def testSimulation(self):
if TestStatus.getTestStatus() == TestStatus.TEST_LONG:
blanchettePath = TestStatus.getPathToDataSets() + "/blanchettesSimulation/00.job"
outputPath = TestStatus.getPathToDataSets() + "/ortheus/blanchettesSimulationTest"
treeString = "(((((((((((((human:0.006969,chimp:0.009727):0.025291,((baboon:0.008968):0.011019):0.024581):0.023649):0.066673):0.018405,((rat:0.081244,mouse:0.072818):0.238435):0.021892):0.02326,(((cow:0.164728,(cat:0.109852,dog:0.107805):0.049576):0.004663):0.010883):0.033242):0.028346):0.016015):0.226853):0.063898):0.126639):0.119814):0.16696);"
seqFiles = ["HUMAN", "CHIMP", "BABOON", "RAT", "MOUSE", "COW", "CAT", "DOG"]
seqFiles = [blanchettePath + "/" + i for i in seqFiles]
outputFile = outputPath + "/outputJob1.mfa"
command = "Ortheus.py -e %s -d '%s' -f %s -j -a -b" % (" ".join(seqFiles), treeString, outputFile)
print "running command", command
system(command)
def testSimulation(self):
if TestStatus.getTestStatus() == TestStatus.TEST_LONG:
blanchettePath = TestStatus.getPathToDataSets(
) + "/blanchettesSimulation/00.job"
outputPath = TestStatus.getPathToDataSets(
) + "/ortheus/blanchettesSimulationTest"
treeString = '(((((((((((((human:0.006969,chimp:0.009727):0.025291,((baboon:0.008968):0.011019):0.024581):0.023649):0.066673):0.018405,((rat:0.081244,mouse:0.072818):0.238435):0.021892):0.02326,(((cow:0.164728,(cat:0.109852,dog:0.107805):0.049576):0.004663):0.010883):0.033242):0.028346):0.016015):0.226853):0.063898):0.126639):0.119814):0.16696);'
seqFiles = [
"HUMAN", "CHIMP", "BABOON", "RAT", "MOUSE", "COW", "CAT", "DOG"
]
seqFiles = [blanchettePath + "/" + i for i in seqFiles]
outputFile = outputPath + "/outputJob1.mfa"
command = "Ortheus.py -e %s -d '%s' -f %s -j -a -b" % \
(" ".join(seqFiles), treeString, outputFile)
print "running command", command
system(command)
def setUp(self):
unittest.TestCase.setUp(self)
self.encodeRegion = "ENm001"
self.encodePath = os.path.join(TestStatus.getPathToDataSets(), "MAY-2005")
self.regionPath = os.path.join(self.encodePath, self.encodeRegion)
self.tempDir = getTempDirectory(os.getcwd())
self.tempOutputFile = os.path.join(self.tempDir, "results1.txt")
def testEvolver_Primates_Large(self):
inputDir = os.path.join(TestStatus.getPathToDataSets(), "evolver", "primates", "large")
primateSequences = ("simChimp.masked.fa", "simGorilla.masked.fa", "simHuman.masked.fa", "simOrang.masked.fa")
runWorkflow_multipleExamples(self.id(),
lambda regionNumber=0, tempDir=None : getInputs(inputDir, primateSequences),
batchSystem=self.batchSystem,
buildToilStats=True)
def testEvolver_Mammals_Large(self):
inputDir = os.path.join(TestStatus.getPathToDataSets(), "evolver", "mammals", "large")
mammalSequences = ("simCow.masked.fa", "simDog.masked.fa", "simHuman.masked.fa", "simMouse.masked.fa", "simRat.masked.fa")
runWorkflow_multipleExamples(self.id(),
lambda regionNumber=0, tempDir=None : getInputs(inputDir, mammalSequences),
batchSystem=self.batchSystem,
buildToilStats=True)
def run(self):
previousOutputFile = None
previousOutputFile2 = None
blanchettePath = os.path.join(TestStatus.getPathToDataSets(), "blanchettesSimulation")
for i in xrange(self.options.blanchetteRepeats):
trueAlignmentMFA = os.path.join(os.path.join(blanchettePath, "%.2i.job" % i), "true.mfa")
trueAlignmentMAF = os.path.join(self.getLocalTempDir(), "temp.maf")
treeFile = os.path.join(blanchettePath, "tree.newick")
system("mfaToMaf --mfaFile %s --outputFile %s --treeFile %s" % (trueAlignmentMFA, trueAlignmentMAF, treeFile))
trueRenamedMAF = trueAlignmentMAF + ".renamed"
