def runCactusProgressive(inputDir,
jobTreeDir,
logLevel=None, retryCount=0,
batchSystem="single_machine",
rescueJobFrequency=None,
skipAlignments=False,
buildHal=None,
buildFasta=None,
buildAvgs=False,
jobTreeStats=False,
maxThreads=None,
maxCpus=None,
defaultMemory=None,
recursive=None,
logFile=None,
event=None,
extraJobTreeArgumentsString="",
profileFile=None):
command = ("cactus_progressive.py %s" % inputDir) + " " + _fn(jobTreeDir,
logLevel, retryCount, batchSystem, rescueJobFrequency, skipAlignments,
buildAvgs, None,
buildHal,
buildFasta,
jobTreeStats, maxThreads, maxCpus, defaultMemory, logFile, extraJobTreeArgumentsString=extraJobTreeArgumentsString) + \
(" %s %s" % (nameValue("recursive", recursive, bool),
nameValue("event", event)))
if profileFile != None:
command = "python -m cProfile -o %s %s/bin/%s" % (profileFile, cactusRootPath(), command)
system(command)
logger.info("Ran the cactus progressive okay")
def runCactusAddReferenceCoordinates(cactusDiskDatabaseString, flowerNames, logLevel=None, referenceEventString=None, outgroupEventString=None, secondaryDatabaseString=None, bottomUpPhase=None):
logLevel = getLogLevelString2(logLevel)
bottomUpPhase = nameValue("bottomUpPhase", bottomUpPhase, bool)
referenceEventString = nameValue("referenceEventString", referenceEventString)
outgroupEventString = nameValue("outgroupEventString", outgroupEventString)
secondaryDatabaseString = nameValue("secondaryDisk", secondaryDatabaseString, quotes=True)
command = "cactus_addReferenceCoordinates --cactusDisk '%s' %s --logLevel %s %s %s %s" % (cactusDiskDatabaseString, secondaryDatabaseString, logLevel, referenceEventString, outgroupEventString, bottomUpPhase)
popenPush(command, stdinString=flowerNames)
def calculateCoverage(sequenceFile, cigarFile, outputFile, fromGenome=None, depthById=False):
logger.info("Calculating coverage of cigar file %s on %s, writing to %s" % (
cigarFile, sequenceFile, outputFile))
system("cactus_coverage %s %s %s %s > %s" % (sequenceFile,
cigarFile,
nameValue("from", fromGenome),
nameValue("depthById", depthById, bool),
outputFile))
def runCactusMAFGenerator(mAFFile, cactusDiskDatabaseString, flowerName="0",
logLevel=None, referenceEventString=None,
showOnlySubstitutionsWithRespectToTheReference=None):
logLevel = getLogLevelString2(logLevel)
referenceEventString = nameValue("referenceEventString", referenceEventString, str)
showOnlySubstitutionsWithRespectToTheReference = nameValue("showOnlySubstitutionsWithRespectToTheReference", showOnlySubstitutionsWithRespectToTheReference, bool)
system("cactus_MAFGenerator --cactusDisk '%s' --flowerName %s --outputFile %s --logLevel %s %s %s" \
% (cactusDiskDatabaseString, flowerName, mAFFile, logLevel, referenceEventString, showOnlySubstitutionsWithRespectToTheReference))
logger.info("Created a MAF for the given cactusDisk")
def runCactusCheck(cactusDiskDatabaseString,
flowerNames=encodeFlowerNames((0,)),
logLevel=None,
recursive=None,
checkNormalised=None):
logLevel = getLogLevelString2(logLevel)
recursive = nameValue("recursive", recursive, bool)
checkNormalised = nameValue("checkNormalised", checkNormalised, bool)
popenPush("cactus_check --cactusDisk '%s' --logLevel %s %s %s" % (cactusDiskDatabaseString, logLevel, recursive, checkNormalised), stdinString=flowerNames)
logger.info("Ran cactus check")
def runCactusSetup(cactusDiskDatabaseString, sequences,
newickTreeString, logLevel=None, outgroupEvents=None,
makeEventHeadersAlphaNumeric=None):
logLevel = getLogLevelString2(logLevel)
