def addMkDirJob(workflow=None, mkdir=None, outputDir=None, namespace=None, version=None,\
parentJobLs=None, extraDependentInputLs=None):
"""
2012.10.2, increment workflow.no_of_jobs
2012.9.11
make sure that parentJobLs and extraDependentInputLs are not None.
2012.3.10
add argument parentJobLs, extraDependentInputLs
2011-11-28
get namespace and version from workflow first
2011-9-14
"""
# Add a mkdir job for any directory.
job = Job(namespace=getattr(workflow, 'namespace', namespace), name=mkdir.name, \
version=getattr(workflow, 'version', version))
job.addArguments(outputDir)
job.folder = outputDir #custom attribute
job.output = outputDir #custom attribute
workflow.addJob(job)
if parentJobLs:
for parentJob in parentJobLs:
if parentJob:
workflow.depends(parent=parentJob, child=job)
if extraDependentInputLs:
for input in extraDependentInputLs:
if input is not None:
job.uses(input, transfer=True, register=True, link=Link.INPUT)
if hasattr(workflow, 'no_of_jobs'): #2012.10.2
workflow.no_of_jobs += 1
return job
def addReadCountJob(self, workflow, VariousReadCountJava=None, GenomeAnalysisTKJar=None,\
refFastaFList=None, bamF=None, baiF=None, readCountOutputF=None,\
parentJobLs=[], job_max_memory = 1000, extraArguments="", \
transferOutput=False):
"""
2011-11-25
"""
javaMemRequirement = "-Xms128m -Xmx%sm"%job_max_memory
refFastaF = refFastaFList[0]
job = Job(namespace=workflow.namespace, name=VariousReadCountJava.name, version=workflow.version)
job.addArguments(javaMemRequirement, '-jar', GenomeAnalysisTKJar, "-T", "VariousReadCount",\
'-R', refFastaF, '-o', readCountOutputF, "-mmq 30")
job.addArguments("-I", bamF)
if extraArguments:
job.addArguments(extraArguments)
self.addJobUse(job, file=GenomeAnalysisTKJar, transfer=True, register=True, link=Link.INPUT)
job.uses(bamF, transfer=True, register=True, link=Link.INPUT)
job.uses(baiF, transfer=True, register=True, link=Link.INPUT)
self.registerFilesAsInputToJob(job, refFastaFList)
job.output = readCountOutputF
job.uses(readCountOutputF, transfer=transferOutput, register=True, link=Link.OUTPUT)
workflow.addJob(job)
yh_pegasus.setJobProperRequirement(job, job_max_memory=job_max_memory)
for parentJob in parentJobLs:
workflow.depends(parent=parentJob, child=job)
"""
#2013.3.24 should use this
job = self.addGATKJob(self, workflow=None, executable=None, GenomeAnalysisTKJar=None, GATKAnalysisType=None,\
inputFile=None, inputArgumentOption=None, refFastaFList=None, inputFileList=None,\
argumentForEachFileInInputFileList=None,\
interval=None, outputFile=None, \
parentJobLs=None, transferOutput=True, job_max_memory=2000,\
frontArgumentList=None, extraArguments=None, extraArgumentList=None, extraOutputLs=None, \
extraDependentInputLs=None, no_of_cpus=None, walltime=120, **keywords)
"""
return job
