Merge pull request #236 from npklein/master

Make PROseq pipeline folder

compute5/PROseq/protocols/AddOrReplaceReadGroups.sh

@@ -0,0 +1,66 @@
+#MOLGENIS walltime=23:59:00 mem=6gb nodes=1 ppn=4
+
+#Parameter mapping  #why not string foo,bar? instead of string foo\nstring bar
+#string stage
+#string checkStage
+#string starVersion
+#string WORKDIR
+#string projectDir
+
+#string picardVersion
+#string starAlignmentPassTwoDir
+#string sampleName
+#string internalId
+
+
+#string addOrReplaceGroupsDir
+#string addOrReplaceGroupsBam
+#string addOrReplaceGroupsBai
+
+
+
+echo "## "$(date)" ##  $0 Started "
+
+getFile ${starAlignmentPassTwoDir}/Aligned.out.sam
+
+${stage} picard-tools/${picardVersion}
+${checkStage}
+
+set -x
+set -e
+
+mkdir -p ${addOrReplaceGroupsDir}
+
+echo "## "$(date)" Start $0"
+
+if java -Xmx6g -XX:ParallelGCThreads=4 -jar $PICARD_HOME/AddOrReplaceReadGroups.jar \
+ INPUT=${starAlignmentPassTwoDir}/Aligned.out.sam \
+ OUTPUT=${addOrReplaceGroupsBam} \
+ SORT_ORDER=coordinate \
+ RGID=${internalId} \
+ RGLB=${sampleName}_${internalId} \
+ RGPL=ILLUMINA \
+ RGPU=${sampleName}_${internalId}_${internalId} \
+ RGSM=${sampleName} \
+ RGDT=$(date --rfc-3339=date) \
+ CREATE_INDEX=true \
+ MAX_RECORDS_IN_RAM=4000000 \
+ TMP_DIR=${addOrReplaceGroupsDir} \
+
+then
+ echo "returncode: $?"; 
+
+ putFile ${addOrReplaceGroupsBam}
+ putFile ${addOrReplaceGroupsBai}
+
+ echo "succes moving files";
+else
+ echo "returncode: $?";
+ echo "fail";
+fi
+
+echo "## "$(date)" ##  $0 Done "
+
+
+
+echo "## "$(date)" ##  $0 Done "

compute5/PROseq/protocols/CollectMultipleMetrics.sh

@@ -0,0 +1,65 @@
+#MOLGENIS walltime=23:59:00 mem=4gb nodes=1 ppn=4
+
+#string stage
+#string checkStage
+#string picardVersion
+#string RVersion
+#string reads2FqGz
+#string collectMultipleMetricsDir
+#string collectMultipleMetricsPrefix
+#string onekgGenomeFasta
+#string sortedBam
+#string sortedBai
+#string toolDir
+
+
+getFile ${sortedBam}
+getFile ${sortedBai}
+getFile ${onekgGenomeFasta}
+
+
+#load modules
+${stage} picard/${picardVersion}
+
+#Check modules
+${checkStage}
+
+mkdir -p ${collectMultipleMetricsDir}_QC
+
+echo "## "$(date)" Start $0"
+
+insertSizeMetrics=""
+if [ ${#reads2FqGz} -ne 0 ]; then
+	insertSizeMetrics="PROGRAM=CollectInsertSizeMetrics"
+fi
+
+#Run Picard CollectAlignmentSummaryMetrics, CollectInsertSizeMetrics, QualityScoreDistribution and MeanQualityByCycle
+if java -jar -Xmx4g -XX:ParallelGCThreads=4 ${toolDir}picard/${picardVersion}/CollectMultipleMetrics.jar \
+ I=${sortedBam} \
+ O=${collectMultipleMetricsPrefix} \
+ R=${onekgGenomeFasta} \
+ PROGRAM=CollectAlignmentSummaryMetrics \
+ PROGRAM=QualityScoreDistribution \
+ PROGRAM=MeanQualityByCycle \
+ $insertSizeMetrics \
+ TMP_DIR=${collectMultipleMetricsDir}
+then
+ echo "returncode: $?";
+ putFile ${collectMultipleMetricsPrefix}.alignment_summary_metrics
+ putFile ${collectMultipleMetricsPrefix}.quality_by_cycle_metrics
+ putFile ${collectMultipleMetricsPrefix}.quality_by_cycle.pdf
+ putFile ${collectMultipleMetricsPrefix}.quality_distribution_metrics
+ putFile ${collectMultipleMetricsPrefix}.quality_distribution.pdf
+
+ if [ ${#reads2FqGz} -ne 0 ]; then
+   putFile ${collectMultipleMetricsPrefix}.insert_size_histogram.pdf
+   putFile ${collectMultipleMetricsPrefix}.insert_size_metrics
+ fi
+  echo "succes moving files";
+else
+ echo "returncode: $?";
+ echo "fail";
+fi
+
+
+echo "## "$(date)" ##  $0 Done "

