def __init__(self, halFile, phyloPModel, bedFileDict, jobsPerGenome, threshold):
Target.__init__(self)
self.halFile = halFile
self.phyloPModel = phyloPModel
self.bedFileDict = bedFileDict
self.jobsPerGenome = jobsPerGenome
self.threshold = threshold
def __init__(self, halfile, names, outdir, maxOut, minIn):
Target.__init__(self)
self.halfile = halfile
self.names = names
self.outdir = outdir
self.maxOut = maxOut
self.minIn = minIn
def __init__(self, options, outdir, halfile, genome2seq2len, type):
Target.__init__(self)
self.options = options
self.outdir = outdir
self.halfile = halfile
self.genome2seq2len = genome2seq2len
self.type = type #type has to be bed or wiggle
def __init__(self, cactusDisk, flowerName, finalResultsFile, blastOptions):
Target.__init__(self)
self.cactusDisk = cactusDisk
self.flowerName = flowerName
self.finalResultsFile = finalResultsFile
self.blastOptions = blastOptions
blastOptions.roundsOfCoordinateConversion = 2
def __init__(self, indir, outdir, pattern, filteredSamples, includeCoverage=False):
Target.__init__(self, time=0.25)
self.indir = indir
self.outdir = outdir
self.pattern = pattern
self.includeCoverage = includeCoverage
self.filteredSamples = filteredSamples
def __init__(self, options, refseq, outdir, readdir):
#Target.__init__(self, time=0.00025)
Target.__init__(self)
self.options = options
self.refseq = refseq
self.outdir = outdir
self.readdir = readdir
def __init__(self, halFile, genome, bedForJob, modelFile, output):
Target.__init__(self)
self.halFile = halFile
self.genome = genome
self.bedForJob = bedForJob
self.modelFile = modelFile
self.output = output
def __init__(self, options, outdir, halfile, genome2seq2len, type):
Target.__init__(self)
self.options = options
self.outdir = outdir
self.halfile = halfile
self.genome2seq2len = genome2seq2len
self.type = type #type has to be bed or wiggle
def __init__(self, readFastqFile, referenceFastaFile, outputSamFile,
options):
Target.__init__(self)
self.readFastqFile = readFastqFile
self.referenceFastaFile = referenceFastaFile
self.outputSamFile = outputSamFile
self.options = options #These are the options from cactus_expectationMaximisation
def __init__(self, samplenames, pair2stat, outbase, attr, opts):
Target.__init__(self)
self.names = samplenames
self.pair2stat = pair2stat
self.outbase = outbase
self.attr = attr
self.opts = opts
def __init__(self, indir, outdir, size, topFreqs, samSizes):
Target.__init__(self)
self.indir = indir #simSampleTempDir
self.outdir = outdir #simTempDir/sampleID
self.size = size
self.topFreqs = topFreqs
self.samSizes = samSizes
def __init__(self, indir, outdir, opts=None, *args):
Target.__init__(self)
self.indir = indir
self.outdir = outdir
self.opts = opts
self.args = args
self.name2obj = None
def __init__(self, outputDir, experiments):
Target.__init__(self)
self.experiments = experiments
self.outputDir = outputDir
#Quadruples of (readFastqFile, readType, referenceFastaFile, mapper) to pairs of (analyses, resultsDir)
self.experimentHash = {}
#Mappers
self.mappers = set()
#Read file readType double
self.readFastqFiles = set()
#Reference files
self.referenceFastaFiles = set()
#readTypes
self.readTypes = set()
#base mappers (lastz, last, bwa, blasr)
self.baseMappers = set()
#Store all this stuff
for readFastqFile, readType, referenceFastaFile, mapper, analyses, resultsDir in self.experiments:
self.experimentHash[((readFastqFile, readType), referenceFastaFile,
mapper)] = (analyses, resultsDir)
self.mappers.add(mapper)
self.readFastqFiles.add((readFastqFile, readType))
self.referenceFastaFiles.add(referenceFastaFile)
self.readTypes.add(readType)
self.baseMappers.add(re.findall("[A-Z][a-z]*", mapper.__name__)[0])
def find_analyses(target, recordsToAnalyze, templateFastqFiles, complementFastqFiles, references, outputDir):
"""takes a set of records to analyze and finds the corresponding sequences and creates alignment targets"""
files = {"template":[], "complement":[]}
logger.info("Finding template analyses")
for fastqFile in templateFastqFiles:
for name, seq, qual in fastqRead(fastqFile):
