Merge pull request #271 from RoanKanninga/gatk4

Gatk4

parameters.csv

@@ -8,13 +8,13 @@ hpoVersion,90
 gatkJar,gatk-package-4.1.2.0-local.jar
 gavinPlusJar,gavin-plus-1.5.0-RELEASE.jar
 picardJar,picard.jar
-vepDBVersion,90
+vepDBVersion,92
 vepAssemblyVersion,GRCh37
 bcfToolsVersion,BCFtools/1.9-${toolChain_min}
 bedToolsVersion,BEDTools/2.28.0-${toolChain_min}
-bwaVersion,BWA/2.0pre1-${toolChain_max}
+bwaVersion,BWA/0.7.17-${toolChain_min}
 computeVersion,Molgenis-Compute/v19.01.1-Java-11-LTS
-caddVersion,CADD/v1.3
+caddVersion,CADD/v1.4-foss-2018b
 convadingVersion,1.2.1-${toolChain_min}
 cutadaptVersion,cutadapt/1.13-${toolChain_max}-Python-2.7.10
 fastqcVersion,FastQC/0.11.8-Java-11-LTS
@@ -37,7 +37,7 @@ rVersion,R/3.6.1-${toolChain_max}-bare
 sambambaVersion,sambamba/0.7.0
 samtoolsVersion,SAMtools/1.9-${toolChain_min}
 seqTkVersion,seqtk/1.3-${toolChain_min}
-snpEffVersion,snpEff/4.3t-Java-Java-11-LTS
+snpEffVersion,snpEff/4.3t-Java-11-LTS
 vcfAnnoVersion,vcfanno/v0.3.2
 vepVersion,VEP/90.5
 verifyBamIDVersion,verifyBamID/1.1.3-${toolChain_min}
@@ -206,8 +206,8 @@ vcfAnnoCustomConfLua,${projectPrefix}.batch-${batchID}.custom.conf.lua
 vcfAnnoGnomadGenomesConf,${projectPrefix}.batch-${batchID}.conf.gnomad.genomes.txt
 vcfAnnoGnomadExomesConf,${projectPrefix}.batch-${batchID}.conf.gnomad.exomes.txt
 projectBatchGenotypedAnnotatedVariantCalls,${projectPrefix}.batch-${batchID}.variant.calls.genotyped.annotated.vcf
-toCADD,${projectPrefix}.batch-${batchID}.toCadd.tsv
-fromCADD,${projectPrefix}.batch-${batchID}.fromCadd.tsv.gz
+toCADD,${projectPrefix}.batch-${batchID}.toCadd.vcf
+fromCADD,${projectPrefix}.batch-${batchID}.fromCadd.vcf.gz
 fromCADDMerged,${projectPrefix}.batch-${batchID}.fromCadd.merged.vcf
 
 
@@ -402,7 +402,7 @@ manVarListMVL_LB_B,${manVarListDir}/MVL_2018-06-27_LB-B.bed
 manVarListMVL_VUS_LP_P,${manVarListDir}/MVL_2018-06-27_VUS-LP-P.bed
 manVarListVKGL_consensus_VUS_LP_P,${manVarListDir}/VKGL_consensus_2018-06-27_VUS-LP-P.bed
 
-vcfPedVersion,VCFped/20180527_d1bbdf5-${toolChain}-Python-2.7.11
+vcfPedVersion,VCFped/20180527_d1bbdf5-${toolChain_max}-Python-2.7.16
 cgdDataDir,${dataDir}/CGD/
 projectBatchGenotypedCGDAnnotatedVariantCalls,${projectPrefix}.batch-${batchID}.variant.calls.genotyped.cgd.annotated.vcf
 cgdFile,${cgdDataDir}/CGD_perPosition.bed.gz 

protocols/AnnotateVcf.sh

@@ -13,6 +13,7 @@
 #string fromCADDMerged
 #string vcfAnnoConf
 #string caddVersion
+#string vepAssemblyVersion
 #string exacAnnotation
 #string gonlAnnotation
 #string gnomADGenomesAnnotation
@@ -48,10 +49,9 @@ then
 	bcftools norm -f "${indexFile}" -m -any "${projectBatchGenotypedVariantCalls}" | awk '{if (!/^#/){if (length($4) > 1 || length($5) > 1){print $1"\t"$2"\t"$3"\t"$4"\t"$5}}}' | bgzip -c > "${toCADD}.gz"
 
 	echo "starting to get CADD annotations locally for ${toCADD}.gz"
-	score.sh "${toCADD}.gz" "${fromCADD}"
+	CADD.sh -g "${vepAssemblyVersion}" "${toCADD}.gz" "${fromCADD}"
 
