def getTrackExtractionOptions(genome, trackName):
from gtrackcore.track.core.Track import PlainTrack
from gtrackcore.input.userbins.UserBinSource import MinimalBinSource
from gtrackcore.extract.fileformats.FileFormatComposer import \
findMatchingFileFormatComposers, getComposerClsFromFileSuffix
tf = PlainTrack(trackName).getTrackView(
MinimalBinSource(genome)[0]).trackFormat
extractionOptions = []
matchingComposers = findMatchingFileFormatComposers(tf)
for composerInfo in matchingComposers:
allOverlapRules = tf.getAllOverlapRules()
for allowOverlaps in allOverlapRules:
extractionOptions.append( \
(composerInfo.trackFormatName.capitalize() + \
' ' + TrackExtractor.getFileFormatText(composerInfo.fileFormatName) + \
(', ' + (TrackExtractor.ALLOW_OVERLAPS_TRUE_TEXT if allowOverlaps else \
TrackExtractor.ALLOW_OVERLAPS_FALSE_TEXT) \
if len(allOverlapRules) > 1 else ''), \
composerInfo.fileSuffix) )
ti = TrackInfo(genome, trackName)
if ti.fileType != '':
try:
extractionOptions.append(
(TrackExtractor.ORIG_FILE_FORMAT_TEXT.capitalize() + \
' ' + TrackExtractor.getFileSuffixText(ti.fileType), \
getComposerClsFromFileSuffix(ti.fileType).getDefaultFileNameSuffix()))
except Exception, e:
print 'Error:', e
def getTrackExtractionOptions(genome, trackName):
from gtrackcore.track.core.Track import PlainTrack
from gtrackcore.input.userbins.UserBinSource import MinimalBinSource
from gtrackcore.extract.fileformats.FileFormatComposer import \
findMatchingFileFormatComposers, getComposerClsFromFileSuffix
tf = PlainTrack(trackName).getTrackView(MinimalBinSource(genome)[0]).trackFormat
extractionOptions = []
matchingComposers = findMatchingFileFormatComposers(tf)
for composerInfo in matchingComposers:
allOverlapRules = tf.getAllOverlapRules()
for allowOverlaps in allOverlapRules:
extractionOptions.append( \
(composerInfo.trackFormatName.capitalize() + \
' ' + TrackExtractor.getFileFormatText(composerInfo.fileFormatName) + \
(', ' + (TrackExtractor.ALLOW_OVERLAPS_TRUE_TEXT if allowOverlaps else \
TrackExtractor.ALLOW_OVERLAPS_FALSE_TEXT) \
if len(allOverlapRules) > 1 else ''), \
composerInfo.fileSuffix) )
ti = TrackInfo(genome, trackName)
if ti.fileType != '':
try:
extractionOptions.append(
(TrackExtractor.ORIG_FILE_FORMAT_TEXT.capitalize() + \
' ' + TrackExtractor.getFileSuffixText(ti.fileType), \
getComposerClsFromFileSuffix(ti.fileType).getDefaultFileNameSuffix()))
except Exception, e:
print 'Error:', e
def count_elements_in_all_bounding_regions(track_name, genome='testgenome', allow_overlaps=False):
bounding_regions = BoundingRegionShelve(genome, track_name, allow_overlaps).getAllBoundingRegions()
track = PlainTrack(track_name)
num_elements = 0
for tv in [track.getTrackView(region) for region in bounding_regions]:
num_elements += count_elements(tv)
return num_elements
def _createRandomizedNumpyArrays(self, binLen, starts, ends, vals, strands, ids, edges, weights, extras, origTrackFormat, region):
if self._minimal:
return numpy.array([]), None, None, None, None, None, None, OrderedDict()
intensityTV = PlainTrack(self._trackNameIntensity).getTrackView(region)
if len(intensityTV.valsAsNumpyArray())==0:
raise InvalidRunSpecException('Error: No intensity data available for sampling randomized locations in region' + \
str(region) + \
'. Please check that the intensity track was created with the same main track that is being randomized in this analysis.')
#intensityTV = PlainTrack(self._trackNameIntensity).getTrackView(self._origRegion) #Dependence on origRegion is not nice, but not a big problem..
if intensityTV.trackFormat.isDense():
assert intensityTV.trackFormat.isValued('number')
return self._createRandomizedNumpyArraysFromIntensityFunction(binLen, starts, ends, vals, strands, ids, edges, weights, extras, intensityTV)
else:
raise NotImplementedError
def _createRandomizedNumpyArrays(self, binLen, starts, ends, vals, strands,
ids, edges, weights, extras,
origTrackFormat, region):
if self._minimal:
return numpy.array(
[]), None, None, None, None, None, None, OrderedDict()
intensityTV = PlainTrack(self._trackNameIntensity).getTrackView(region)
if len(intensityTV.valsAsNumpyArray()) == 0:
raise InvalidRunSpecException('Error: No intensity data available for sampling randomized locations in region' + \
str(region) + \
'. Please check that the intensity track was created with the same main track that is being randomized in this analysis.')
#intensityTV = PlainTrack(self._trackNameIntensity).getTrackView(self._origRegion) #Dependence on origRegion is not nice, but not a big problem..
if intensityTV.trackFormat.isDense():
assert intensityTV.trackFormat.isValued('number')
return self._createRandomizedNumpyArraysFromIntensityFunction(
binLen, starts, ends, vals, strands, ids, edges, weights,
extras, intensityTV)
else:
raise NotImplementedError
def get_track_view(track_name, genome_region):
track = PlainTrack(track_name)
return track.getTrackView(genome_region)