       CoveragePerBase or per Target calculations for a specific targetpanel
-    -d|--cramToBam                Converting cram files to bam(CramConversion.sh)
-    -l|--liftover                 Liftover vcf file (LiftoverVcf.sh)
+    -m|--makeSamplesheet           Go to tortilla_makeSamplesheet, for different make samplesheet options. (tortilla_makeSamplesheet.sh)
+    -b|--bamout                    Recreating the bam file for a certain region where the variant calling is based on (bamout.sh)
+    -c|--countCoverage             Counting coverage (avg,med,sd,percentage 10/20/30/50/100x coverage) per Gene and target based on the panel that is given (countCoverage.sh)
+    -v|--vcfCompare                Comparing 2 vcf files with eachother, this will output the differences + a vcf stats file (vcf-compare_2.0.sh)
+    -n|--validateNGS               Script to check the known SNPs back in the NGS_DNA_Verification (checkValidationNGS_DNA_v7.sh)
+    -cv|--compareWithVKGL          script that compares vcf files with the VKGL standard
+    -cv4|--compareWithVKGL_GATK4   same as compareWithVKGL but with gatk4 commands
+		-cv438|--compareWithVKGL_GATK4 compareWithVKGL, with GATK and GRCh38
+    -r|--revertBamToFastQ          go back from bam to fastq (paired end only)
+    -cc|--calculateCoverage        CoveragePerBase or per Target calculations for a specific targetpanel
+    -d|--cramToBam                 Converting cram files to bam(CramConversion.sh)
+    -l|--liftover                  Liftover vcf file (LiftoverVcf.sh)
 ===============================================================================================================
 EOH
 trap - EXIT
@@ -66,6 +67,11 @@ then
 	shift
 	# shellcheck disable=SC2154
 	"${EBROOTNGSMINUTILS}/bin/compareWithVKGL_gatk4.sh" "${@}"
+elif [[ "${1}" == "--compareWithVKGL_GATK4_38" || "${1}" == "-cv438" ]]
+then
+	shift
+	# shellcheck disable=SC2154
+	"${EBROOTNGSMINUTILS}/bin/compareWithVKGL_gatk4_b38.sh" "${@}"
 elif [[ "${1}" == "--revertBamToFastQ" || "${1}" == "-r" ]]
 then
 	shift