outgroupEvents = nameValue("outgroupEvents", outgroupEvents, str, quotes=True)
makeEventHeadersAlphaNumeric=nameValue("makeEventHeadersAlphaNumeric", makeEventHeadersAlphaNumeric, bool)
masterMessages = popenCatch("cactus_setup %s --speciesTree '%s' --cactusDisk '%s' \
--logLevel %s %s %s" \
% (" ".join(sequences), newickTreeString,
cactusDiskDatabaseString, logLevel, outgroupEvents, makeEventHeadersAlphaNumeric))
logger.info("Ran cactus setup okay")
return [ i for i in masterMessages.split("\n") if i != '' ]
def runCactusMAFGenerator(mAFFile,
cactusDiskDatabaseString,
flowerName="0",
logLevel=None,
referenceEventString=None,
showOnlySubstitutionsWithRespectToTheReference=None):
logLevel = getLogLevelString2(logLevel)
referenceEventString = nameValue("referenceEventString",
referenceEventString, str)
showOnlySubstitutionsWithRespectToTheReference = nameValue(
"showOnlySubstitutionsWithRespectToTheReference",
showOnlySubstitutionsWithRespectToTheReference, bool)
system("cactus_MAFGenerator --cactusDisk '%s' --flowerName %s --outputFile %s --logLevel %s %s %s" \
% (cactusDiskDatabaseString, flowerName, mAFFile, logLevel, referenceEventString, showOnlySubstitutionsWithRespectToTheReference))
logger.info("Created a MAF for the given cactusDisk")
def runCactusHalGenerator(cactusDiskDatabaseString,
secondaryDatabaseString,
flowerNames,
referenceEventString,
outputFile=None,
showOnlySubstitutionsWithRespectToReference=None,
logLevel=None):
logLevel = getLogLevelString2(logLevel)
popenPush("cactus_halGenerator --cactusDisk '%s' --secondaryDisk '%s' --logLevel %s %s %s %s" %
(cactusDiskDatabaseString, secondaryDatabaseString, logLevel,
nameValue("referenceEventString", referenceEventString),
nameValue("outputFile", outputFile),
nameValue("showOnlySubstitutionsWithRespectToReference",
showOnlySubstitutionsWithRespectToReference, bool)),
stdinString=flowerNames)
def calculateExpectations(target, sequences, alignments, modelsFile,
expectationsFile, options):
#Run cPecanRealign
system(
"cat %s | cPecanRealign --logLevel DEBUG %s %s --outputExpectations=%s %s"
% (alignments, sequences, nameValue("loadHmm", modelsFile, str),
expectationsFile, options.optionsToRealign))
def runCactusAdjacencyGraphViewer(graphFile,
cactusDiskDatabaseString, flowerName="0",
logLevel=None, includeInternalAdjacencies=False):
logLevel = getLogLevelString2(logLevel)
includeInternalAdjacencies = nameValue("includeInternalAdjacencies", includeInternalAdjacencies, bool)
system("cactus_adjacencyGraphViewer --cactusDisk '%s' --flowerName %s --outputFile %s --logLevel %s" \
% (cactusDiskDatabaseString, flowerName, graphFile, logLevel))
logger.info("Created a break point graph of the problem")
def runCactusCreateMultiCactusProject(experimentFile, outputDir,
logLevel=None, fixNames=True,
root=None):
logLevel = getLogLevelString2(logLevel)
root = nameValue("root", root, str, quotes=True)
command = "cactus_createMultiCactusProject.py %s %s --fixNames=%s %s" % (experimentFile, outputDir, str(fixNames), root)
system(command)
logger.info("Ran the cactus create multi project")
def runCactusBlast(sequenceFiles, outputFile, jobTreeDir,
chunkSize=None, overlapSize=None,
logLevel=None,
blastString=None,
selfBlastString=None,
compressFiles=None,
lastzMemory=None,
targetSequenceFiles=None):
logLevel = getLogLevelString2(logLevel)
chunkSize = nameValue("chunkSize", chunkSize, int)
overlapSize = nameValue("overlapSize", overlapSize, int)
blastString = nameValue("blastString", blastString, str)
selfBlastString = nameValue("selfBlastString", selfBlastString, str)