if name in recordsToAnalyze:
outfile = os.path.join(target.getGlobalTempDir(), "template_" + name)
files["template"].append(outfile)
ref_name, ref_start, ref_stop = recordsToAnalyze[name]
ref_seq = references[ref_name][ref_start : ref_stop]
analysis = [name, seq, ref_name, ref_seq, outfile]
target.addChildTarget(Target.makeTargetFn(analyze, args=analysis))
logger.info("Finding complement analyses")
for fastqFile in complementFastqFiles:
for name, seq, qual in fastqRead(fastqFile):
if name in recordsToAnalyze:
outfile = os.path.join(target.getGlobalTempDir(), "complement_" + name)
files["complement"].append(outfile)
ref_name, ref_start, ref_stop = recordsToAnalyze[name]
ref_seq = references[ref_name][ref_start : ref_stop]
analysis = [name, seq, ref_name, ref_seq, outfile]
target.addChildTarget(Target.makeTargetFn(analyze, args=analysis))
target.setFollowOnTargetFn(merge, args=(files, outputDir))
def __init__(self, options): Target.__init__(self) self.options=options self.events=[] self.totalp=0 self.edges=[] self.historyScores=[]
def find_analyses(target, recordsToAnalyze, templateFastqFiles,
complementFastqFiles, references, outputDir):
"""takes a set of records to analyze and finds the corresponding sequences and creates alignment targets"""
files = {"template": [], "complement": []}
logger.info("Finding template analyses")
for fastqFile in templateFastqFiles:
for name, seq, qual in fastqRead(fastqFile):
if name in recordsToAnalyze:
outfile = os.path.join(target.getGlobalTempDir(),
"template_" + name)
files["template"].append(outfile)
ref_name, ref_start, ref_stop = recordsToAnalyze[name]
ref_seq = references[ref_name][ref_start:ref_stop]
analysis = [name, seq, ref_name, ref_seq, outfile]
target.addChildTarget(
Target.makeTargetFn(analyze, args=analysis))
logger.info("Finding complement analyses")
for fastqFile in complementFastqFiles:
for name, seq, qual in fastqRead(fastqFile):
if name in recordsToAnalyze:
outfile = os.path.join(target.getGlobalTempDir(),
"complement_" + name)
files["complement"].append(outfile)
ref_name, ref_start, ref_stop = recordsToAnalyze[name]
ref_seq = references[ref_name][ref_start:ref_stop]
analysis = [name, seq, ref_name, ref_seq, outfile]
target.addChildTarget(
Target.makeTargetFn(analyze, args=analysis))
target.setFollowOnTargetFn(merge, args=(files, outputDir))
def __init__(self, args):
Target.__init__(self)
self.clonefile = args[0]
self.vfile = args[1]
self.jfile = args[2]
self.dfile = args[3]
self.outdir = args[4]
def __init__(self, sample1, sample2, c2n2s_dir, outfile, opts):
Target.__init__(self)
self.sample1 = sample1
self.sample2 = sample2
self.c2n2s_dir = c2n2s_dir
self.outfile = outfile
self.opts = opts
def __init__(self, clone, indir, outfile, opts, s2g):
Target.__init__(self)
self.clone = clone
self.indir = indir
self.outfile = outfile
self.opts = opts
self.s2g = s2g
def __init__(self, c2n2s_dir, sams, indir, outdir, opts):
Target.__init__(self)
self.c2n2s_dir = c2n2s_dir
self.sams = sams
self.outdir = outdir
self.indir = indir
self.opts = opts
def __init__(self, indir, outdir, size, pair, cutoffs):
Target.__init__(self, time=0.00025)
self.indir = indir #simTempDir (which has simTempDir/sampleId/rep.pickle)
self.outdir = outdir #outdir/sims/batchId/sim-Id/sampling-Id
self.size = size
self.pair = pair
self.cutoffs = cutoffs
def __init__(self, exp, ref, sample, outdir, options):
Target.__init__(self)
self.exp = exp
self.ref = ref
self.sample = sample
self.outdir = outdir
self.options = options
def __init__(self, options,
sequences,
newickTree,
outputDir,
params):
#requiredSpecies,
#singleCopySpecies,
#referenceAlgorithm, minimumBlockDegree,
#blastAlignmentString, baseLevel, maxNumberOfChains, permutations,
#theta, useSimulatedAnnealing, heldOutSequence):
Target.__init__(self, cpu=4, memory=4000000000)
self.sequences = sequences
self.newickTree = newickTree
#self.requiredSpecies = requiredSpecies
#self.singleCopySpecies = singleCopySpecies
self.outputDir = outputDir
#self.referenceAlgorithm = referenceAlgorithm
#self.minimumBlockDegree = int(minimumBlockDegree)
