Merge pull request #4 from Gerbenvandervries/master

added boxy parameter, fix for environment check

README.md

@@ -1 +1 @@
-# NGS_RNA
+# NGS_RNA 

generate_template.sh

@@ -4,12 +4,11 @@ module load NGS_RNA/3.2.4-Molgenis-Compute-v16.05.1-Java-1.8.0_45
 module list
 
 HOST=$(hostname)
-##Running script for checking the environment variables
-sh ${EBROOTNGS_RNA}/checkEnvironment.sh ${HOST}
+thisDir=$(pwd)
 
-ENVIRONMENT=$(awk '{print $1}' ./environment_checks.txt)
-TMPDIR=$(awk '{print $2}' ./environment_checks.txt)
-GROUP=$(awk '{print $3}' ./environment_checks.txt)
+ENVIRONMENT="parameters.${HOST%%.*}.csv"
+TMPDIRECTORY=$(basename $(cd ../../ && pwd ))
+GROUP=$(basename $(cd ../../../ && pwd ))
 
 PROJECT="PROJECTNAME"
 RUNID="run01"

parameters.boxy.csv

@@ -0,0 +1,8 @@
+#### ENVIRONMENT VARIABLES ####
+queue,gaf
+workDir,/groups/umcg-gaf/
+dataDir,${root}/data/
+tmpName,tmp03
+root,/apps/
+tempDir,${workDir}/${tmpName}/tmp/
+permanentDir,${workDir}/prm03

parameters.csv

@@ -6,18 +6,18 @@ jobname,jobname
 ##### Tools and versions #####
 jdkVersion,Java/1.7.0_80
 NGSUtilsVersion,ngs-utils
-NGSRNAVersion,NGS_RNA/3.2.3-Molgenis-Compute-v16.05.1-Java-1.8.0_45
+NGSRNAVersion,NGS_RNA/3.2.4
 fastqcVersion,FastQC/0.11.3-Java-1.7.0_80
-samtoolsVersion,SAMtools/1.2-goolf-1.7.20
+samtoolsVersion,SAMtools/1.2-foss-2015b
 RVersion,R/3.2.1-goolf-1.7.20
 wkhtmltopdfVersion,wkhtmltopdf/0.11.0_rc1-static-amd64
 picardVersion,picard/1.130-Java-1.7.0_80
 anacondaVersion,Anaconda/1.8.0-Linux-x86_64
 htseqVersion,HTSeq/0.6.1p1
-hisatVersion,hisat/0.1.5-beta-goolf-1.7.20
+hisatVersion,hisat/0.1.5-beta-foss-2015b
 pythonVersion,Python/2.7.9-goolf-1.7.20
-gatkVersion,GATK/3.4-46-Java-1.7.0_80 
-ghostscriptVersion,Ghostscript/9.16-goolf-1.7.20
+gatkVersion,GATK/3.6-Java-1.8.0_74
+ghostscriptVersion,Ghostscript/9.16-foss-2015b
 kallistoVersion,Kallisto/0.43.0-goolf-1.7.20
 BBMapVersion,BBMap/35.69-Java-1.7.0_80
 picardJar,picard.jar

parameters.homo_sapiens.csv

@@ -6,7 +6,7 @@ indexFolderName,human_g1k_v37
 dbSNPFileID,dbsnp_138.${genome}
 indicesDir,${dataDir}/ftp.broadinstitute.org/bundle/2.8/${genome}/
 dbSNPDir,${dataDir}/dbSNP/
-hisatIndex,${dataDir}/ftp.broadinstitute.org/bundle/2.8/${genome}/${hisatVersion}/${indexFolderName}
+hisatIndex,${dataDir}/ftp.broadinstitute.org/bundle/2.8/${genome}/hisat/0.1.5-beta-goolf-1.7.20/${indexFolderName}
 kallistoIndex,${dataDir}/ftp.ensembl.org/pub/release-75/fasta/homo_sapiens/Homo_sapiens.GRCh37.75.cdna.all.fa.idx
 indexFileFastaIndex,${indexSpecies}.fai
 indexSpecies,${indicesDir}/${indexFileID}.fasta

protocols/CreateExternSamplesProjects.sh

@@ -11,6 +11,7 @@
 #string jdkVersion
 #string groupname
 #string NGSUtilsVersion
+#string NGSRNAVersion
 #list sequencingStartDate
 #list sequencer
 #list run
@@ -36,7 +37,7 @@
 
 umask 0007
 module load Molgenis-Compute/${computeVersion}
-module load ngs-utils/16.09.1
+module load ${NGSUtilsVersion}
 
 module list
 #
@@ -96,7 +97,7 @@ cd $ROCKETPOINT
 
 echo "before splitting"
 echo `pwd`
-module load ${ngsUtilsVersion}
+module load ${NGSRNAVersion}
 
 #
 # TODO: array for each sample:

protocols/HisatAlignment.sh

@@ -54,9 +54,6 @@ tmpSortedBai=${MC_tmpFile}
 
 #Load modules
 ${stage} ${hisatVersion}
-${stage} ${samtoolsVersion}
-${stage} ${picardVersion}
-
 #check modules
 ${checkStage}
 
@@ -75,6 +72,11 @@ echo "## "$(date)" Start $0"
 	perl -nle 'print $2,"|\t",$1 while (m%^[ ]*([.0-9\%]+\s\(.+\)|[.0-9\%]+).(.+)%g);' ${intermediateDir}/${externalSampleID}_L${lane}.hisat.log > ${intermediateDir}/${externalSampleID}_L${lane}.hisat.final.log
 
 
+${stage} ${picardVersion}
+
+#check modules
+${checkStage}
+
 java -XX:ParallelGCThreads=4 -jar -Xmx6g ${EBROOTPICARD}/${picardJar} SortSam \
 	INPUT=${tmpAlignedSam} \
 	OUTPUT=${tmpSortedBam} \

test/autotest_generate_template.sh

@@ -60,7 +60,7 @@ sh ${EBROOTMOLGENISMINCOMPUTE}/molgenis_compute.sh \
 -o "workflowpath=${WORKFLOW};outputdir=scripts/jobs;\
 groupname=${GROUP};\
 mainParameters=${WORKDIR}/generatedscripts/${PROJECT}/parameters.csv;\
-ngsversion='NGS_RNA/3.2.4-Molgenis-Compute-v16.05.1-Java-1.8.0_45';\
+ngsversion='NGS_RNA/3.2.4';\
 worksheet=${WORKDIR}/generatedscripts/${PROJECT}/${PROJECT}.csv;\
 parameters_build=${WORKDIR}/generatedscripts/${PROJECT}/parameters.${BUILD}.csv;\
 parameters_species=${WORKDIR}/generatedscripts/${PROJECT}/parameters.${SPECIES}.csv;\

workflow_lexogen.csv

@@ -2,6 +2,7 @@ step,protocol,dependencies
 s00_TrimReads,protocols/TrimReads.sh,
 s01_FastQC,protocols/FastQC.sh,s00_TrimReads
 s02_HisatAlignment,protocols/HisatAlignment.sh,s00_TrimReads
+s02_AddOrReplaceReadGroups,protocols/AddOrReplaceReadGroups.sh,s02_HisatAlignment
 s03_MergeBam,protocols/MergeBam.sh,s02_HisatAlignment
 s04_MarkDuplicates,protocols/MarkDuplicates.sh,s03_MergeBam
 s05_QCStats,protocols/QCStats.sh,s04_MarkDuplicates