expPath = os.path.join(self.outputDir, str(i), "experiment.xml")
applyNamingToMaf(expPath, trueAlignmentMAF, trueRenamedMAF)
trueAlignmentMAF = trueRenamedMAF
if self.params.vanilla == False:
predictedAlignmentMaf = os.path.join(self.outputDir, str(i), "progressiveCactusAlignment", "Anc0", "Anc0.maf")
else:
predictedAlignmentMaf = os.path.join(self.outputDir, str(i), "cactusVanilla.maf")
outputFile = os.path.join(self.getLocalTempDir(), "temp%i" % i)
system("mafComparator --mafFile1 %s --mafFile2 %s --outputFile %s" % (trueAlignmentMAF, predictedAlignmentMaf, outputFile))
system("cp %s %s" % (outputFile, os.path.join(self.outputDir, str(i), "mafComparison.xml")))
if previousOutputFile != None:
system("mergeMafComparatorResults.py --results1 %s --results2 %s --outputFile %s" % (outputFile, previousOutputFile, outputFile))
previousOutputFile = outputFile
system("mv %s %s" % (previousOutputFile, os.path.join(self.outputDir, "mafComparison.xml")))
def run(self):
simDir = os.path.join(TestStatus.getPathToDataSets(), "evolver", "mammals", "loci1")
sequences, newickTreeString = getInputs(simDir, ("simHuman.chr6", "simMouse.chr6", "simRat.chr6", "simCow.chr6", "simDog.chr6"))
outputDir = os.path.join(self.options.outputDir, "%s%s" % (self.name, self.params))
self.addChildTarget(MakeAlignment(self.options, sequences, newickTreeString, outputDir,
self.params))
self.setupStats(outputDir, os.path.join(simDir, "all.burnin.maf"), self.params)
def getInputs(path, sequenceNames):
"""Requires setting SON_TRACE_DATASETS variable and having access to datasets.
"""
seqPath = os.path.join(TestStatus.getPathToDataSets(), path)
sequences = [ os.path.join(seqPath, sequence) for sequence in sequenceNames ] #Same order as tree
newickTreeString = parseNewickTreeFile(os.path.join(path, "tree.newick"))
return sequences, newickTreeString
def getInputs(path, sequenceNames):
"""Requires setting SON_TRACE_DATASETS variable and having access to datasets.
"""
seqPath = os.path.join(TestStatus.getPathToDataSets(), path)
sequences = [ os.path.join(seqPath, sequence) for sequence in sequenceNames ] #Same order as tree
newickTreeString = parseNewickTreeFile(os.path.join(path, "tree.newick"))
return sequences, newickTreeString
def testENm001(self):
if TestStatus.getTestStatus() == TestStatus.TEST_VERY_LONG:
encodePath = TestStatus.getPathToDataSets() + "/MAY-2005/ENm001"
outputPath = TestStatus.getPathToDataSets() + "/ortheus/encodeTest"
#treeString = '(((((((((((((human:0.006969,chimp:0.009727):0.025291,((baboon:0.008968):0.011019):0.024581):0.023649):0.066673):0.018405,((rat:0.081244,mouse:0.072818):0.238435):0.021892):0.02326,(((cow:0.164728,(cat:0.109852,dog:0.107805):0.049576):0.004663):0.010883):0.033242):0.028346):0.016015):0.226853):0.063898):0.126639):0.119814):0.16696);'
treeString = '((((human:0.006969,chimp:0.009727):0.025291,baboon:0.044568):0.108727,(rat:0.081244,mouse:0.072818):0.260327):0.02326,(cow:0.164728,(cat:0.109852,dog:0.107805):0.049576):0.048788):0.749525;'
seqFiles = [
"human.ENm001.fa", "chimp.ENm001.fa", "baboon.ENm001.fa",
"rat.ENm001.fa", "mouse.ENm001.fa", "cow.ENm001.fa",
"cat.ENm001.fa", "dog.ENm001.fa"
]
seqFiles = [encodePath + "/" + i for i in seqFiles]
outputFile = outputPath + "/outputENm001.mfa"
command = "Ortheus.py -e %s -d '%s' -f %s -j -a -b" % \
(" ".join(seqFiles), treeString, outputFile)
print "running command", command
system(command)
def getCactusInputs_evolverPrimates():
"""Gets the inputs for running cactus_workflow using some simulated, half megabase primate chromosomes.