compressFiles = nameValue("compressFiles", compressFiles, bool)
lastzMemory = nameValue("lastzMemory", lastzMemory, int)
if targetSequenceFiles != None:
targetSequenceFiles = " ".join(targetSequenceFiles)
targetSequenceFiles = nameValue("targetSequenceFiles", targetSequenceFiles, quotes=True)
command = "cactus_blast.py %s --cigars %s %s %s %s %s %s %s %s --jobTree %s --logLevel %s" % \
(" ".join(sequenceFiles), outputFile,
chunkSize, overlapSize, blastString, selfBlastString, compressFiles,
lastzMemory, targetSequenceFiles, jobTreeDir, logLevel)
logger.info("Running command : %s" % command)
system(command)
logger.info("Ran the cactus_blast command okay")
def runCactusFastaGenerator(cactusDiskDatabaseString,
flowerName,
outputFile,
referenceEventString=None,
logLevel=None):
logLevel = getLogLevelString2(logLevel)
system("cactus_fastaGenerator --cactusDisk '%s' --flowerName %s --outputFile %s --logLevel %s %s" %
(cactusDiskDatabaseString, flowerName, outputFile, logLevel,
nameValue("referenceEventString", referenceEventString)))
def runCactusAdjacencyGraphViewer(graphFile,
cactusDiskDatabaseString,
flowerName="0",
logLevel=None,
includeInternalAdjacencies=False):
logLevel = getLogLevelString2(logLevel)
includeInternalAdjacencies = nameValue("includeInternalAdjacencies",
includeInternalAdjacencies, bool)
system("cactus_adjacencyGraphViewer --cactusDisk '%s' --flowerName %s --outputFile %s --logLevel %s" \
% (cactusDiskDatabaseString, flowerName, graphFile, logLevel))
logger.info("Created a break point graph of the problem")
def trimGenome(sequenceFile, coverageFile, outputFile, complement=False,
flanking=0, minSize=1, windowSize=10, threshold=1, depth=None):
system("cactus_trimSequences.py %s %s %s %s %s %s %s %s > %s" % (
nameValue("complement", complement, valueType=bool),
nameValue("flanking", flanking), nameValue("minSize", minSize),
nameValue("windowSize", windowSize), nameValue("threshold", threshold),
nameValue("depth", depth), sequenceFile, coverageFile, outputFile))
def runCactusTreeStats(outputFile,
cactusDiskDatabaseString,
flowerName='0',
logLevel=None,
referenceEventString=None):
logLevel = getLogLevelString2(logLevel)
referenceEventString = nameValue("referenceEventString",
referenceEventString, str)
command = "cactus_treeStats --cactusDisk '%s' --flowerName %s --outputFile %s --logLevel %s %s" % (
cactusDiskDatabaseString, flowerName, outputFile, logLevel,
referenceEventString)
system(command)
logger.info("Ran the cactus tree stats command apprently okay")
def runCPecanEm(sequenceFiles, alignmentsFile, outputModelFile,
inputModelFile=None,
modelType=None,
jobTreeDir=None,
iterations=None, randomStart=None,
trials=None,
optionsToRealign=None,
logLevel=None,
updateTheBand=None,
maxAlignmentLengthPerJob=None,
maxAlignmentLengthToSample=None,
useDefaultModelAsStart=None,
setJukesCantorStartingEmissions=None,
trainEmissions=None,
tieEmissions=None,
outputTrialHmms = None,
outputXMLModelFile = None,
blastScoringMatrixFile=None):
logLevel = getLogLevelString2(logLevel)
jobTreeDir= nameValue("jobTree", jobTreeDir, str)
inputModelFile= nameValue("inputModel", inputModelFile, str)
modelType = nameValue("modelType", modelType, str)
iterations = nameValue("iterations", iterations, int)
trials = nameValue("trials", trials, int)
randomStart = nameValue("randomStart", randomStart, bool)
updateTheBand = nameValue("updateTheBand", updateTheBand, bool)
maxAlignmentLengthPerJob = nameValue("maxAlignmentLengthPerJob", maxAlignmentLengthPerJob, int)