compute5/PROseq/protocols/CollectRnaSeqMetrics.sh

@@ -0,0 +1,54 @@
+#MOLGENIS walltime=23:59:00 mem=8gb nodes=1 ppn=4
+
+#string stage
+#string checkStage
+#string picardVersion
+#string sortedBam
+#string sortedBai
+#string collectRnaSeqMetricsDir
+#string collectRnaSeqMetrics
+#string collectRnaSeqMetricsChart
+#string genesRefFlat
+#string rRnaIntervalList
+#string onekgGenomeFasta
+#string toolDir
+#string RVersion
+
+getFile ${sortedBam}
+getFile ${sortedBai}
+
+#Load module
+${stage} picard/${picardVersion}
+${stage} R/${RVersion}
+
+#Check modules
+${checkStage}
+
+mkdir -p ${collectRnaSeqMetricsDir}
+
+echo "## "$(date)" ##  $0 Started "
+
+if java -Xmx8g -XX:ParallelGCThreads=4 -jar ${toolDir}picard/${picardVersion}/CollectRnaSeqMetrics.jar \
+ INPUT=${sortedBam} \
+ OUTPUT=${collectRnaSeqMetrics} \
+ CHART_OUTPUT=${collectRnaSeqMetricsChart} \
+ METRIC_ACCUMULATION_LEVEL=SAMPLE \
+ METRIC_ACCUMULATION_LEVEL=READ_GROUP \
+ REFERENCE_SEQUENCE=${onekgGenomeFasta} \
+ REF_FLAT=${genesRefFlat} \
+ RIBOSOMAL_INTERVALS=${rRnaIntervalList} \
+ STRAND_SPECIFICITY=NONE \
+ TMP_DIR=${collectRnaSeqMetricsDir}
+
+then
+ echo "returncode: $?";
+ putFile ${collectRnaSeqMetrics}
+ putFile ${collectRnaSeqMetricsChart}
+
+ echo "succes moving files";
+else
+ echo "returncode: $?";
+ echo "fail";
+fi
+
+echo "## "$(date)" ##  $0 Done "

compute5/PROseq/protocols/CombineBedFiles.sh

@@ -0,0 +1,58 @@
+#MOLGENIS walltime=23:59:00 mem=6gb ppn=4
+
+#string stage
+#string checkStage
+#string projectDir
+#list genotypeHarminzerOutput
+#string combinedBEDDir
+#string plinkVersion
+#string genotypeHarmonizerDir
+
+
+
+getFile ${genotypeHarminzerOutput}.bed
+getFile ${genotypeHarminzerOutput}.bim
+getFile ${genotypeHarminzerOutput}.fam
+getFile ${genotypeHarminzerOutput}.log
+
+#Load module
+${stage} PLINK/${plinkVersion}
+
+#Check staging of module
+${checkStage}
+
+mkdir -p ${combinedBEDDir}
+
+
+echo "## "$(date)" ##  $0 Started "
+
+{
+echo "$(printf '%s.bed %s.bim %s.fam\n' $(printf '%s\n' ${genotypeHarminzerOutput[@]}) $(printf '%s\n' ${genotypeHarminzerOutput[@]}) $(printf '%s\n' ${genotypeHarminzerOutput[@]}))"
+} > ${combinedBEDDir}combinedFiles.txt.tmp
+# remove first line (e.g. first sample) as this will be used as input for plink
+# to which the other samples will be merged
+sed '1d' ${combinedBEDDir}combinedFiles.txt.tmp > ${combinedBEDDir}combinedFiles.txt
+rm ${combinedBEDDir}combinedFiles.txt.tmp
+
+if plink \
+--bfile ${genotypeHarminzerOutput[0]} \
+--merge-list ${combinedBEDDir}combinedFiles.txt \
+--make-bed \
+--out ${combinedBEDDir}combinedFiles
+
+then
+ echo "returncode: $?";
+ putFile ${combinedBEDDir}combinedFiles.txt
+ putFile ${combinedBEDDir}combinedFiles.log
+ putFile ${combinedBEDDir}combinedFiles.bed
+ putFile ${combinedBEDDir}combinedFiles.bim
+ putFile ${combinedBEDDir}combinedFiles.fam
+ putFile ${combinedBEDDir}combinedFiles.nosex
+
+ echo "succes moving files";
+else
+ echo "returncode: $?";
+ echo "fail";
+fi
+
+echo "## "$(date)" ##  $0 Done "