Requires setting SON_TRACE_DATASETS variable and having access to datasets.
"""
evolverPath = os.path.join(TestStatus.getPathToDataSets(), "evolver", "primates", "loci1")
sequences = [ os.path.join(evolverPath, seqFile) for seqFile in ("simHuman.chr6", "simChimp.chr6", "simGorilla.chr6" , "simOrang.chr6") ]
newickTreeString = parseNewickTreeFile(os.path.join(evolverPath, "tree.newick"))
return sequences, newickTreeString
def run(self):
simDir = os.path.join(TestStatus.getPathToDataSets(), "evolver", "mammals", "large")
sequences, newickTreeString = getInputs(simDir, ("simHuman.masked.fa", "simMouse.masked.fa"))
newickTreeString = "(simHuman:0.144018,simMouse:0.356483);"
outputDir = os.path.join(self.options.outputDir, "%s%s" % (self.name, self.params))
self.addChildTarget(MakeAlignment(self.options, sequences, newickTreeString, outputDir,
self.params))
self.setupStats(outputDir, os.path.join(simDir, "all.burnin.maf"), self.params)
def testEvolver_Mammals_Loci1(self):
if "SON_TRACE_DATASETS" not in os.environ:
return
inputDir = os.path.join(TestStatus.getPathToDataSets(), "evolver", "mammals", "loci1")
mammalSequences = ("simCow.chr6", "simDog.chr6", "simHuman.chr6", "simMouse.chr6", "simRat.chr6")
runWorkflow_multipleExamples(lambda regionNumber=0, tempDir=None : getInputs(inputDir, mammalSequences),
testRestrictions=(TestStatus.TEST_MEDIUM,),
batchSystem=self.batchSystem,
buildToilStats=True)
def getCactusInputs_evolverPrimates():
"""Gets the inputs for running cactus_workflow using some simulated, half megabase primate chromosomes.
Requires setting SON_TRACE_DATASETS variable and having access to datasets.
"""
evolverPath = os.path.join(TestStatus.getPathToDataSets(), "evolver", "primates", "loci1")
sequences = [ os.path.join(evolverPath, seqFile) for seqFile in ("simHuman.chr6", "simChimp.chr6", "simGorilla.chr6" , "simOrang.chr6") ]
newickTreeString = parseNewickTreeFile(os.path.join(evolverPath, "tree.newick"))
return sequences, newickTreeString
def testEvolver_Mammals_Large(self):
if "SON_TRACE_DATASETS" not in os.environ:
return
inputDir = os.path.join(TestStatus.getPathToDataSets(), "evolver", "mammals", "large")
mammalSequences = ("simCow.masked.fa", "simDog.masked.fa", "simHuman.masked.fa", "simMouse.masked.fa", "simRat.masked.fa")
runWorkflow_multipleExamples(lambda regionNumber=0, tempDir=None : getInputs(inputDir, mammalSequences),
testRestrictions=(TestStatus.TEST_VERY_LONG,),
batchSystem=self.batchSystem,
buildToilStats=True)
def testEvolver_Primates_Large(self):
if "SON_TRACE_DATASETS" not in os.environ:
return
inputDir = os.path.join(TestStatus.getPathToDataSets(), "evolver", "primates", "large")
primateSequences = ("simChimp.masked.fa", "simGorilla.masked.fa", "simHuman.masked.fa", "simOrang.masked.fa")
runWorkflow_multipleExamples(lambda regionNumber=0, tempDir=None : getInputs(inputDir, primateSequences),
testRestrictions=(TestStatus.TEST_VERY_LONG,),
batchSystem=self.batchSystem,
buildJobTreeStats=True)
def testEvolver_Primates_Loci1(self):
if "SON_TRACE_DATASETS" not in os.environ:
return
inputDir = os.path.join(TestStatus.getPathToDataSets(), "evolver", "primates", "loci1")
primateSequences = ("simChimp.chr6", "simGorilla.chr6", "simHuman.chr6", "simOrang.chr6")
runWorkflow_multipleExamples(lambda regionNumber=0, tempDir=None : getInputs(inputDir, primateSequences),
testRestrictions=(TestStatus.TEST_SHORT,),
batchSystem=self.batchSystem,
buildToilStats=True)
def testEvolver_Mammals_Large(self):
if "SON_TRACE_DATASETS" not in os.environ:
return
inputDir = os.path.join(TestStatus.getPathToDataSets(), "evolver", "mammals", "large")
mammalSequences = ("simCow.masked.fa", "simDog.masked.fa", "simHuman.masked.fa", "simMouse.masked.fa", "simRat.masked.fa")
runWorkflow_multipleExamples(lambda regionNumber=0, tempDir=None : getInputs(inputDir, mammalSequences),
testRestrictions=(TestStatus.TEST_VERY_LONG,),
batchSystem=self.batchSystem,
buildJobTreeStats=True)
def run(self):
simDir = os.path.join(TestStatus.getPathToDataSets(), "blanchettesSimulation", "00.job")
sequences = os.path.join(simDir, "HUMAN"), os.path.join(simDir, "MOUSE"), os.path.join(simDir, "DOG")
#, newickTreeString = getInputs(simDir, ("HUMAN", "MOUSE"))
newickTreeString = "((HUMAN:0.144018,MOUSE:0.356483):0.0238,DOG:0.197);"
outputDir = os.path.join(self.options.outputDir, "%s%s" % (self.name, self.params))
self.addChildTarget(MakeAlignment(self.options, sequences, newickTreeString, outputDir,
self.params))
self.setupStats(outputDir, os.path.join(simDir, "true.maf"), self.params)
def testEvolver_Primates_Large(self):
if "SON_TRACE_DATASETS" not in os.environ:
return
inputDir = os.path.join(TestStatus.getPathToDataSets(), "evolver", "primates", "large")
primateSequences = ("simChimp.masked.fa", "simGorilla.masked.fa", "simHuman.masked.fa", "simOrang.masked.fa")
runWorkflow_multipleExamples(lambda regionNumber=0, tempDir=None : getInputs(inputDir, primateSequences),
testRestrictions=(TestStatus.TEST_VERY_LONG,),
batchSystem=self.batchSystem,
buildToilStats=True)
def setUp(self):
self.testNo = TestStatus.getTestSetup(1, 5, 10, 100)
self.tempDir = getTempDirectory(os.getcwd())
self.tempFiles = []
unittest.TestCase.setUp(self)
self.tempOutputFile = os.path.join(self.tempDir, "results1.txt")
self.tempFiles.append(self.tempOutputFile)
self.tempOutputFile2 = os.path.join(self.tempDir, "results2.txt")
self.tempFiles.append(self.tempOutputFile2)
self.encodePath = os.path.join(TestStatus.getPathToDataSets(), "MAY-2005")
def setUp(self):
unittest.TestCase.setUp(self)
self.encodeRegion = "ENm001"
self.encodePath = os.path.join(TestStatus.getPathToDataSets(), "MAY-2005")
self.regionPath = os.path.join(self.encodePath, self.encodeRegion)
self.tempDir = getTempDirectory(os.getcwd())
self.tempOutputFile = os.path.join(self.tempDir, "results1.txt")
self.toilDir = os.path.join(self.tempDir, "toil")
self.toilOptions = Job.Runner.getDefaultOptions(self.toilDir)
self.toilOptions.disableCaching = True
def getCactusInputs_chromosomeX(regionNumber=0, tempDir=None):
"""Gets the inputs for running cactus_workflow using an some mammlian chromosome
X's.