maxAlignmentLengthToSample = nameValue("maxAlignmentLengthToSample", maxAlignmentLengthToSample, int)
optionsToRealign = nameValue("optionsToRealign", optionsToRealign, quotes=True)
useDefaultModelAsStart = nameValue("useDefaultModelAsStart", useDefaultModelAsStart, bool)
trainEmissions = nameValue("trainEmissions", trainEmissions, bool)
tieEmissions = nameValue("tieEmissions", tieEmissions, bool)
setJukesCantorStartingEmissions = nameValue("setJukesCantorStartingEmissions", setJukesCantorStartingEmissions, float)
outputTrialHmms = nameValue("outputTrialHmms", outputTrialHmms, bool)
outputXMLModelFile = nameValue("outputXMLModelFile", outputXMLModelFile, str)
blastScoringMatrixFile = nameValue("blastScoringMatrixFile", blastScoringMatrixFile, str)
system("cPecanEm --sequences '%s' --alignments %s --outputModel %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s" % \
(" ".join(sequenceFiles), alignmentsFile, outputModelFile, iterations, trials, randomStart,
jobTreeDir, inputModelFile, optionsToRealign, modelType,
maxAlignmentLengthPerJob, maxAlignmentLengthToSample, updateTheBand, useDefaultModelAsStart,
trainEmissions, tieEmissions, setJukesCantorStartingEmissions, outputTrialHmms,
outputXMLModelFile, blastScoringMatrixFile))
def _fn(jobTreeDir,
logLevel=None, retryCount=0,
batchSystem="single_machine",
rescueJobFrequency=None,
skipAlignments=False,
buildAvgs=False, buildReference=False,
buildHal=False,
buildFasta=False,
jobTreeStats=False,
maxThreads=None,
maxCpus=None,
defaultMemory=None,
logFile=None,
extraJobTreeArgumentsString=""):
logLevel = getLogLevelString2(logLevel)
skipAlignments = nameValue("skipAlignments", skipAlignments, bool)
buildAvgs = nameValue("buildAvgs", buildAvgs, bool)
buildReference = nameValue("buildReference", buildReference, bool)
buildHal = nameValue("buildHal", buildHal, bool)
buildFasta = nameValue("buildFasta", buildFasta, bool)
#Jobtree args
batchSystem = nameValue("batchSystem", batchSystem, str, quotes=True)
retryCount = nameValue("retryCount", retryCount, int)
rescueJobFrequency = nameValue("rescueJobsFrequency", rescueJobFrequency, int)
jobTreeStats = nameValue("stats", jobTreeStats, bool)
maxThreads = nameValue("maxThreads", maxThreads, int)
maxCpus = nameValue("maxCpus", maxCpus, int)
defaultMemory= nameValue("defaultMemory", defaultMemory, int)
logFile = nameValue("logFile", logFile, str)
return "%s %s %s --jobTree %s --logLevel %s %s %s %s %s %s %s %s %s %s %s %s" % (skipAlignments, buildAvgs,
buildReference, jobTreeDir, logLevel, buildHal, buildFasta, batchSystem, retryCount, rescueJobFrequency, jobTreeStats, maxThreads, maxCpus, logFile, defaultMemory, extraJobTreeArgumentsString)
def runCactusTreeStats(outputFile, cactusDiskDatabaseString, flowerName='0', logLevel=None, referenceEventString=None):
logLevel = getLogLevelString2(logLevel)
referenceEventString = nameValue("referenceEventString", referenceEventString, str)
command = "cactus_treeStats --cactusDisk '%s' --flowerName %s --outputFile %s --logLevel %s %s" % (cactusDiskDatabaseString, flowerName, outputFile, logLevel, referenceEventString)
system(command)
logger.info("Ran the cactus tree stats command apprently okay")
def runCactusReference(cactusDiskDatabaseString, flowerNames, logLevel=None,
matchingAlgorithm=None,
referenceEventString=None,
permutations=None,
useSimulatedAnnealing=None,
theta=None,
phi=None,
maxWalkForCalculatingZ=None,
ignoreUnalignedGaps=None,
wiggle=None,
numberOfNs=None,
minNumberOfSequencesToSupportAdjacency=None,
makeScaffolds=None):
"""Runs cactus reference.
