!/bin/bash

export SV_DIR=/work/SoftW/svtoolkit
runDir=IEMS
SV_TMPDIR=IEMS/tmpdir_SVDiscovery
inputFile=IEMS.list
sites=IEMS.discovery.vcf
genotypes=IEMS.genotypes.vcf

These executables must be on your path.

which java > /dev/null || exit 1
which Rscript > /dev/null || exit 1
which samtools > /dev/null || exit 1

For SVAltAlign, you must use the version of bwa compatible with Genome STRiP.

export PATH=${SV_DIR}/bwa:${PATH}
export LD_LIBRARY_PATH=${SV_DIR}/bwa:${LD_LIBRARY_PATH}

mx="-Xmx4g"
classpath="${SV_DIR}/lib/SVToolkit.jar:${SV_DIR}/lib/gatk/GenomeAnalysisTK.jar:${SV_DIR}/lib/gatk/Queue.jar"

mkdir -p ${runDir}/logs || exit 1
mkdir -p ${runDir}/metadata || exit 1

Run discovery.

java -cp ${classpath} ${mx} \
org.broadinstitute.gatk.queue.QCommandLine \
-cp ${classpath} \
-S ${SV_DIR}/qscript/SVDiscovery.q \
-S ${SV_DIR}/qscript/SVQScript.q \
-gatk ${SV_DIR}/lib/gatk/GenomeAnalysisTK.jar \
--disableJobReport \
-configFile conf/genstrip_parameters.txt \
-tempDir ${SV_TMPDIR} \
-R /work/wsh/0.Pipeline/TargetSeq/Genome_STRiP_ref/Homo_sapiens_assembly19.fasta \
-genomeMaskFile /work/wsh/0.Pipeline/TargetSeq/Genome_STRiP_ref/Homo_sapiens_assembly19.svmask.fasta \
-runDirectory ${runDir} \
-md ${runDir}/metadata \
-genderMapFile IEMS_gender.map \
-disableGATKTraversal \
-jobLogDir ${runDir}/logs \
-suppressVCFCommandLines \
-sample IEMS_sample.list \
-minimumSize 100 \
-maximumSize 1000000 \
-I ${inputFile} \
-O ${sites} \
-run

#

And the error is:

INFO 16:44:56,231 HelpFormatter - -----------------------------------------------------------------------------------------
INFO 16:44:56,234 HelpFormatter - The Genome Analysis Toolkit (GATK) v3.7.GS-r1748-0-g74bfe0b, Compiled 2017/10/06 08:08:49
INFO 16:44:56,234 HelpFormatter - Copyright (c) 2010-2016 The Broad Institute
INFO 16:44:56,234 HelpFormatter - For support and documentation go to https://software.broadinstitute.org/gatk
INFO 16:44:56,234 HelpFormatter - [Fri Jan 26 16:44:56 CST 2018] Executing on Linux 2.6.32-696.6.3.el6.x86_64 amd64
INFO 16:44:56,234 HelpFormatter - Java HotSpot(TM) 64-Bit Server VM 1.8.0_141-b15
INFO 16:44:56,240 HelpFormatter - Program Args: -T SVDiscoveryWalker -R /work/wsh/0.Pipeline/TargetSeq/Genome_STRiP_ref/Homo_sapiens_assembly19.fasta -O /work1/wsh/4.test/1.perl/1.pipetest/IEMS/IEMS/P0001.discovery.vcf.gz -disableGATKTraversal true -md IEMS/metadata -configFile conf/genstrip_parameters.txt -runDirectory IEMS -genderMapFile IEMS_gender.map -genomeMaskFile /work/wsh/0.Pipeline/TargetSeq/Genome_STRiP_ref/Homo_sapiens_assembly19.svmask.fasta -partitionName P0001 -runFilePrefix P0001 -storeReadPairFile true -L 1:1-249250621 -searchLocus 1:1-249250621 -searchWindow 1:1-249250621 -searchMinimumSize 100 -searchMaximumSize 1000000
INFO 16:44:56,241 HelpFormatter - Executing as wsh@localhost on Linux 2.6.32-696.6.3.el6.x86_64 amd64; Java HotSpot(TM) 64-Bit Server VM 1.8.0_141-b15.
INFO 16:44:56,241 HelpFormatter - Date/Time: 2018/01/26 16:44:56
INFO 16:44:56,241 HelpFormatter - -----------------------------------------------------------------------------------------
INFO 16:44:56,242 HelpFormatter - -----------------------------------------------------------------------------------------
INFO 16:44:56,247 26-Jan-2018 GenomeAnalysisEngine - Strictness is SILENT
INFO 16:44:56,385 26-Jan-2018 GenomeAnalysisEngine - Downsampling Settings: No downsampling
INFO 16:44:56,408 26-Jan-2018 IntervalUtils - Processing 249250621 bp from intervals
INFO 16:44:56,461 26-Jan-2018 GenomeAnalysisEngine - Preparing for traversal
INFO 16:44:56,466 26-Jan-2018 GenomeAnalysisEngine - Done preparing for traversal
INFO 16:44:56,466 26-Jan-2018 ProgressMeter - [INITIALIZATION COMPLETE; STARTING PROCESSING]
INFO 16:44:56,466 26-Jan-2018 ProgressMeter - | processed | time | per 1M | | total | remaining
INFO 16:44:56,466 26-Jan-2018 ProgressMeter - Location | reads | elapsed | reads | completed | runtime | runtime
INFO 16:44:56,466 26-Jan-2018 SVDiscovery - Initializing SVDiscovery ...
INFO 16:44:56,467 26-Jan-2018 SVDiscovery - Reading configuration file ...
INFO 16:44:56,470 26-Jan-2018 SVDiscovery - Read configuration file.
INFO 16:44:56,470 26-Jan-2018 SVDiscovery - Opening reference sequence ...
INFO 16:44:56,470 26-Jan-2018 SVDiscovery - Opened reference sequence.
INFO 16:44:56,470 26-Jan-2018 SVDiscovery - Opening genome mask ...
INFO 16:44:56,471 26-Jan-2018 SVDiscovery - Opened genome mask.
INFO 16:44:56,471 26-Jan-2018 SVDiscovery - Initializing input data set ...
INFO 16:44:56,741 26-Jan-2018 SVDiscovery - Initialized data set: 25 files, 25 read groups, 25 samples.
INFO 16:44:56,743 26-Jan-2018 MetaData - Opening metadata ...
INFO 16:44:56,743 26-Jan-2018 MetaData - Adding metadata location IEMS/metadata ...
INFO 16:44:56,744 26-Jan-2018 MetaData - Opened metadata.
INFO 16:44:56,746 26-Jan-2018 SVDiscovery - Opened metadata.
INFO 16:44:56,750 26-Jan-2018 MetaData - Loading insert size histograms ...
INFO 16:44:56,858 26-Jan-2018 SVDiscovery - Processing locus: 1:1-249250621:100-1000000
INFO 16:44:56,858 26-Jan-2018 SVDiscovery - Locus search window: 1:1-249250621
INFO 16:45:26,469 26-Jan-2018 ProgressMeter - Starting 0.0 30.0 s 49.6 w 100.0% 30.0 s 0.0 s
INFO 16:45:27,838 26-Jan-2018 SVDiscovery - Discovery alt home filtering is disabled.
INFO 16:45:27,981 26-Jan-2018 SVDiscovery - Processing clusters ...

