def testBoundingRegionsChrInUnsortedOrder(self):
self._setUpShelve()
brTuples = [BoundingRegionTuple(GenomeRegion('TestGenome', 'chrM', 1000, 2000), 5), \
BoundingRegionTuple(GenomeRegion('TestGenome', 'chr21', 0, 1000000), 10), \
BoundingRegionTuple(GenomeRegion('TestGenome', 'chr21', 2000000, 2500000), 20)]
self._brShelve.storeBoundingRegions(brTuples, ['chr21', 'chrM'],
sparse=True)
def _decorateGESource(self, geSource):
brRegionList = geSource.getBoundingRegionTuples()
if self._countElsInBoundingRegions:
brTuples = [BoundingRegionTuple(region, 0) for region in brRegionList]
return GEBoundingRegionElementCounter(geSource, brTuples)
else:
brTuples = [BoundingRegionTuple(region, len(region)) for region in self._brRegionList]
return BrTuplesGESourceWrapper(geSource, brTuples)
def testBoundingRegionsUnsortedInChr(self):
self._setUpShelve()
brTuples = [BoundingRegionTuple(GenomeRegion('TestGenome', 'chr21', 2000000, 2500000), 20),\
BoundingRegionTuple(GenomeRegion('TestGenome', 'chr21', 0, 1000000), 10)]
self.assertRaises(InvalidFormatError,
self._brShelve.storeBoundingRegions,
brTuples, ['chr21'],
sparse=True)
def testBoundingRegionIncorrectCountDense(self):
self._setUpShelve()
brTuples = [BoundingRegionTuple(GenomeRegion('TestGenome', 'chr21', 0, 1000000), 1000000), \
BoundingRegionTuple(GenomeRegion('TestGenome', 'chr21', 2000000, 2500000), 500000), \
BoundingRegionTuple(GenomeRegion('TestGenome', 'chrM', 1000, 2000), 500)]
self.assertRaises(InvalidFormatError,
self._brShelve.storeBoundingRegions,
brTuples, ['chr21', 'chrM'],
sparse=False)
def _getIter(elList,
valDataType,
valDim,
edgeWeightDataType,
edgeWeightDim,
brList=[]):
geIter = MyGeIter(valDataType, valDim, edgeWeightDataType, edgeWeightDim)
for i in xrange(len(elList)):
ge = GenomeElement(genome=elList[i][0],
chr=elList[i][1],
start=elList[i][2],
end=elList[i][3])
if len(elList[i]) == 5:
for prefix in elList[i][4]:
setattr(ge, prefix, elList[i][4][prefix])
geIter.iter.append(ge)
for i in xrange(len(brList)):
br = GenomeRegion(genome=brList[i][0],
chr=brList[i][1],
start=brList[i][2],
end=brList[i][3])
geIter.boundingRegionTuples.append(
BoundingRegionTuple(br, brList[i][4]))
return geIter
def _appendBoundingRegionTuple(self):
#if self._genomeElement.chr is not None:
# brRegion = GenomeRegion(self._genome, self._genomeElement.chr, 0, self._elCount)
if self._chr is not None:
brRegion = GenomeRegion(self._genome, self._chr, 0, self._elCount)
self._boundingRegionTuples.append(
BoundingRegionTuple(brRegion, self._elCount))
def _appendBoundingRegionTuple(self):
boundingRegion = GenomeRegion(genome=self._genome, chr=self._chr, start=self._start, \
end=self._getEnd(self._getFixedStepCurElStart()))
elCount = self._curElCountInBoundingRegion + (1 if self._isStepFunction
else 0)
self._boundingRegionTuples.append(
BoundingRegionTuple(boundingRegion, elCount))
def testBoundingRegionsNotPositive(self):
self._setUpShelve()
brTuples = [
BoundingRegionTuple(GenomeRegion('TestGenome', 'chr21', 0, 0), 1)
]
self.assertRaises(InvalidFormatError,
self._brShelve.storeBoundingRegions,
brTuples, ['chr21'],
sparse=True)
def getBoundingRegionTuples(self):
if self._boundingRegionTuples is None:
track = self._getTrack()
self._boundingRegionTuples = []
for region,tv in ((region, self._getTrackView(track, region)) for region in self._boundingRegions):
self._boundingRegionTuples.append(BoundingRegionTuple(region, tv.getNumElements()))
#self._removeBoundingRegionTuplesIfFullChrsAndNotFixedGapSize()
return self._boundingRegionTuples
def testGetBoundingInfoEmptyBoundingRegionSparse(self):
self._setUpShelve()