"""
logLevel = getLogLevelString2(logLevel)
matchingAlgorithm = nameValue("matchingAlgorithm", matchingAlgorithm)
referenceEventString = nameValue("referenceEventString", referenceEventString)
permutations = nameValue("permutations", permutations, int)
useSimulatedAnnealing = nameValue("useSimulatedAnnealing", useSimulatedAnnealing, bool)
theta = nameValue("theta", theta, float)
phi = nameValue("phi", phi, float)
maxWalkForCalculatingZ = nameValue("maxWalkForCalculatingZ", maxWalkForCalculatingZ, int)
ignoreUnalignedGaps = nameValue("ignoreUnalignedGaps", ignoreUnalignedGaps, bool)
wiggle = nameValue("wiggle", wiggle, float)
numberOfNs = nameValue("numberOfNs", numberOfNs, int)
minNumberOfSequencesToSupportAdjacency = nameValue("minNumberOfSequencesToSupportAdjacency", minNumberOfSequencesToSupportAdjacency, int)
makeScaffolds = nameValue("makeScaffolds", makeScaffolds, bool)
command = "cactus_reference --cactusDisk '%s' --logLevel %s %s %s %s %s %s %s %s %s %s %s %s %s" % \
(cactusDiskDatabaseString, logLevel, matchingAlgorithm, referenceEventString, permutations,
useSimulatedAnnealing, theta, phi, maxWalkForCalculatingZ, ignoreUnalignedGaps, wiggle, numberOfNs, minNumberOfSequencesToSupportAdjacency, makeScaffolds)
masterMessages = popenCatch(command, stdinString=flowerNames)
logger.info("Ran cactus_reference okay")
return [ i for i in masterMessages.split("\n") if i != '' ]
def runCactusBar(cactusDiskDatabaseString, flowerNames, logLevel=None,
spanningTrees=None, maximumLength=None,
gapGamma=None,
matchGamma=None,
splitMatrixBiggerThanThis=None,
anchorMatrixBiggerThanThis=None,
repeatMaskMatrixBiggerThanThis=None,
diagonalExpansion=None,
constraintDiagonalTrim=None,
minimumBlockDegree=None,
minimumIngroupDegree=None,
minimumOutgroupDegree=None,
alignAmbiguityCharacters=None,
pruneOutStubAlignments=None,
useProgressiveMerging=None,
calculateWhichEndsToComputeSeparately=None,
largeEndSize=None,
endAlignmentsToPrecomputeOutputFile=None,
precomputedAlignments=None,
ingroupCoverageFile=None,
minimumSizeToRescue=None,
minimumCoverageToRescue=None,
minimumNumberOfSpecies=None):
"""Runs cactus base aligner.
