From 6dd9a635fd48eb6897a6213c37c66fd81faa1f2e Mon Sep 17 00:00:00 2001
From: RoanKanninga <roankanninga@gmail.com>
Date: Wed, 29 Nov 2023 16:49:14 +0100
Subject: [PATCH 1/2] added new script for many-to-many manual
 concordanceChecks

---
 bin/concordanceCheck-ManyToManyVCFs.sh | 100 +++++++++++++++++++++++++
 1 file changed, 100 insertions(+)
 create mode 100644 bin/concordanceCheck-ManyToManyVCFs.sh

diff --git a/bin/concordanceCheck-ManyToManyVCFs.sh b/bin/concordanceCheck-ManyToManyVCFs.sh
new file mode 100644
index 0000000..b0b2f86
--- /dev/null
+++ b/bin/concordanceCheck-ManyToManyVCFs.sh
@@ -0,0 +1,100 @@
+set -eu
+
+function showHelp() {
+	#
+	# Display commandline help on STDOUT.
+	#
+	cat <<EOH
+===============================================================================================================
+Script to do (many-to-many) ConcordanceChecks manually.
+Usage:
+	$(basename $0) OPTIONS
+Options:
+	-h   Show this help.
+	-i   folder with index samples
+	-c   folder with the compareWith samples
+	-d   dataType. DRAGEN or nonDRAGEN (default) DRAGEN outputdata contains only familyNumber+umcgnumber as the samplename in the header of the vcf
+	-w   working directory (default=current dir)
+===============================================================================================================
+EOH
+	trap - EXIT
+	exit 0
+}
+
+while getopts "w:i:c:d:h" opt;
+do
+	case $opt in h)showHelp;; i)indexFolder="${OPTARG}";; c)compareWithFolder="${OPTARG}";; d)data="${OPTARG}";; w)workDir="${OPTARG}";;
+	esac
+done
+
+if [[ -z "${indexFolder:-}" ]]
+then
+	echo -e '\nERROR: Must specify an indexFolder!\n'
+
+	showHelp
+	exit 1
+fi
+
+if [[ -z "${compareWithFolder:-}" ]]
+then
+	echo -e '\nERROR: Must specify an compareWithFolder!\n'
+
+	showHelp
+	exit 1
+fi
+
+if [[ -z "${data:-}" ]]
+then
+	data="nonDRAGEN"
+fi
+if [[ -z "${workDir:-}" ]]
+then
+	workDir="$(pwd)"
+fi
+
+ml CompareGenotypeCalls
+
+
+tmpDir="${workDir}/tmp"
+mkdir -p "${tmpDir}"
+mkdir -p "${workDir}/samplesheet/"
+mkdir -p "${workDir}/output"
+for compare in "${compareWithFolder}/"*".gz"
+do
+	compareWithSampleName=$(basename "${compare}")
+	if [[ "${data}" == 'DRAGEN' ]]
+	then
+		compareWithSampleName=$(echo "${compareWithSampleName}" | awk 'BEGIN {FS="_"}{print $1"_"$2}')
+	else
+		compareWithSampleName=${compareWithSampleName%%.*}
+	fi
+
+	for index in "${indexFolder}/"*".gz"
+	do
+		indexSampleName=$(basename "${index}")
+		if [[ "${data}" == 'DRAGEN' ]]
+		then
+			indexSampleName=$(echo "${indexSampleName}" | awk 'BEGIN {FS="_"}{print $1"_"$2}')
+		else
+			indexSampleName=${indexSampleName%%.*}
+		fi
+
+
+		## create samplesheet 
+		sampleSheet="${workDir}/samplesheet/${indexSampleName}_${compareWithSampleName}.sampleId.txt"
+		echo -e "data1Id\tdata2Id\tlocation1\tlocation2" > "${sampleSheet}"
+		echo -e "${indexSampleName}\t${compareWithSampleName}\t${index}\t${compare}" >> "${sampleSheet}"
+
+		java -XX:ParallelGCThreads=1 -Djava.io.tmpdir="${tmpDir}" -Xmx9g -jar ${EBROOTCOMPAREGENOTYPECALLS}/CompareGenotypeCalls.jar \
+		-d1 "${index}" \
+		-D1 VCF \
+		-d2 "${compare}" \
+		-D2 VCF \
+		-ac \
+		--sampleMap "${sampleSheet}" \
+		-o "${workDir}/output/${indexSampleName}_${compareWithSampleName}" \
+		-sva
+
+		echo "${indexSampleName}_${compareWithSampleName} done: output/${indexSampleName}_${compareWithSampleName}"
+	done
+done

From df2b7361ff47d006df8d16bf420c83a45ddfd883 Mon Sep 17 00:00:00 2001
From: RoanKanninga <roankanninga@gmail.com>
Date: Thu, 30 Nov 2023 10:58:26 +0100
Subject: [PATCH 2/2] added missing quotes

---
 bin/concordanceCheck-ManyToManyVCFs.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/bin/concordanceCheck-ManyToManyVCFs.sh b/bin/concordanceCheck-ManyToManyVCFs.sh
index b0b2f86..ceb61eb 100644
--- a/bin/concordanceCheck-ManyToManyVCFs.sh
+++ b/bin/concordanceCheck-ManyToManyVCFs.sh
@@ -66,7 +66,7 @@ do
 	then
 		compareWithSampleName=$(echo "${compareWithSampleName}" | awk 'BEGIN {FS="_"}{print $1"_"$2}')
 	else
-		compareWithSampleName=${compareWithSampleName%%.*}
+		compareWithSampleName="${compareWithSampleName%%.*}"
 	fi
 
 	for index in "${indexFolder}/"*".gz"
@@ -76,7 +76,7 @@ do
 		then
 			indexSampleName=$(echo "${indexSampleName}" | awk 'BEGIN {FS="_"}{print $1"_"$2}')
 		else
-			indexSampleName=${indexSampleName%%.*}
+			indexSampleName="${indexSampleName%%.*}"
 		fi
 
 
@@ -85,7 +85,7 @@ do
 		echo -e "data1Id\tdata2Id\tlocation1\tlocation2" > "${sampleSheet}"
 		echo -e "${indexSampleName}\t${compareWithSampleName}\t${index}\t${compare}" >> "${sampleSheet}"
 
-		java -XX:ParallelGCThreads=1 -Djava.io.tmpdir="${tmpDir}" -Xmx9g -jar ${EBROOTCOMPAREGENOTYPECALLS}/CompareGenotypeCalls.jar \
+		java -XX:ParallelGCThreads=1 -Djava.io.tmpdir="${tmpDir}" -Xmx9g -jar "${EBROOTCOMPAREGENOTYPECALLS}/CompareGenotypeCalls.jar" \
 		-d1 "${index}" \
 		-D1 VCF \
 		-d2 "${compare}" \