def createFileStructure(mcProj, expTemplate, configTemplate, options):
if not os.path.exists(options.path):
os.makedirs(options.path)
mcProj.writeXML(os.path.join(options.path, "%s_project.xml" % options.name))
for name, expPath in list(mcProj.expMap.items()):
path = os.path.join(options.path, name)
children = mcProj.entireTree.getChildNames(name)
# Get outgroups
outgroups = []
if configTemplate.getOutgroupStrategy() != 'none' \
and name in mcProj.outgroup.ogMap:
# Outgroup name is the first element of the ogMap tuples
outgroups.extend(list(map(itemgetter(0), mcProj.outgroup.ogMap[name])))
subtree = mcProj.entireTree.extractSpanningTree(children + [name] + outgroups)
exp = ExperimentWrapper.createExperimentWrapper(NXNewick().writeString(subtree),
children + [name] + outgroups,
databaseConf=expTemplate.confElem)
exp.setRootGenome(name)
exp.setOutgroupGenomes(outgroups)
if not os.path.exists(path):
os.makedirs(path)
config = ConfigWrapper(copy.deepcopy(configTemplate.xmlRoot))
if expTemplate.getSequenceID(name):
exp.setRootReconstructed(False)
exp.setSequenceID(name, expTemplate.getSequenceID(name))
else:
exp.setRootReconstructed(True)
exp.writeXML(expPath)
def run(self):
cactusAlignmentName = "cactusAlignment"
cactusAlignment = os.path.join(self.outputDir, cactusAlignmentName)
if not os.path.exists(cactusAlignment):
#Prepare the assembly
#First copy it.
if self.assemblyFile[-3:] == '.gz':
tempAssemblyFile = getTempFile(rootDir=self.getLocalTempDir(),
suffix=".gz")
system("cp %s %s" % (self.assemblyFile, tempAssemblyFile))
system("gunzip %s" % tempAssemblyFile)
tempAssemblyFile = tempAssemblyFile[:-3]
assert os.path.exists(tempAssemblyFile)
else:
tempAssemblyFile = getTempFile(rootDir=self.getLocalTempDir(),
suffix="")
system("cp %s %s" % (self.assemblyFile, tempAssemblyFile))
#Make the supporting temporary files
tempExperimentFile = getTempFile(rootDir=self.getLocalTempDir())
tempJobTreeDir = os.path.join(self.getLocalTempDir(), "jobTree")
#Make the experiment file
cactusWorkflowExperiment = ExperimentWrapper.createExperimentWrapper(
sequences=self.haplotypeSequences + [tempAssemblyFile],
newickTreeString=self.newickTree,
outputDir=self.getLocalTempDir(),
configFile=self.configFile)
cactusWorkflowExperiment.setDbName(cactusAlignmentName)
cactusWorkflowExperiment.setDbDir(
os.path.join(self.getLocalTempDir(),
cactusWorkflowExperiment.getDbName())
) #This needs to be set to ensure the thing gets put in the right directory
cactusWorkflowExperiment.writeXML(tempExperimentFile)
#Now run cactus workflow
runCactusWorkflow(experimentFile=tempExperimentFile,
jobTreeDir=tempJobTreeDir,
buildAvgs=False,
buildReference=True,
batchSystem="single_machine",
maxThreads=1,
jobTreeStats=True)
logger.info("Ran the workflow")
#Check if the jobtree completed sucessively.
runJobTreeStatusAndFailIfNotComplete(tempJobTreeDir)
logger.info("Checked the job tree dir")
#Compute the stats
cactusAlignmentDir = os.path.join(self.getLocalTempDir(),
cactusAlignmentName)
tempJobTreeStatsFile = os.path.join(self.getLocalTempDir(),
"jobTreeStats.xml")
system("jobTreeStats --jobTree %s --outputFile %s" %
(tempJobTreeDir, tempJobTreeStatsFile))
#Now copy the true assembly back to the output
system("mv %s/* %s" % (self.getLocalTempDir(), self.outputDir))
#system("mv %s %s/config.xml" % (tempExperimentFile, self.outputDir))
#system("mv %s %s/" % (tempJobTreeStatsFile, self.outputDir))
#system("mv %s %s/" % (cactusAlignmentDir, self.outputDir))
assert os.path.exists(cactusAlignment)
#We're done!
self.addChildTarget(
MakeStats1(self.outputDir, cactusAlignment, self.options))
def getCactusWorkflowExperimentForTest(sequences,
newickTreeString,
outputDir,
configFile=None,
constraints=None,
progressive=False,
reconstruct=True):
"""Wrapper to constructor of CactusWorkflowExperiment which additionally incorporates
any globally set database conf.