compute5/PROseq/protocols/Fastqc.sh

@@ -0,0 +1,103 @@
+#MOLGENIS nodes=1 ppn=1 mem=1gb walltime=10:00:00
+
+#string stage
+#string checkStage
+#string fastqcVersion
+#string WORKDIR
+#string projectDir
+#string fastqcDir
+#string fastqcZipExt
+#string pairedEndfastqcZip1
+#string pairedEndfastqcZip2
+#string reads1FqGz
+#string reads2FqGz
+#string sampleName
+
+echo -e "test ${reads1FqGz} ${reads2FqGz} 1: $(basename ${reads1FqGz} .gz)${fastqcZipExt} \n2: $(basename ${reads2FqGz} .gz)${fastqcZipExt} "
+
+${stage} FastQC/${fastqcVersion}
+${checkStage}
+
+set -e
+
+echo "## "$(date)" ##  $0 Started "
+
+if [ ${#reads2FqGz} -eq 0 ]; then
+
+	echo "## "$(date)" Started single end fastqc"
+	alloutputsexist \
+	 ${fastqcDir}/$(basename ${reads1FqGz} .gz)${fastqcZipExt} \
+	 ${singleEndfastqcZip}
+
+	getFile ${reads1FqGz}
+
+	mkdir -p ${fastqcDir}
+	cd ${fastqcDir}
+
+	##################################################################
+	echo
+	echo "## "$(date)" reads1FqGz"
+	if fastqc --noextract ${reads1FqGz} --outdir ${fastqcDir}
+	  echo
+	  cp -v ${fastqcDir}/$(basename ${reads1FqGz} .gz)${fastqcZipExt} ${singleEndfastqcZip}
+
+	  ##################################################################
+
+	  cd $OLDPWD
+    then
+      echo "returncode: $?";
+      putFile ${fastqcDir}/$(basename ${reads1FqGz} .gz)${fastqcZipExt}
+      putFile ${singleEndfastqcZip}
+      echo "succes moving files";
+    else
+      echo "returncode: $?";
+      echo "fail";
+    fi
+
+
+else
+	echo "## "$(date)" Started paired end fastqc"
+
+	alloutputsexist \
+	 ${fastqcDir}/$(basename ${reads1FqGz} .gz)${fastqcZipExt} \
+	 ${fastqcDir}/$(basename ${reads2FqGz} .gz)${fastqcZipExt} \
+	 ${pairedEndfastqcZip1} \
+	 ${pairedEndfastqcZip2}
+
+	getFile ${reads1FqGz}
+	getFile ${reads2FqGz}
+
+	mkdir -p ${fastqcDir}
+	cd ${fastqcDir}
+
+	##################################################################
+	echo
+	echo "## "$(date)" reads1FqGz"
+	if fastqc --noextract ${reads1FqGz} --outdir ${fastqcDir}
+
+	  cp -v ${fastqcDir}/$(basename ${reads1FqGz} .gz)${fastqcZipExt} ${pairedEndfastqcZip1}
+	  echo
+	  echo "## "$(date)" reads2FqGz"
+	  fastqc --noextract ${reads2FqGz} --outdir ${fastqcDir}
+	  echo
+	  cp -v ${fastqcDir}/$(basename ${reads2FqGz} .gz)${fastqcZipExt} ${pairedEndfastqcZip2}
+
+	  ##################################################################
+	  cd $OLDPWD
+
+    then
+      echo "returncode: $?";
+      putFile ${fastqcDir}/$(basename ${reads1FqGz} .gz)${fastqcZipExt}
+      putFile ${fastqcDir}/$(basename ${reads2FqGz} .gz)${fastqcZipExt}
+      putFile ${pairedEndfastqcZip1}
+      putFile ${pairedEndfastqcZip2}
+
+      echo "succes moving files";
+    else
+      echo "returncode: $?";
+      echo "fail";
+    fi
+fi
+
+
+echo "## "$(date)" ##  $0 Done "