def loadFile(self, bedPath, binSize = 1, bgRate = None,
events = BedMutations.defaultEvents):
self.bins = defaultdict(int)
self.binSize = binSize
self.bgRate = bgRate
bm = BedMutations()
self.totalEvents = 0.0
for line in bm.scan(bedPath, events):
d = bm.distance()
if d is not None:
bin = d / binSize
self.bins[bin] += 1
self.totalEvents += 1.0
def identifyConservedIntervals(self, bedPath, outStream, maxPVal=0.05,
cutoff=0.5):
assert self.rate is not None
self.writtenCount = 0
self.writtenBases = 0
bm = BedMutations()
borderLength = int((1. / self.rate) * cutoff)
for line in bm.scan(bedPath, self.events):
d = bm.distance()
if d is not None and d > 2 * borderLength:
pval = self.bfProb(d)
if pval <= maxPVal:
startPos = int(bm.prevRange[1]) + borderLength
endPos = int(bm.range[0]) - borderLength
outStream.write("%s\t%d\t%d\t%f\t%s\t%s\n" % (
bm.sequence, startPos, endPos,
pval, bm.ancGenome, bm.genome))
self.writtenBases += (d - (2 * borderLength))
self.writtenCount += 1
def loadFile(self,
bedPath,
binSize=1,
bgRate=None,
events=BedMutations.defaultEvents):
self.bins = defaultdict(int)
self.binSize = binSize
self.bgRate = bgRate
bm = BedMutations()
self.totalEvents = 0.0
for line in bm.scan(bedPath, events):
d = bm.distance()
if d is not None:
bin = d / binSize
self.bins[bin] += 1
self.totalEvents += 1.0
def identifyConservedIntervals(self,
bedPath,
outStream,
maxPVal=0.05,
cutoff=0.5):
assert self.rate is not None
self.writtenCount = 0
self.writtenBases = 0
bm = BedMutations()
borderLength = int((1. / self.rate) * cutoff)
for line in bm.scan(bedPath, self.events):
d = bm.distance()
if d is not None and d > 2 * borderLength:
pval = self.bfProb(d)
if pval <= maxPVal:
startPos = int(bm.prevRange[1]) + borderLength
endPos = int(bm.range[0]) - borderLength
outStream.write("%s\t%d\t%d\t%f\t%s\t%s\n" %
(bm.sequence, startPos, endPos, pval,
bm.ancGenome, bm.genome))
self.writtenBases += (d - (2 * borderLength))
self.writtenCount += 1