"""
halFile = os.path.join(outputDir, "test.hal")
fastaFile = os.path.join(outputDir, "test.fa")
databaseConf = ET.fromstring(
_GLOBAL_DATABASE_CONF_STRING
) if _GLOBAL_DATABASE_CONF_STRING is not None else None
tree = NXNewick().parseString(newickTreeString, addImpliedRoots=False)
genomes = [
tree.getName(id) for id in tree.postOrderTraversal() if tree.isLeaf(id)
]
exp = ExperimentWrapper.createExperimentWrapper(newickTreeString,
genomes,
outputDir,
databaseConf=databaseConf,
configFile=configFile,
halFile=halFile,
fastaFile=fastaFile,
constraints=constraints,
progressive=progressive)
for genome, sequence in zip(genomes, sequences):
print((genome, sequence))
exp.setSequenceID(genome, sequence)
exp.setRootGenome("reference")
if reconstruct:
exp.setRootReconstructed(True)
return exp
def getCactusWorkflowExperimentForTest(sequences, newickTreeString, outputDir, configFile=None,
constraints=None, progressive=False):
"""Wrapper to constructor of CactusWorkflowExperiment which additionally incorporates
any globally set database conf.
"""
halFile = os.path.join(outputDir, "test.hal")
fastaFile = os.path.join(outputDir, "test.fa")
return ExperimentWrapper.createExperimentWrapper(sequences, newickTreeString, outputDir,
databaseConf=_GLOBAL_DATABASE_CONF_STRING, configFile=configFile,
halFile=halFile, fastaFile=fastaFile, constraints=constraints, progressive=progressive)
def run(self):
cactusAlignmentName = "cactusAlignment"
cactusAlignment = os.path.join(self.outputDir, cactusAlignmentName)
if not os.path.exists(cactusAlignment):
#Prepare the assembly
#First copy it.
if self.assemblyFile[-3:] == '.gz':
tempAssemblyFile = getTempFile(rootDir=self.getLocalTempDir(), suffix=".gz")
system("cp %s %s" % (self.assemblyFile, tempAssemblyFile))
system("gunzip %s" % tempAssemblyFile)
tempAssemblyFile = tempAssemblyFile[:-3]
assert os.path.exists(tempAssemblyFile)
else:
tempAssemblyFile = getTempFile(rootDir=self.getLocalTempDir(), suffix="")
system("cp %s %s" % (self.assemblyFile, tempAssemblyFile))
#Make the supporting temporary files
tempExperimentFile = getTempFile(rootDir=self.getLocalTempDir())
tempJobTreeDir = os.path.join(self.getLocalTempDir(), "jobTree")
#Make the experiment file
cactusWorkflowExperiment = ExperimentWrapper.createExperimentWrapper(
sequences=self.haplotypeSequences + [ tempAssemblyFile ],
newickTreeString=self.newickTree,
outputDir=self.getLocalTempDir(),
configFile=self.configFile)
cactusWorkflowExperiment.setDbName(cactusAlignmentName)
cactusWorkflowExperiment.setDbDir(os.path.join(self.getLocalTempDir(), cactusWorkflowExperiment.getDbName())) #This needs to be set to ensure the thing gets put in the right directory
cactusWorkflowExperiment.writeXML(tempExperimentFile)
#Now run cactus workflow
runCactusWorkflow(experimentFile=tempExperimentFile, jobTreeDir=tempJobTreeDir,
buildAvgs=False, buildReference=True,
batchSystem="single_machine", maxThreads=1, jobTreeStats=True)
logger.info("Ran the workflow")
#Check if the jobtree completed sucessively.
runJobTreeStatusAndFailIfNotComplete(tempJobTreeDir)
logger.info("Checked the job tree dir")
#Compute the stats
cactusAlignmentDir = os.path.join(self.getLocalTempDir(), cactusAlignmentName)
tempJobTreeStatsFile = os.path.join(self.getLocalTempDir(),"jobTreeStats.xml")
system("jobTreeStats --jobTree %s --outputFile %s" % (tempJobTreeDir, tempJobTreeStatsFile))
#Now copy the true assembly back to the output
system("mv %s/* %s" % (self.getLocalTempDir(), self.outputDir))
#system("mv %s %s/config.xml" % (tempExperimentFile, self.outputDir))
#system("mv %s %s/" % (tempJobTreeStatsFile, self.outputDir))
#system("mv %s %s/" % (cactusAlignmentDir, self.outputDir))
assert os.path.exists(cactusAlignment)
#We're done!
self.addChildTarget(MakeStats1(self.outputDir, cactusAlignment, self.options))
def getCactusWorkflowExperimentForTest(sequences,
newickTreeString,
outputDir,
configFile=None,
constraints=None,
progressive=False):
"""Wrapper to constructor of CactusWorkflowExperiment which additionally incorporates
any globally set database conf.
"""
halFile = os.path.join(outputDir, "test.hal")
fastaFile = os.path.join(outputDir, "test.fa")
databaseConf = ET.fromstring(
_GLOBAL_DATABASE_CONF_STRING
) if _GLOBAL_DATABASE_CONF_STRING is not None else None
return ExperimentWrapper.createExperimentWrapper(sequences,
newickTreeString,
outputDir,
databaseConf=databaseConf,
configFile=configFile,
halFile=halFile,
fastaFile=fastaFile,
constraints=constraints,
progressive=progressive)