Requires setting SON_TRACE_DATASETS variable and having access to datasets.
"""
chrXPath = os.path.join(TestStatus.getPathToDataSets(), "chr_x")
sequences = [ os.path.join(chrXPath, seqFile) for seqFile in ("cow.fa", "dog.fa", "human.fa", "mouse.fa", "rat.fa") ]
newickTreeString = parseNewickTreeFile(os.path.join(chrXPath, "newickTree.txt"))
return sequences, newickTreeString
def getCactusInputs_chromosomeX(regionNumber=0, tempDir=None):
"""Gets the inputs for running cactus_workflow using an some mammlian chromosome
X's.
Requires setting SON_TRACE_DATASETS variable and having access to datasets.
"""
chrXPath = os.path.join(TestStatus.getPathToDataSets(), "chr_x")
sequences = [ os.path.join(chrXPath, seqFile) for seqFile in ("cow.fa", "dog.fa", "human.fa", "mouse.fa", "rat.fa") ]
newickTreeString = parseNewickTreeFile(os.path.join(chrXPath, "newickTree.txt"))
return sequences, newickTreeString
def setUp(self):
self.testNo = TestStatus.getTestSetup(1, 5, 10, 100)
self.tempDir = getTempDirectory(os.getcwd())
self.tempFiles = []
unittest.TestCase.setUp(self)
self.tempOutputFile = os.path.join(self.tempDir, "results1.txt")
self.tempFiles.append(self.tempOutputFile)
self.tempOutputFile2 = os.path.join(self.tempDir, "results2.txt")
self.tempFiles.append(self.tempOutputFile2)
self.encodePath = os.path.join(TestStatus.getPathToDataSets(), "MAY-2005")
def testENm001(self):
if TestStatus.getTestStatus() == TestStatus.TEST_VERY_LONG:
encodePath = TestStatus.getPathToDataSets() + "/MAY-2005/ENm001"
outputPath = TestStatus.getPathToDataSets() + "/ortheus/encodeTest"
# treeString = '(((((((((((((human:0.006969,chimp:0.009727):0.025291,((baboon:0.008968):0.011019):0.024581):0.023649):0.066673):0.018405,((rat:0.081244,mouse:0.072818):0.238435):0.021892):0.02326,(((cow:0.164728,(cat:0.109852,dog:0.107805):0.049576):0.004663):0.010883):0.033242):0.028346):0.016015):0.226853):0.063898):0.126639):0.119814):0.16696);'
treeString = "((((human:0.006969,chimp:0.009727):0.025291,baboon:0.044568):0.108727,(rat:0.081244,mouse:0.072818):0.260327):0.02326,(cow:0.164728,(cat:0.109852,dog:0.107805):0.049576):0.048788):0.749525;"
seqFiles = [
"human.ENm001.fa",
"chimp.ENm001.fa",
"baboon.ENm001.fa",
"rat.ENm001.fa",
"mouse.ENm001.fa",
"cow.ENm001.fa",
"cat.ENm001.fa",
"dog.ENm001.fa",
]
seqFiles = [encodePath + "/" + i for i in seqFiles]
outputFile = outputPath + "/outputENm001.mfa"
command = "Ortheus.py -e %s -d '%s' -f %s -j -a -b" % (" ".join(seqFiles), treeString, outputFile)
print "running command", command
system(command)
def setUp(self):
unittest.TestCase.setUp(self)
self.tempDir = getTempDirectory(os.getcwd())
self.tempFiles = []
unittest.TestCase.setUp(self)
self.tempOutputFile = os.path.join(self.tempDir, "results1.txt")
self.tempFiles.append(self.tempOutputFile)
self.tempOutputFile2 = os.path.join(self.tempDir, "results2.txt")
self.tempFiles.append(self.tempOutputFile2)
self.encodePath = os.path.join(TestStatus.getPathToDataSets(), "MAY-2005")
self.defaultLastzArguments = "--ambiguous=iupac"
self.defaultRealignArguments = ""
def getCactusInputs_blanchette(regionNumber=0, tempDir=None):
"""Gets the inputs for running cactus_workflow using a blanchette simulated region
(0 <= regionNumber < 50).