-	echo "convert fromCADD tsv file to fromCADD vcf"
-	##convert tsv to vcf
+	echo "convert fromCADD vcf file to fromCADD vcf"
 	(echo -e '##fileformat=VCFv4.1\n##INFO=<ID=raw,Number=A,Type=Float,Description="raw cadd score">\n##INFO=<ID=phred,Number=A,Type=Float,Description="phred-scaled cadd score">\n##CADDCOMMENT=<ID=comment,comment="CADD v1.3 (c) University of Washington and Hudson-Alpha Institute for Biotechnology 2013-2015. All rights reserved.">\n#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO' && gzip -dc ${fromCADD}\
 	| awk '{if(NR>2){ printf $1"\t"$2"\t.\t"$3"\t"$4"\t1\tPASS\traw="; printf "%0.1f;",$5 ;printf "phred=";printf "%0.1f\n",$6}}') | bgzip -c > "${fromCADD}.vcf.gz"
 

protocols/CreateInhouseProjects.sh

@@ -248,8 +248,8 @@ sh "${EBROOTMOLGENISMINCOMPUTE}/molgenis_compute.sh" \
 -p "resources_parameters.converted.csv" \
 -p "${tmpdir_parameters}" \
 -rundir "${projectJobsDir}" \
---header "${EBROOTNGS_DNA}/templates/slurm/header_tnt.ftl" \
---footer "${EBROOTNGS_DNA}/templates/slurm/footer_tnt.ftl" \
+--header "${EBROOTNGS_DNA}/templates/slurm/header.ftl" \
+--footer "${EBROOTNGS_DNA}/templates/slurm/footer.ftl" \
 --submit "${EBROOTNGS_DNA}/templates/slurm/submit.ftl" \
 -w "${workflowpath}" \
 -b slurm \

protocols/DetermineTrio.sh

@@ -6,6 +6,7 @@
 #string intermediateDir
 #string projectFinalVcf
 #string projectPrefix
+#string whichSex
 
 module load "${vcfPedVersion}"
 
@@ -52,7 +53,7 @@ then
 			while read line
 			do
 				printf "${line} "
-				if [ $(tail -1 "${intermediateDir}/${line}.chosenSex.txt") == "Female" ]
+				if [ $(tail -1 "${whichSex}") == "Female" ]
 				then
 					echo "Mother"
 				else

protocols/GenderCheck.sh

@@ -32,9 +32,9 @@ else
 	#select only the mean target coverage of the whole genome file
 	awk '{
 		if ($0 ~ /^#/){}
-		else if ($40 == ""){}
-		else if ($40 == "MEAN_TARGET_COVERAGE"){}
-		else {print $40}
+		else if ($34 == ""){}
+		else if ($34 == "MEAN_TARGET_COVERAGE"){}
+		else {print $34}
 		}' "${dedupBamMetrics}.hs_metrics" >> "${checkSexMeanCoverage}"
 
 
@@ -55,9 +55,9 @@ else
 		#select only the mean target coverage of chromosome X
 		awk '{
 			if ($0 ~ /^#/){}
-			else if ($40 == ""){}
-			else if ($40 == "MEAN_TARGET_COVERAGE"){}
-			else {print $40}
+			else if ($34 == ""){}
+			else if ($34 == "MEAN_TARGET_COVERAGE"){}
+			else {print $34}
 			}' "${hsMetricsNonAutosomalRegionChrX}" >> "${checkSexMeanCoverage}"
 
 

protocols/Manta.sh

@@ -8,7 +8,6 @@
 #string dedupBam
 #string mantaDir
 #string mantaVersion
-#string python2Version
 #string capturingKit
 #string capturedBed
 #string bedToolsVersion

protocols/MultiQC.sh

@@ -25,8 +25,6 @@
 #string plink2Version
 #string plinkSeqVersion
 #string picardVersion
-#string python2Version
-#string python3Version
 #string rVersion
 #string sambambaVersion
 #string samtoolsVersion
@@ -77,8 +75,6 @@ echo -e "report_header_info:
     - '': '${plink2Version}'
     - '': '${plinkSeqVersion}'
     - '': '${picardVersion}'
-    - '': '${python2Version}'
-    - '': '${python3Version}'
     - '': '${rVersion}'
     - '': '${sambambaVersion}'
     - '': '${samtoolsVersion}'

templates/generate_template.sh

@@ -1,4 +1,11 @@
 #!/bin/bash
+if module list | grep -o -P 'NGS_DNA(.+)' 
+then
+	echo "DNA pipeline loaded, proceding"
+else
+	echo "No DNA Pipeline loaded, exiting"
+	exit 1
+fi
 
 module list