本文整理汇总了Python中pymodule.PassingData.trioCallerReplicateConcordanceJob方法的典型用法代码示例。如果您正苦于以下问题:Python PassingData.trioCallerReplicateConcordanceJob方法的具体用法?Python PassingData.trioCallerReplicateConcordanceJob怎么用?Python PassingData.trioCallerReplicateConcordanceJob使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类pymodule.PassingData
的用法示例。
在下文中一共展示了PassingData.trioCallerReplicateConcordanceJob方法的2个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: mapEachInterval
# 需要导入模块: from pymodule import PassingData [as 别名]
# 或者: from pymodule.PassingData import trioCallerReplicateConcordanceJob [as 别名]
#.........这里部分代码省略.........
extraDependentInputLs=None, \
transferOutput=False, \
extraArguments=None, \
job_max_memory=self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=4000, \
minJobPropertyValue=4000, maxJobPropertyValue=9000).value, \
walltime= self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=60, \
minJobPropertyValue=60, maxJobPropertyValue=1200).value,\
)
refineGenotypeOutputF = File(os.path.join(self.mapDirJob.folder, \
'%s.trioCaller.vcf'%(intervalFileBasenamePrefix)))
refineGenotypeJob = self.addTrioCallerJob(trioCallerWrapper=self.trioCallerWrapper, \
trioCallerPath=self.trioCallerPath, \
inputVCF=replicateVCFGenotypeColumnsJob.output,\
pedFile=self.outputReplicatePedigreeJob.output, outputVCF=refineGenotypeOutputF, \
inputPhased=True,\
parentJobLs=[self.mapDirJob, replicateVCFGenotypeColumnsJob, self.outputReplicatePedigreeJob], \
extraDependentInputLs=[], transferOutput=False, \
extraArguments=None, \
job_max_memory = self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=4000, \
minJobPropertyValue=4000, maxJobPropertyValue=9000).value,\
walltime= self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=60, \
minJobPropertyValue=60, maxJobPropertyValue=1200).value) #1.2G memory for 12K loci
returnData.refineGenotypeJob = refineGenotypeJob
"""
2013.07.10 the TrioCaller VCF has some info tags that are not described in VCF header
"""
outputFile = File(os.path.join(self.mapDirJob.folder, \
'%s.extraInfoDesc.vcf'%(intervalFileBasenamePrefix)))
addInfoDescJob = self.addGenericJob(executable=self.AddMissingInfoDescriptionToVCFHeader, \
inputFile=refineGenotypeJob.output, \
inputArgumentOption="-i", \
outputFile=outputFile, outputArgumentOption="-o", \
parentJobLs=[self.mapDirJob, refineGenotypeJob], \
extraDependentInputLs=None, extraOutputLs=None, \
frontArgumentList=None, extraArguments=None, extraArgumentList=None, \
transferOutput=False, sshDBTunnel=None, \
key2ObjectForJob=None, objectWithDBArguments=None, \
no_of_cpus=None,
job_max_memory=self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=2000, \
minJobPropertyValue=1000, maxJobPropertyValue=3000).value, \
walltime=self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=60, \
minJobPropertyValue=60, maxJobPropertyValue=500).value,\
max_walltime=None)
# a CheckGenotypeConcordanceAmongReplicates.py job
trioCallerReplicateConcordanceFile = File(os.path.join(self.statDirJob.folder, \
'%s.trioCaller.concordance.tsv'%(intervalFileBasenamePrefix)))
returnData.trioCallerReplicateConcordanceJob = self.addGATKJob(executable=self.CalculateConcordanceJava, \
GenomeAnalysisTKJar=self.GenomeAnalysisTKJar, \
GATKAnalysisType="CalculateConcordanceAmongReplicates",\
inputFile=refineGenotypeJob.output, inputArgumentOption="--variant", \
refFastaFList=self.registerReferenceData.refFastaFList, \
interval=None, \
outputFile=trioCallerReplicateConcordanceFile, outputArgumentOption="--concordanceStatFname",\
frontArgumentList=None, extraArguments="--replicateIndividualTag %s"%(self.replicateIndividualTag), \
extraArgumentList=None, extraOutputLs=None, \
parentJobLs=[self.statDirJob, refineGenotypeJob], \
transferOutput=False, \
no_of_cpus=None, \
job_max_memory=self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=6000, \
minJobPropertyValue=9000, maxJobPropertyValue=16000).value, \
walltime=self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=60, \
minJobPropertyValue=60, maxJobPropertyValue=1200).value)
#2013.06.14
#merge replicates to generate consensus call
# (not haplotype-based, as different recombination points across replicate haplotypes make it non-trivial )
mergeReplicateOutputF = File(os.path.join(self.mapDirJob.folder, \
'%s.replicatesMerged.vcf'%(intervalFileBasenamePrefix)))
returnData.mergeVCFReplicateColumnsJob = self.addMergeVCFReplicateGenotypeColumnsJob(\
executable=self.MergeVCFReplicateHaplotypesJava,\
GenomeAnalysisTKJar=self.GenomeAnalysisTKJar, \
inputF=addInfoDescJob.output, outputF=mergeReplicateOutputF, \
replicateIndividualTag=self.replicateIndividualTag, \
refFastaFList=self.registerReferenceData.refFastaFList, \
parentJobLs=[self.mapDirJob, addInfoDescJob], \
extraDependentInputLs=[], transferOutput=False, \
extraArguments=None, \
analysis_type='MergeVCFReplicateGenotypeColumns',\
job_max_memory = self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=4000, \
minJobPropertyValue=5000, maxJobPropertyValue=9000).value,\
walltime= self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=60, \
minJobPropertyValue=60, maxJobPropertyValue=1200).value)
return returnData
示例2: addRefineGenotypeJobsViaTrioCaller
# 需要导入模块: from pymodule import PassingData [as 别名]
# 或者: from pymodule.PassingData import trioCallerReplicateConcordanceJob [as 别名]
#.........这里部分代码省略.........