Requires setting SON_TRACE_DATASETS variable and having access to datasets.
"""
assert regionNumber >= 0
assert regionNumber < 50
blanchettePath = os.path.join(TestStatus.getPathToDataSets(), "blanchettesSimulation")
sequences = [os.path.join(blanchettePath, ("%.2i.job" % regionNumber), species) \
for species in ("HUMAN", "CHIMP", "BABOON", "MOUSE", "RAT", "DOG", "CAT", "PIG", "COW")] #Same order as tree
newickTreeString = parseNewickTreeFile(os.path.join(blanchettePath, "tree.newick"))
return sequences, newickTreeString
def getCactusInputs_blanchette(regionNumber=0, tempDir=None):
"""Gets the inputs for running cactus_workflow using a blanchette simulated region
(0 <= regionNumber < 50).
Requires setting SON_TRACE_DATASETS variable and having access to datasets.
"""
assert regionNumber >= 0
assert regionNumber < 50
blanchettePath = os.path.join(TestStatus.getPathToDataSets(), "blanchettesSimulation")
sequences = [os.path.join(blanchettePath, ("%.2i.job" % regionNumber), species) \
for species in ("HUMAN", "CHIMP", "BABOON", "MOUSE", "RAT", "DOG", "CAT", "PIG", "COW")] #Same order as tree
newickTreeString = parseNewickTreeFile(os.path.join(blanchettePath, "tree.newick"))
return sequences, newickTreeString
def getCactusInputs_encode(regionNumber=0, tempDir=None):
"""Gets the inputs for running cactus_workflow using an Encode pilot project region.
(0 <= regionNumber < 15).
Requires setting SON_TRACE_DATASETS variable and having access to datasets.
"""
assert regionNumber >= 0
assert regionNumber < 14
encodeRegionString = "ENm%03i" % (regionNumber+1)
encodeDatasetPath = os.path.join(TestStatus.getPathToDataSets(), "MAY-2005")
sequences = [ os.path.join(encodeDatasetPath, encodeRegionString, ("%s.%s.fa" % (species, encodeRegionString))) for\
species in ("human", "chimp", "baboon", "mouse", "rat", "dog", "cow") ]
newickTreeString = parseNewickTreeFile(os.path.join(encodeDatasetPath, "reducedTree.newick"))
return sequences, newickTreeString
def getCactusInputs_encode(regionNumber=0, tempDir=None):
"""Gets the inputs for running cactus_workflow using an Encode pilot project region.
(0 <= regionNumber < 15).
Requires setting SON_TRACE_DATASETS variable and having access to datasets.
"""
assert regionNumber >= 0
assert regionNumber < 14
encodeRegionString = "ENm%03i" % (regionNumber+1)
encodeDatasetPath = os.path.join(TestStatus.getPathToDataSets(), "MAY-2005")
sequences = [ os.path.join(encodeDatasetPath, encodeRegionString, ("%s.%s.fa" % (species, encodeRegionString))) for\
species in ("human", "chimp", "baboon", "mouse", "rat", "dog", "cow") ]
newickTreeString = parseNewickTreeFile(os.path.join(encodeDatasetPath, "reducedTree.newick"))
return sequences, newickTreeString
def seqFilePairGenerator():
##Get sequences
encodePath = os.path.join(TestStatus.getPathToDataSets(), "MAY-2005")