#self.blastAlignmentString = blastAlignmentString
#self.baseLevel = baseLevel
#self.maxNumberOfChains = maxNumberOfChains
#self.permutations = permutations
#self.theta = theta
#self.useSimulatedAnnealing = useSimulatedAnnealing
self.options = options
#self.heldOutSequence = heldOutSequence
self.params = params
def __init__(self, genomes, genome2seq2len, halfile, options, outdir):
Target.__init__(self)
self.genomes = genomes
self.genome2seq2len = genome2seq2len
self.halfile = halfile
self.options = options
self.outdir = outdir
def __init__(self, outputss, outPaths, doSamplings, numSampless, headers):
Target.__init__(self)
self.outputss = outputss
self.outPaths = outPaths
self.doSamplings = doSamplings
self.numSampless = numSampless
self.headers = headers
def __init__(self, i, i2, options, events, datadir): Target.__init__(self) self.options=options self.i=i self.i2=i2 self.outdir=datadir self.events=events
def __init__(self, genome, seq2len, halfile, outdir, options):
Target.__init__(self)
self.genome = genome
self.seq2len = seq2len
self.halfile = halfile
self.outdir = outdir
self.options = options
def __init__(self, experiment, sample, dir, outdir, mask):
Target.__init__(self, time=0.00025)
self.exp = experiment
self.sample = sample
self.dir = dir
self.outdir = outdir
self.mask = mask
def __init__(self, nodesList, leafsDict, options):
Target.__init__(self)
self.options = options
self.nodesList = nodesList
self.nodeParentDict = lsc.buildNodeParentDict(self.nodesList)
self.leafsDict = leafsDict
self.nodeDict = lsc.buildNodesDict(self.nodesList, self.leafsDict)
def __init__(self, halfile, tree, bigbeddir, maxOut, minIn):
Target.__init__(self)
self.halfile = halfile
self.tree = tree
self.bigbeddir = bigbeddir
self.maxOut = maxOut
self.minIn = minIn
def __init__(self, options, trueMaf, predictedMaf, outputFile, params):
Target.__init__(self)
self.options = options
self.trueMaf = trueMaf
self.predictedMaf = predictedMaf
self.outputFile = outputFile
self.params = params
def __init__(self, options):
Target.__init__(self)
self.options = options
self.events = []
self.totalp = 0
self.edges = []
self.historyScores = []
def __init__(self, halfile, tree, bigbeddir, maxOut, minIn):
Target.__init__(self)
self.halfile = halfile
self.tree = tree
self.bigbeddir = bigbeddir
self.maxOut = maxOut
self.minIn = minIn
def __init__(self, halfile, names, outdir, maxOut, minIn):
Target.__init__(self)
self.halfile = halfile
self.names = names
self.outdir = outdir
self.maxOut = maxOut
self.minIn = minIn
def __init__(self, opts, positions, outputFile, speciesTree, positionSet):
Target.__init__(self)
self.opts = opts
self.positions = positions
self.outputFile = outputFile
self.speciesTree = speciesTree
self.positionSet = positionSet
def __init__(self, vj, sams, indir, outfile, sizetype):
Target.__init__(self)
self.vj = vj
self.sams = sams
self.indir = indir
self.outfile = outfile
self.sizetype = sizetype
def __init__(self, blocks, events, i, outputdir, options): Target.__init__(self) self.options=options self.blocks=blocks self.events=events self.outputdir=outputdir self.i = i
def __init__(self, tree, event, sleepTime, startTime, cpu):
Target.__init__(self, cpu=cpu)
self.tree = tree
self.event = event
self.sleepTime = sleepTime
self.startTime = startTime
self.cpu = cpu
def __init__(self, sample, samdir, outfile, func, *func_args):
Target.__init__(self)
self.sample = sample
self.samdir = samdir
self.outfile = outfile
self.func = func
self.func_args = func_args
def __init__(self, experiment, sample, dir, outdir, mask):
Target.__init__(self, time=0.00025)
self.exp = experiment
self.sample = sample
self.dir = dir
self.outdir = outdir
self.mask = mask
def __init__(self, tree, event, sleepTime, startTime, cpu):
Target.__init__(self, cpu=cpu)
self.tree = tree
self.event = event
self.sleepTime = sleepTime
self.startTime = startTime
self.cpu = cpu
def __init__(self, outDir, dataDir, genomes, psls, primaryKeyColumn):
Target.__init__(self)
self.outDir = outDir
self.genomes = genomes
self.psls = psls
self.primaryKeyColumn = primaryKeyColumn