"""
logLevel = getLogLevelString2(logLevel)
maximumLength = nameValue("maximumLength", maximumLength, int)
spanningTrees = nameValue("spanningTrees", spanningTrees, int)
gapGamma = nameValue("gapGamma", gapGamma, float)
matchGamma = nameValue("matchGamma", matchGamma, float)
splitMatrixBiggerThanThis=nameValue("splitMatrixBiggerThanThis", splitMatrixBiggerThanThis, int)
anchorMatrixBiggerThanThis=nameValue("anchorMatrixBiggerThanThis", anchorMatrixBiggerThanThis, int)
repeatMaskMatrixBiggerThanThis=nameValue("repeatMaskMatrixBiggerThanThis", repeatMaskMatrixBiggerThanThis, int)
diagonalExpansion=nameValue("diagonalExpansion", diagonalExpansion, int)
constraintDiagonalTrim = nameValue("constraintDiagonalTrim", constraintDiagonalTrim, int)
minimumBlockDegree = nameValue("minimumDegree", minimumBlockDegree, int)
minimumIngroupDegree = nameValue("minimumIngroupDegree", minimumIngroupDegree, int)
minimumOutgroupDegree = nameValue("minimumOutgroupDegree", minimumOutgroupDegree, int)
pruneOutStubAlignments = nameValue("pruneOutStubAlignments", pruneOutStubAlignments, bool)
alignAmbiguityCharacters = nameValue("alignAmbiguityCharacters", alignAmbiguityCharacters, bool)
useProgressiveMerging=nameValue("useProgressiveMerging", useProgressiveMerging, bool)
calculateWhichEndsToComputeSeparately=nameValue("calculateWhichEndsToComputeSeparately", calculateWhichEndsToComputeSeparately, bool)
largeEndSize=nameValue("largeEndSize", largeEndSize, int)
endAlignmentsToPrecomputeOutputFile=nameValue("endAlignmentsToPrecomputeOutputFile", endAlignmentsToPrecomputeOutputFile, str)
precomputedAlignments=nameValue("precomputedAlignments", precomputedAlignments, str, quotes=True)
ingroupCoverageFile = nameValue("ingroupCoverageFile", ingroupCoverageFile, str, quotes=True)
minimumSizeToRescue = nameValue("minimumSizeToRescue", minimumSizeToRescue, int)
minimumCoverageToRescue = nameValue("minimumCoverageToRescue", minimumCoverageToRescue, float)
minimumNumberOfSpecies = nameValue("minimumNumberOfSpecies", minimumNumberOfSpecies, int)
masterMessages = popenCatch("cactus_bar --cactusDisk '%s' --logLevel %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s" %
(cactusDiskDatabaseString, logLevel, spanningTrees, maximumLength, gapGamma, matchGamma,
splitMatrixBiggerThanThis, anchorMatrixBiggerThanThis, repeatMaskMatrixBiggerThanThis,
constraintDiagonalTrim, minimumBlockDegree, minimumIngroupDegree, minimumOutgroupDegree,
alignAmbiguityCharacters, pruneOutStubAlignments, diagonalExpansion,
useProgressiveMerging, calculateWhichEndsToComputeSeparately,
largeEndSize, endAlignmentsToPrecomputeOutputFile, precomputedAlignments, ingroupCoverageFile, minimumSizeToRescue, minimumCoverageToRescue, minimumNumberOfSpecies), stdinString=flowerNames)
logger.info("Ran cactus_bar okay")
return [ i for i in masterMessages.split("\n") if i != '' ]
def runCactusCaf(cactusDiskDatabaseString, alignments,
flowerNames=encodeFlowerNames((0,)),
logLevel=None,
writeDebugFiles=False,
annealingRounds=None,
deannealingRounds=None,
trim=None,
minimumTreeCoverage=None,
blockTrim=None,
minimumBlockDegree=None,
minimumIngroupDegree=None,
minimumOutgroupDegree=None,
alignmentFilter=None,
lastzArguments=None,
minimumSequenceLengthForBlast=None,
maxAdjacencyComponentSizeRatio=None,
constraints=None,
minLengthForChromosome=None,
proportionOfUnalignedBasesForNewChromosome=None,
maximumMedianSequenceLengthBetweenLinkedEnds=None,
realign=None,
realignArguments=None,
phylogenyNumTrees=None,
phylogenyScoringMethod=None,
phylogenyRootingMethod=None,
phylogenyBreakpointScalingFactor=None,
phylogenySkipSingleCopyBlocks=None,
phylogenyMaxBaseDistance=None,
phylogenyMaxBlockDistance=None,
phylogenyDebugFile=None,
phylogenyKeepSingleDegreeBlocks=None,
phylogenyTreeBuildingMethod=None,
phylogenyCostPerDupPerBase=None,
phylogenyCostPerLossPerBase=None,
referenceEventHeader=None,
phylogenyDoSplitsWithSupportHigherThanThisAllAtOnce=None,
numTreeBuildingThreads=None,
doPhylogeny=None,
removeLargestBlock=None,
phylogenyNucleotideScalingFactor=None,
minimumBlockDegreeToCheckSupport=None,
minimumBlockHomologySupport=None,
removeRecoverableChains=None,
minimumNumberOfSpecies=None,
maxRecoverableChainsIterations=None,
maxRecoverableChainLength=None,
phylogenyHomologyUnitType=None,
phylogenyDistanceCorrectionMethod=None):