brTuples = [BoundingRegionTuple(GenomeRegion('TestGenome', 'chrM', 1000, 2000), 0), \
BoundingRegionTuple(GenomeRegion('TestGenome', 'chr21', 0, 1000000), 10), \
BoundingRegionTuple(GenomeRegion('TestGenome', 'chr21', 2000000, 2500000), 20)]
self._brShelve.storeBoundingRegions(brTuples, ['chr21'], sparse=True)
self.assertEquals(
BoundingRegionInfo(0, 1000000, 0, 30, 0, 470),
self._brShelve.getBoundingRegionInfo(
GenomeRegion('TestGenome', 'chr21', 50000, 52000)))
self.assertEquals(
BoundingRegionInfo(2000000, 2500000, 0, 30, 0, 470),
self._brShelve.getBoundingRegionInfo(
GenomeRegion('TestGenome', 'chr21', 2050000, 2052000)))
self.assertEquals(
BoundingRegionInfo(1000, 2000, 0, 0, 0, 0),
self._brShelve.getBoundingRegionInfo(
GenomeRegion('TestGenome', 'chrM', 1000, 2000)))
def getBoundingRegionTuples(self):
boundingRegionTuples = [x for x in self._getBoundingRegionTuples() \
if x.region.chr is not None]
if len(boundingRegionTuples) == 0:
from gtrackcore.input.core.GenomeElementSource import BoundingRegionTuple
from gtrackcore.track.core.GenomeRegion import GenomeRegion
from gtrackcore.metadata.GenomeInfo import GenomeInfo
geChrList = self.getAllChrs()
boundingRegionTuples = [BoundingRegionTuple( \
GenomeRegion(chr=chr, start=0, end=GenomeInfo.getChrLen(self._geSource.genome, chr)), \
self.getNumElementsForChr(chr) ) \
for chr in geChrList]
self._boundingRegionsAndGEsCorrespond = False
else:
self._boundingRegionsAndGEsCorrespond = True
return boundingRegionTuples
def getBoundingRegionTuples(self):
return [
BoundingRegionTuple(
GenomeRegion(genome='TestGenome', chr='chr21', start=0, end=1),
1)
]
tv = self._getTrackView(trackName, region, allowOverlaps)
self.assertEquals(chrElCountDict[chr], len([x for x in tv]))
def _getTrackView(self, trackName, region, allowOverlaps):
track = Track(trackName)
track.addFormatReq(TrackFormatReq(allowOverlaps=allowOverlaps))
return track.getTrackView(region)
def _getBoundingRegionTupleList(self, case, sortedAssertElList):
boundingRegions = [
br for br in sorted(case.boundingRegionsAssertList)
if br.region.chr is not None
]
if len(boundingRegions) > 0:
return [BoundingRegionTuple(GenomeRegion(self.GENOME, chr=br.region.chr, \
start=br.region.start if br.region.start is not None else 0, \
end=br.region.end if br.region.end is not None else \
GenomeInfo.getChrLen(self.GENOME, br.region.chr)), br.elCount)
for br in boundingRegions]
else:
totChrList = [ge.chr for ge in sortedAssertElList]
chrBrList = OrderedDict([(i, totChrList.count(i))
for i in sorted(set(totChrList))])
return [BoundingRegionTuple(GenomeRegion(self.GENOME, chr=chr, start=0, \
end=GenomeInfo.getChrLen(self.GENOME, chr)), elCount) \
for chr, elCount in chrBrList.iteritems()]
def _getCaseTrackView(self, case, br, allowOverlaps):
return self._getTrackView(self.TRACK_NAME_PREFIX + case.trackName, \
GenomeRegion(genome=self.GENOME, chr=br.chr, start=br.start, end=br.end), \
allowOverlaps=allowOverlaps)
def _commonStoreBoundingRegions(self, sparse):
brTuples = [BoundingRegionTuple(GenomeRegion('TestGenome', 'chr21', 0, 1000000), 10 if sparse else 1000000),\
BoundingRegionTuple(GenomeRegion('TestGenome', 'chr21', 2000000, 2500000), 20 if sparse else 500000),\
BoundingRegionTuple(GenomeRegion('TestGenome', 'chrM', 1000, 2000), 5 if sparse else 1000)]
self._brShelve.storeBoundingRegions(brTuples, ['chr21', 'chrM'],
sparse)
def getBoundingRegionTuples(self):
if self._boundingRegionTuples is None:
self._boundingRegionTuples = [BoundingRegionTuple(tv.genomeAnchor, tv.getNumElements()) for tv in self._trackViewDict.values()]
#self._removeBoundingRegionTuplesIfFullChrsAndNotFixedGapSize()
return self._boundingRegionTuples