encodeRegions = [ "ENm00" + str(i) for i in xrange(1,2) ] #, 2) ] #Could go to six
species = ("human", "mouse") #, "dog")#, "chimp")
#Other species to try "rat", "monodelphis", "macaque", "chimp"
for encodeRegion in encodeRegions:
regionPath = os.path.join(encodePath, encodeRegion)
for i in xrange(len(species)):
species1 = species[i]
for species2 in species[i+1:]:
seqFile1 = os.path.join(regionPath, "%s.%s.fa" % (species1, encodeRegion))
seqFile2 = os.path.join(regionPath, "%s.%s.fa" % (species2, encodeRegion))
yield seqFile1, seqFile2
def testAndyYatesFirstExample(self):
if TestStatus.getTestStatus() == TestStatus.TEST_LONG:
filePath = TestStatus.getPathToDataSets(
) + "/ortheus/andyYatesExample1"
seqs = "seq1.fa seq2.fa seq3.fa seq4.fa seq5.fa seq6.fa seq7.fa seq8.fa seq9.fa seq10.fa seq11.fa \
seq12.fa seq13.fa seq14.fa seq15.fa seq16.fa seq17.fa seq18.fa seq19.fa seq20.fa seq21.fa seq22.fa seq23.fa seq24.fa seq25.fa seq26.fa \
seq27.fa seq28.fa seq29.fa seq30.fa seq31.fa seq32.fa seq33.fa seq34.fa seq35.fa seq36.fa"
seqs = " ".join(["%s/%s" % (filePath, i) for i in seqs.split()])
command = 'Ortheus.py -l "#-j 0 -e" -e %s -z \
"(((1012:0.0112,1051:0.0119):0.0026,(1055:0.0015,1052:0.0018):0.0370):0.0022,1054:0.0108,1053:0.0116);" \
-A 1054 1051 1054 1054 1053 1012 1054 1054 1053 1054 1051 1054 1051 1051 1053 1051 1051 1012 1051 1054 1012 1054 1053 1051 1053 \
1054 1054 1051 1012 1012 1054 1053 1053 1012 1054 1051 -f %s/output.16163.mfa -g %s/output.16163.tree-a -k "# -A" -m "java -Xmx1800m -Xms1800m" -a -b' % \
(seqs, filePath, filePath)
print "running command", command
system(command)
def testAndyYatesFirstExample(self):
if TestStatus.getTestStatus() == TestStatus.TEST_LONG:
filePath = TestStatus.getPathToDataSets() + "/ortheus/andyYatesExample1"
seqs = "seq1.fa seq2.fa seq3.fa seq4.fa seq5.fa seq6.fa seq7.fa seq8.fa seq9.fa seq10.fa seq11.fa \
seq12.fa seq13.fa seq14.fa seq15.fa seq16.fa seq17.fa seq18.fa seq19.fa seq20.fa seq21.fa seq22.fa seq23.fa seq24.fa seq25.fa seq26.fa \
seq27.fa seq28.fa seq29.fa seq30.fa seq31.fa seq32.fa seq33.fa seq34.fa seq35.fa seq36.fa"
seqs = " ".join(["%s/%s" % (filePath, i) for i in seqs.split()])
command = (
'Ortheus.py -l "#-j 0 -e" -e %s -z \
"(((1012:0.0112,1051:0.0119):0.0026,(1055:0.0015,1052:0.0018):0.0370):0.0022,1054:0.0108,1053:0.0116);" \
-A 1054 1051 1054 1054 1053 1012 1054 1054 1053 1054 1051 1054 1051 1051 1053 1051 1051 1012 1051 1054 1012 1054 1053 1051 1053 \
1054 1054 1051 1012 1012 1054 1053 1053 1012 1054 1051 -f %s/output.16163.mfa -g %s/output.16163.tree-a -k "# -A" -m "java -Xmx1800m -Xms1800m" -a -b'
% (seqs, filePath, filePath)
)
print "running command", command
system(command)
def testCactusWorkflow_Blanchette(self):
"""Runs the workflow on blanchette's simulated (colinear) regions.