# remove annoying carriage returns in caf command line.
cactusDiskDatabaseString = cactusDiskDatabaseString.replace('\n', '')
logLevel = getLogLevelString2(logLevel)
annealingRounds = nameValue("annealingRounds", annealingRounds, quotes=True)
deannealingRounds = nameValue("deannealingRounds", deannealingRounds, quotes=True)
trim = nameValue("trim", trim, quotes=True)
alignments = nameValue("alignments", alignments)
lastzArguments = nameValue("lastzArguments", lastzArguments, quotes=True)
minimumTreeCoverage = nameValue("minimumTreeCoverage", minimumTreeCoverage, float)
blockTrim = nameValue("blockTrim", blockTrim, int)
minimumBlockDegree = nameValue("minimumDegree", minimumBlockDegree, int)
minimumSequenceLengthForBlast = nameValue("minimumSequenceLengthForBlast", minimumSequenceLengthForBlast, int)
minimumIngroupDegree = nameValue("minimumIngroupDegree", minimumIngroupDegree, int)
minimumOutgroupDegree = nameValue("minimumOutgroupDegree", minimumOutgroupDegree, int)
alignmentFilter = nameValue("alignmentFilter", alignmentFilter)
maxAdjacencyComponentSizeRatio = nameValue("maxAdjacencyComponentSizeRatio", maxAdjacencyComponentSizeRatio, float)
constraints = nameValue("constraints", constraints)
realign = nameValue("realign", realign, bool)
realignArguments = nameValue("realignArguments", realignArguments, quotes=True)
phylogenyNumTrees = nameValue("phylogenyNumTrees", phylogenyNumTrees, int)
phylogenyRootingMethod = nameValue("phylogenyRootingMethod", phylogenyRootingMethod, quotes=True)
phylogenyScoringMethod = nameValue("phylogenyScoringMethod", phylogenyScoringMethod, quotes=True)
phylogenyBreakpointScalingFactor = nameValue("phylogenyBreakpointScalingFactor", phylogenyBreakpointScalingFactor)
phylogenySkipSingleCopyBlocks = nameValue("phylogenySkipSingleCopyBlocks", phylogenySkipSingleCopyBlocks, bool)
phylogenyMaxBaseDistance = nameValue("phylogenyMaxBaseDistance", phylogenyMaxBaseDistance)
phylogenyMaxBlockDistance = nameValue("phylogenyMaxBlockDistance", phylogenyMaxBlockDistance)
phylogenyDebugFile = nameValue("phylogenyDebugFile", phylogenyDebugFile)
phylogenyKeepSingleDegreeBlocks = nameValue("phylogenyKeepSingleDegreeBlocks", phylogenyKeepSingleDegreeBlocks, bool)
phylogenyTreeBuildingMethod = nameValue("phylogenyTreeBuildingMethod", phylogenyTreeBuildingMethod)
phylogenyCostPerDupPerBase = nameValue("phylogenyCostPerDupPerBase", phylogenyCostPerDupPerBase)
phylogenyCostPerLossPerBase = nameValue("phylogenyCostPerLossPerBase", phylogenyCostPerLossPerBase)
referenceEventHeader = nameValue("referenceEventHeader", referenceEventHeader, quotes=True)
phylogenyDoSplitsWithSupportHigherThanThisAllAtOnce = nameValue("phylogenyDoSplitsWithSupportHigherThanThisAllAtOnce", phylogenyDoSplitsWithSupportHigherThanThisAllAtOnce)
numTreeBuildingThreads = nameValue("numTreeBuildingThreads", numTreeBuildingThreads)
doPhylogeny = nameValue("phylogeny", doPhylogeny, bool)
minimumBlockDegreeToCheckSupport = nameValue("minimumBlockDegreeToCheckSupport", minimumBlockDegreeToCheckSupport)
minimumBlockHomologySupport = nameValue("minimumBlockHomologySupport", minimumBlockHomologySupport)