self.tmpDir = dataDir
def __init__(self, events, pedgesfile, historyScores, totalp, ignore_cn):
Target.__init__(self)
self.events = events
self.pedgesfile = pedgesfile
self.historyScores = historyScores
self.totalp = totalp
self.ignore_cn = ignore_cn
def __init__(self, indir, minsam, maxsam, outdir, sampling):
Target.__init__(self)
self.indir = indir
self.minsam = minsam
self.maxsam = maxsam
self.outdir = outdir
self.sampling = sampling
def __init__(self, blocks, events, i, outputdir, options):
Target.__init__(self)
self.options = options
self.blocks = blocks
self.events = events
self.outputdir = outputdir
self.i = i
def __init__(self, genomeoutdir, wig, genome, othergenome, halfile, outdir):
Target.__init__(self)
self.genomeoutdir = genomeoutdir
self.wig = wig
self.genome = genome
self.othergenome = othergenome
self.halfile = halfile
self.outdir = outdir
def __init__(self, data_frame, signature_name, positive_samples, negative_samples, parameters, directory):
Target.__init__(self, time=10000)
self.data_frame = data_frame
self.signature_name = signature_name
self.positive_samples = positive_samples
self.negative_samples = negative_samples
self.parameters = parameters
self.directory = directory
def __init__(self, indir, halfile, genome2seq2len, bigwigdir, noLiftover, outdir):
Target.__init__(self)
self.indir = indir
self.halfile = halfile
self.genome2seq2len = genome2seq2len
self.bigwigdir = bigwigdir
self.noLiftover = noLiftover
self.outdir = outdir
def __init_(self, cladedir, halfile, query, queryBed, target, chrsizefile):
Target.__init__(self)
self.cladedir = cladedir
self.halfile = halfile
self.query = query
self.queryBed = queryBed
self.target = target
self.chrsizefile = chrsizefile
def __init__(self, uuid, path, out_dir, graph):
Target.__init__(self)
self.counts = defaultdict(float)
self.normalizing = 0.0
self.uuid = uuid
self.path = path
self.out_dir = out_dir
self.graph = graph
def __init__(self, peventsfile, trueID, historyScores, outname, outputdir,
binwidth):
Target.__init__(self)
self.events = pickle.load(open(peventsfile, 'rb'))
self.outname = outname
self.trueID = trueID
self.historyScores = historyScores
self.outputdir = outputdir
self.binwidth = binwidth
def __init__(self, outDir, resultsDir, simTrueMafDir, simName,
cactusRunTime):
Target.__init__(self)
self.outDir = outDir
self.resultsDir = resultsDir #Directory contains cactus cactusDisk and jobTree
#self.simNum = simNum
self.simTrueMafDir = simTrueMafDir
self.simName = simName
self.cactusRunTime = cactusRunTime
def __init__(self, readFastqFile, readType, referenceFastaFile, samFile,
outputDir):
Target.__init__(self)
self.readFastqFile = readFastqFile
self.referenceFastaFile = referenceFastaFile
self.samFile = samFile
self.outputDir = outputDir
self.readType = readType
print(str(self.samFile))
def __init__(self, newickTree, haplotypeSequences, assemblyFile, outputDir,
configFile, options):
Target.__init__(self, cpu=1, memory=8000000000)
self.newickTree = newickTree
self.haplotypeSequences = haplotypeSequences
self.assemblyFile = assemblyFile
self.outputDir = outputDir
self.configFile = configFile
self.options = options
def __init__(self, analysis, paradigm_setup, directory, nulls=None):
Target.__init__(self, time=10000)
self.analysis = analysis
self.paradigm_setup = paradigm_setup
self.directory = directory
if nulls is None:
self.nulls = self.paradigm_setup.nulls
else:
self.nulls = nulls
def __init__(self, newickTree, haplotypeSequences, assembliesDir,
outputDir, configFile, options):
Target.__init__(self)
self.newickTree = newickTree
self.haplotypeSequences = haplotypeSequences
self.assembliesDir = assembliesDir
self.outputDir = outputDir
self.configFile = configFile
self.options = options
def __init__(self, region, databaseString, outputDir, refSpecies, geneDir):
Target.__init__(self, time=120)
self.region = region
self.dbStr = databaseString
self.refSpecies = refSpecies
self.outputFile = os.path.join(outputDir,
"%s-%s.xml" % ("genemapChain", region))
self.geneFile = os.path.join(geneDir, "refGeneConverted.bed")