transferOutput=False, \
extraArguments=None, \
job_max_memory=self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=4000, \
minJobPropertyValue=4000, maxJobPropertyValue=9000).value, \
walltime= self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=60, \
minJobPropertyValue=60, maxJobPropertyValue=1200).value,\
)
trioCallerOutputFile = File(os.path.join(outputDirJob.folder, \
'%s.trioCaller.vcf'%(vcfBaseFname)))
trioCallerJob = self.addTrioCallerJob(trioCallerWrapper=self.trioCallerWrapper, \
trioCallerPath=self.trioCallerPath, \
inputVCF=replicateVCFGenotypeColumnsJob.output,\
pedFile=self.outputPedigreeJob.output, outputVCF=trioCallerOutputFile, \
inputPhased=False,\
parentJobLs=[outputDirJob, replicateVCFGenotypeColumnsJob, self.outputPedigreeJob], \
extraDependentInputLs=[], transferOutput=False, \
extraArguments=None, \
job_max_memory = self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=4000, \
minJobPropertyValue=4000, maxJobPropertyValue=9000).value,\
walltime= self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=60, \
minJobPropertyValue=60, maxJobPropertyValue=1200).value) #1.2G memory for 12K loci
returnData.trioCallerJob = trioCallerJob
"""
2013.07.10 the TrioCaller VCF has some info tags that are not described in VCF header
"""
outputFile = File(os.path.join(outputDirJob.folder, \
'%s.extraInfoDesc.vcf'%(vcfBaseFname)))
addInfoDescJob = self.addGenericJob(executable=self.AddMissingInfoDescriptionToVCFHeader, \
inputFile=trioCallerJob.output, \
inputArgumentOption="-i", \
outputFile=outputFile, outputArgumentOption="-o", \
parentJobLs=[outputDirJob, trioCallerJob], \
extraDependentInputLs=None, extraOutputLs=None, \
frontArgumentList=None, extraArguments=None, extraArgumentList=None, \
transferOutput=False, sshDBTunnel=None, \
key2ObjectForJob=None, objectWithDBArguments=None, \
no_of_cpus=None,
job_max_memory=self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=2000, \
minJobPropertyValue=1000, maxJobPropertyValue=3000).value, \
walltime=self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=60, \
minJobPropertyValue=60, maxJobPropertyValue=500).value,\
max_walltime=None)
if statDirJob:
# a CheckGenotypeConcordanceAmongReplicates.py job
trioCallerReplicateConcordanceFile = File(os.path.join(self.statDirJob.folder, \
'%s.trioCaller.concordance.tsv'%(vcfBaseFname)))
returnData.trioCallerReplicateConcordanceJob = self.addGATKJob(executable=self.CalculateConcordanceJava, \
GenomeAnalysisTKJar=self.GenomeAnalysisTKJar, \
GATKAnalysisType="CalculateConcordanceAmongReplicates",\
inputFile=trioCallerJob.output, inputArgumentOption="--variant", \
refFastaFList=self.registerReferenceData.refFastaFList, \
interval=None, \
outputFile=trioCallerReplicateConcordanceFile, outputArgumentOption="--concordanceStatFname",\
frontArgumentList=None, extraArguments="--replicateIndividualTag %s"%(self.replicateIndividualTag), \
extraArgumentList=None, extraOutputLs=None, \
parentJobLs=[self.statDirJob, trioCallerJob], \
transferOutput=False, \
no_of_cpus=None, \
job_max_memory=self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=6000, \
minJobPropertyValue=9000, maxJobPropertyValue=16000).value, \
walltime=self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=60, \
minJobPropertyValue=60, maxJobPropertyValue=1200).value)
#2013.06.14
#merge replicates to generate consensus call
# (not haplotype-based, as different recombination points across replicate haplotypes make it non-trivial )
mergeReplicateOutputF = File(os.path.join(outputDirJob.folder, \
'%s.replicatesMerged.vcf'%(vcfBaseFname)))
mergeVCFReplicateColumnsJob = self.addMergeVCFReplicateGenotypeColumnsJob(\
executable=self.MergeVCFReplicateHaplotypesJava,\
GenomeAnalysisTKJar=self.GenomeAnalysisTKJar, \
inputF=addInfoDescJob.output, outputF=mergeReplicateOutputF, \
replicateIndividualTag=self.replicateIndividualTag, \
refFastaFList=self.registerReferenceData.refFastaFList, \
parentJobLs=[outputDirJob, addInfoDescJob], \
extraDependentInputLs=[], transferOutput=False, \
extraArguments=None, \
analysis_type='MergeVCFReplicateGenotypeColumns',\
job_max_memory = self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=4000, \
minJobPropertyValue=5000, maxJobPropertyValue=9000).value,\
walltime= self.scaleJobWalltimeOrMemoryBasedOnInput(realInputVolume=realInputVolume, \
baseInputVolume=baseInputVolume, baseJobPropertyValue=60, \
minJobPropertyValue=60, maxJobPropertyValue=1200).value)
returnData.refineGenotypeJob = mergeVCFReplicateColumnsJob #the final gentoype job
returnData.refineGenotypeJob.intervalData = intervalData #attached so that it could be used by downstream jobs
return returnData