phylogenyNucleotideScalingFactor = nameValue("phylogenyNucleotideScalingFactor", phylogenyNucleotideScalingFactor)
removeRecoverableChains = nameValue("removeRecoverableChains", removeRecoverableChains)
minimumNumberOfSpecies = nameValue("minimumNumberOfSpecies", minimumNumberOfSpecies, int)
maxRecoverableChainsIterations = nameValue("maxRecoverableChainsIterations", maxRecoverableChainsIterations, int)
maxRecoverableChainLength = nameValue("maxRecoverableChainLength", maxRecoverableChainLength, int)
phylogenyHomologyUnitType = nameValue("phylogenyHomologyUnitType", phylogenyHomologyUnitType, quotes=True)
phylogenyDistanceCorrectionMethod = nameValue("phylogenyDistanceCorrectionMethod", phylogenyDistanceCorrectionMethod, quotes=True)
minLengthForChromosome = nameValue("minLengthForChromosome", minLengthForChromosome, int)
proportionOfUnalignedBasesForNewChromosome = nameValue("proportionOfUnalignedBasesForNewChromosome", proportionOfUnalignedBasesForNewChromosome, float)
maximumMedianSequenceLengthBetweenLinkedEnds = nameValue("maximumMedianSequenceLengthBetweenLinkedEnds", maximumMedianSequenceLengthBetweenLinkedEnds, int)
command = "cactus_caf --cactusDisk '%s' --logLevel %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s" % \
(cactusDiskDatabaseString, logLevel, alignments, annealingRounds, deannealingRounds,
trim, minimumTreeCoverage, blockTrim,
minimumBlockDegree, minimumIngroupDegree, minimumOutgroupDegree,
alignmentFilter, lastzArguments, minimumSequenceLengthForBlast, maxAdjacencyComponentSizeRatio, constraints,
minLengthForChromosome, proportionOfUnalignedBasesForNewChromosome, maximumMedianSequenceLengthBetweenLinkedEnds, realign, realignArguments, phylogenyNumTrees, phylogenyRootingMethod, phylogenyScoringMethod, phylogenyBreakpointScalingFactor, phylogenySkipSingleCopyBlocks, phylogenyMaxBaseDistance, phylogenyMaxBlockDistance, phylogenyDebugFile, phylogenyKeepSingleDegreeBlocks, phylogenyTreeBuildingMethod, phylogenyCostPerDupPerBase, phylogenyCostPerLossPerBase, referenceEventHeader, phylogenyDoSplitsWithSupportHigherThanThisAllAtOnce, numTreeBuildingThreads, doPhylogeny, minimumBlockDegreeToCheckSupport, minimumBlockHomologySupport, phylogenyNucleotideScalingFactor, removeRecoverableChains, minimumNumberOfSpecies, phylogenyHomologyUnitType, phylogenyDistanceCorrectionMethod, maxRecoverableChainsIterations, maxRecoverableChainLength)
masterMessages = popenCatch(command, stdinString=flowerNames)
logger.info("Ran cactus_core okay")
return [ i for i in masterMessages.split("\n") if i != '' ]
def runConvertAlignmentsToInternalNames(cactusDiskString, alignmentsFile, outputFile, flowerName, isBedFile=False):
bed = nameValue("bed", isBedFile, bool)
popenCatch("cactus_convertAlignmentsToInternalNames --cactusDisk '%s' %s %s %s" % (cactusDiskString, alignmentsFile, outputFile, bed), stdinString=encodeFlowerNames((flowerName,)))
def calculateExpectations(target, sequences, alignments, modelsFile, expectationsFile, options):
#Run cPecanRealign
system("cat %s | cPecanRealign --logLevel DEBUG %s %s --outputExpectations=%s %s" % (alignments, sequences, nameValue("loadHmm", modelsFile, str), expectationsFile, options.optionsToRealign))