"""
if "SON_TRACE_DATASETS" not in os.environ:
return
for test in xrange(self.testNo):
tempFiles = []
tempDir = getTempDirectory(os.getcwd())
trueAlignment = os.path.join(TestStatus.getPathToDataSets(), "blanchettesSimulation", "00.job", "true.mfa")
#Load the true alignment.
columnAlignment = [ i for i in fastaAlignmentRead(trueAlignment) ]
fastaHeaders = [ i for i in fastaReadHeaders(trueAlignment) ]
sequenceNumber = 9
#The tree
newickTreeString = "((((HUMAN:0.006969, CHIMP:0.009727):0.025291, BABOON:0.044568):0.11,(RAT:0.072818, MOUSE:0.081244):0.260342):0.023260,((DOG:0.07, CAT:0.07):0.087381,(PIG:0.06, COW:0.06):0.104728):0.04);"
#Get random dir
testDir = getTempDirectory(tempDir)
#random alignment
alignmentLength = 5000
randomStart = random.choice(xrange(len(columnAlignment)-alignmentLength))
subAlignment = columnAlignment[randomStart:randomStart+alignmentLength]
logger.info("Got a sub alignment, it is %i columns long" % len(subAlignment))
#Get sequences
sequences = [ (fastaHeaders[seqNo], "".join([ column[seqNo] for column in subAlignment if column[seqNo] != '-' ])) for seqNo in xrange(sequenceNumber) ]
logger.info("Got the sequences")
#Write sequences into temp files
tempFastaFiles = []
for seqNo in xrange(sequenceNumber):
header, sequence = sequences[seqNo]
logger.info("Making temp file for header: %s, seq: %s" % (header, sequence))
tempFastaFile = os.path.join(testDir, "%i.fa" % seqNo)
tempFastaFiles.append(tempFastaFile)
fileHandle = open(tempFastaFile, "w")
fastaWrite(fileHandle, header, sequence)
fileHandle.close()
logger.info("Got the temp sequence files")
experiment = getCactusWorkflowExperimentForTest(tempFastaFiles, newickTreeString, testDir)
experimentFile = os.path.join(testDir, "experiment.xml")
experiment.writeXML(experimentFile)
cactusDiskDatabaseString = experiment.getDiskDatabaseString()
jobTree = os.path.join(testDir, "jobTree")
runCactusWorkflow(experimentFile, jobTree)
logger.info("Ran the the workflow")
#Check the output alignment
runJobTreeStatusAndFailIfNotComplete(jobTree)
logger.info("Checked the job tree dir")
#Output the 'TRUE' alignment file
if os.system("mfaToMaf --help > /dev/null 2>&1") == 0 and\
os.system("cactus_MAFGenerator --help > /dev/null 2>&1") == 0 and\
os.system("mafComparator --help > /dev/null 2>&1") == 0 and\
os.system("cactus_treeStats --help > /dev/null 2>&1") == 0:
trueMFAFile = os.path.join(testDir, "true.mfa")
fastaAlignmentWrite(subAlignment, fastaHeaders, len(fastaHeaders), trueMFAFile)
trueMAFFile = os.path.join(testDir, "true.maf")
system("mfaToMaf --mfaFile %s --outputFile %s --logLevel %s" % (trueMFAFile, trueMAFFile, getLogLevelString()))
system("cat %s" % trueMAFFile)
#Now get mafs for the region.
mAFFile = os.path.join(testDir, "flower.maf")
system("cactus_MAFGenerator --flowerName 0 --cactusDisk '%s' --outputFile %s --logLevel %s" % (cactusDiskDatabaseString, mAFFile, getLogLevelString()))
logger.info("Got the MAFs from the flower disk")
system("cat %s" % mAFFile)
statsFile = os.path.join(testDir, "stats.xml")
system("cactus_treeStats --cactusDisk '%s' --flowerName 0 --outputFile %s --logLevel %s" % (cactusDiskDatabaseString, statsFile, getLogLevelString()))
system("cat %s" % statsFile)
logger.info("Got the cactus tree stats")
#Now compare the mafs to the output.
resultsFile = os.path.join(testDir, "results.xml")
system("mafComparator --mafFile1 %s --mafFile2 %s --outputFile %s --logLevel %s" % (trueMAFFile, mAFFile, resultsFile, getLogLevelString()))
logger.info("Ran the maf comparator")
system("cat %s" % resultsFile)
#Cleanup
experiment.cleanupDb()
system("rm -rf %s" % testDir)
logger.info("Successfully ran test for the problem")
for tempFile in tempFiles:
os.remove(tempFile)
system("rm -rf %s" % tempDir)