ERROR --

ERROR stack trace

java.lang.NullPointerException
at org.broadinstitute.sv.metadata.MetaData.computeSampleLongMap(MetaData.java:406)
at org.broadinstitute.sv.metadata.MetaData.getSampleReadSpanMap(MetaData.java:401)
at org.broadinstitute.sv.discovery.ClusterMembershipModule.init(ClusterMembershipModule.java:155)
at org.broadinstitute.sv.discovery.DeletionDiscoveryAlgorithm.createMembershipModule(DeletionDiscoveryAlgorithm.java:1110)
at org.broadinstitute.sv.discovery.DeletionDiscoveryAlgorithm.initClusterModules(DeletionDiscoveryAlgorithm.java:1055)
at org.broadinstitute.sv.discovery.DeletionDiscoveryAlgorithm.processClusters(DeletionDiscoveryAlgorithm.java:386)
at org.broadinstitute.sv.discovery.DeletionDiscoveryAlgorithm.runDiscovery(DeletionDiscoveryAlgorithm.java:204)
at org.broadinstitute.sv.discovery.SVDiscoveryWalker.onTraversalDone(SVDiscoveryWalker.java:107)
at org.broadinstitute.sv.discovery.SVDiscoveryWalker.onTraversalDone(SVDiscoveryWalker.java:40)
at org.broadinstitute.gatk.engine.executive.Accumulator$StandardAccumulator.finishTraversal(Accumulator.java:129)
at org.broadinstitute.gatk.engine.executive.LinearMicroScheduler.execute(LinearMicroScheduler.java:115)
at org.broadinstitute.gatk.engine.GenomeAnalysisEngine.execute(GenomeAnalysisEngine.java:316)
at org.broadinstitute.gatk.engine.CommandLineExecutable.execute(CommandLineExecutable.java:123)
at org.broadinstitute.sv.main.SVCommandLine.execute(SVCommandLine.java:133)
at org.broadinstitute.gatk.utils.commandline.CommandLineProgram.start(CommandLineProgram.java:256)
at org.broadinstitute.gatk.utils.commandline.CommandLineProgram.start(CommandLineProgram.java:158)
at org.broadinstitute.sv.main.SVCommandLine.main(SVCommandLine.java:87)
at org.broadinstitute.sv.main.SVDiscovery.main(SVDiscovery.java:21)

ERROR ------------------------------------------------------------------------------------------

ERROR A GATK RUNTIME ERROR has occurred (version 3.7.GS-r1748-0-g74bfe0b):

ERROR

ERROR This might be a bug. Please check the documentation guide to see if this is a known problem.

ERROR If not, please post the error message, with stack trace, to the GATK forum.

ERROR Visit our website and forum for extensive documentation and answers to

ERROR commonly asked questions https://software.broadinstitute.org/gatk

ERROR

ERROR MESSAGE: Code exception (see stack trace for error itself)

ERROR ------------------------------------------------------------------------------------------

#

Can anyone help me? Thank you very much!