Merge pull request #458 from RoanKanninga/3.2.3

fix VariantCalling for Unknown genders + bugfixing
molgenis · Mar 11, 2016 · d217ec7 · d217ec7
2 parents 6e55bc0 + 568aa88
commit d217ec7
Show file tree

Hide file tree

Showing 4 changed files with 20 additions and 19 deletions.
diff --git a/compute5/NGS_DNA/protocols/CheckIlluminaEncoding.sh b/compute5/NGS_DNA/protocols/CheckIlluminaEncoding.sh
@@ -16,7 +16,7 @@ checkIlluminaEncoding() {
 barcodeFqGz=$1
 echo ${barcodeFqGz}
 
-lines=(`zcat ${barcodeFqGz} | head -96 | awk 'NR % 4 == 0'`)
+lines=(`zcat ${barcodeFqGz} | head -8000 | tail -192 | awk 'NR % 4 == 0'`)
 count=1
 nodecision=0
 numberoflines=0
@@ -80,7 +80,7 @@ else
         gzip -d -c ${barcodeFqGz} > ${barcodeFqGz}.fq
 	mkdir -p ${projectRawTmpDataDir}/IlluminaEncoding1.5
         mv ${barcodeFqGz} ${projectRawTmpDataDir}/IlluminaEncoding1.5/
-
+	echo "start encoding for ${barcodeFqGz}.fq"
         #convert Phreds+64 to Phred+33 (Illumna 1.5 TO Illumina / Sanger 1.9)
         sed -e '4~4y/@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghi/!"#$%&'\''()*+,-.\/0123456789:;<=>?@ABCDEFGHIJ/' ${barcodeFqGz}.fq > ${barcodeFqGz}.fq.encoded
         gzip ${barcodeFqGz}.fq.encoded

diff --git a/compute5/NGS_DNA/protocols/CreateExternSamplesProjects.sh b/compute5/NGS_DNA/protocols/CreateExternSamplesProjects.sh
@@ -16,7 +16,8 @@
 #list sequencer
 #list run
 #list flowcell
-#list externalFastQ
+#list externalFastQ_1
+#list externalFastQ_2
 
 #string mainParameters
 #string worksheet 
@@ -64,25 +65,25 @@ do
 	then
   		if [[ ${barcode[samplenumber]} == "None" ]]
 		then
-			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz
-			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz.md5
+			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]} ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz
+			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]}.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz.md5
   		else
-      			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz
-      			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz.md5
+      			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]} ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz
+      			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]}.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}.fq.gz.md5
 		fi
 	elif [[ ${seqType[samplenumber]} == "PE" ]]
 	then
 		if [[ ${barcode[samplenumber]} == "None" ]]
     		then
-    			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_1.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz
-			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_2.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.gz
-			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_1.fq.gz.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz.md5
-        		ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_2.fq.gz.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.gz.md5
+    			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]} ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz
+			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_2[samplenumber]} ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.gz
+			ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]}.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz.md5
+        		ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_2[samplenumber]}.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.gz.md5
 		else          
-        		ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_1.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz
-        		ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_2.fq.gz ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.gz
-        		ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_1.fq.gz.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz.md5
-        		ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ[samplenumber]}_2.fq.gz.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.md5
+        		ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]} ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz
+        		ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_2[samplenumber]} ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.gz
+        		ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_1[samplenumber]}.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_1.fq.gz.md5
+        		ln -sf ../../../../../rawdata/ngs/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}/${externalFastQ_2[samplenumber]}.md5 ${projectRawTmpDataDir}/${sequencingStartDate[samplenumber]}_${sequencer[samplenumber]}_${run[samplenumber]}_${flowcell[samplenumber]}_L${lane[samplenumber]}_${barcode[samplenumber]}_2.fq.md5
     		fi
  	fi
 done
@@ -91,7 +92,7 @@ cd $ROCKETPOINT
 
 echo "before splitting"
 echo `pwd`
-module load NGS_DNA/$ngsversion
+module load $ngsversion
 module load ${ngsUtilsVersion}
 
 #
@@ -118,7 +119,7 @@ echo "before run second rocket"
 echo pwd
 
 sh ${EBROOTMOLGENISMINCOMPUTE}/molgenis_compute.sh -p ${mainParameters} \
--p environment_parameters \
+-p ${environment_parameters} \
 -p ${batchIDList} \
 -p ${projectJobsDir}/${project}.csv \
 -rundir ${projectJobsDir} \

diff --git a/compute5/NGS_DNA/protocols/VariantGVCFCalling.sh b/compute5/NGS_DNA/protocols/VariantGVCFCalling.sh
@@ -124,7 +124,7 @@ else
 	elif [[ "${capturedBatchBed}" == *batch-[0-9]*Y.bed ]]
 	then
 		echo "Y"
-		if [ "${sex}" == "Female" ]
+		if [[ "${sex}" == "Female" || "${sex}" == "Unknown" ]]
         	then
 			java -Xmx12g -XX:ParallelGCThreads=2 -Djava.io.tmpdir=${tempDir} -jar \
                         ${EBROOTGATK}/${gatkJar} \

diff --git a/compute5/NGS_DNA/samplesize.sh b/compute5/NGS_DNA/samplesize.sh
@@ -11,5 +11,5 @@ do
 	count=$((count + 1))
 done
 
-cat $DIR/countRows.txt | uniq | wc -l
+cat $DIR/countRows.txt | sort-V | uniq | wc -l
 rm $DIR/countRows.txt