Python TestStatus.getPathToDataSets方法代码示例

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
 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)

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
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  

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
 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)

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
 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)

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
 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)

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
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

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
 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")

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
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

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
 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 = ""

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
 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)

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
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

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
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

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
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

# 需要导入模块: from sonLib.bioio import TestStatus [as 别名]
# 或者: from sonLib.bioio.TestStatus import getPathToDataSets [as 别名]
 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)