def __init__(self, genome, trackName, boundingRegions, globalCoords=True, allowOverlaps=False, printWarnings=True, *args, **kwArgs):
assert len(boundingRegions) > 0
GenomeElementSource.__init__(self, '', genome=genome, trackName=trackName, printWarnings=printWarnings, *args, **kwArgs)
self._boundingRegions = boundingRegions
self._isSorted = all([x == y for x,y in zip(boundingRegions, sorted(boundingRegions))])
self._boundingRegionTuples = None
self._allowOverlaps = allowOverlaps
self._globalCoords = globalCoords
self._prefixList = None
self._valDataType = 'float64'
self._valDim = 1
self._edgeWeightDataType = 'float64'
self._edgeWeightDim = 1
self._foundDataTypesAndDims = False
self._fileType = None
self._preProcVersion = None
self._id = None
self._undirectedEdges = None
self._foundTrackInfoBasedMetaData = False
self._fixedLength = None
self._fixedGapSize = None
self._reprIsDense = None
def __init__(self, fn, *args, **kwArgs):
GenomeElementSource.__init__(self, fn, *args, **kwArgs)
f = open(fn)
possibleHeader = f.readline()
if possibleHeader.startswith('track'):
self._numHeaderLines = 1
self._numCols = None
def __init__(self, genome, trackName, boundingRegions, globalCoords=True, allowOverlaps=False, printWarnings=True, *args, **kwArgs):
assert len(boundingRegions) > 0
GenomeElementSource.__init__(self, '', genome=genome, trackName=trackName, printWarnings=printWarnings, *args, **kwArgs)
self._boundingRegions = boundingRegions
self._isSorted = all([x == y for x,y in zip(boundingRegions, sorted(boundingRegions))])
self._boundingRegionTuples = None
self._allowOverlaps = allowOverlaps
self._globalCoords = globalCoords
self._prefixList = None
self._valDataType = 'float64'
self._valDim = 1
self._edgeWeightDataType = 'float64'
self._edgeWeightDim = 1
self._foundDataTypesAndDims = False
self._fileType = None
self._preProcVersion = None
self._id = None
self._undirectedEdges = None
self._foundTrackInfoBasedMetaData = False
self._doneCalculatingTrackViewBasedValues = False
self._fixedLength = None
self._fixedGapSize = None
self._reprIsDense = None
def __init__(self, fn, *args, **kwArgs):
GenomeElementSource.__init__(self, fn, *args, **kwArgs)
f = open(fn)
trackDef = f.readline().replace('\'', '"')
if not trackDef.startswith('track type="array"'):
raise InvalidFormatError(
'Track definition line must start with: track type="array". Line: '
+ trackDef)
header = self._parseHeader(trackDef)
if not all(key in header
for key in ['expScale', 'expStep', 'expNames']):
raise InvalidFormatError(
'Track definition line must define values for expScale, expStep and expNames: '
+ trackDef)
expNames = header['expNames']
if not all(expNames[i] == '"' for i in [0, -1]):
raise InvalidFormatError(
'expNames does not start and end in quote marks: ' + trackDef)
self._globExpCount = len(
[x for x in expNames[1:-2].split(',') if x != ''])
if self._globExpCount < 3:
raise InvalidFormatError(
'Microarray data must have at least 3 experiments. Length of expNames: '
+ str(self._globExpCount))
def _checkBoundingRegionSortedPair(self, lastBoundingRegion, br):
GenomeElementSource._checkBoundingRegionSortedPair(
self, lastBoundingRegion, br)
if br.start is not None and br.end is not None:
if lastBoundingRegion.end == br.start:
raise InvalidFormatError(
"Error: bounding regions '%s' and '%s' are adjoining (there is no gap between them)."
% (lastBoundingRegion, br))
def __init__(self,
genome,
trackName,
region,
valSlice,
valDataType='float64'):
GenomeElementSource.__init__(self,
None,
genome=genome,
trackName=trackName)
self._returnedOneElement = False
self._valSlice = valSlice
self._region = region
self._valDataType = valDataType
def __init__(self, fn, *args, **kwArgs):
GenomeElementSource.__init__(self, fn, *args, **kwArgs)
f = open(fn)
trackDef = f.readline()
if trackDef.startswith('track type=bedGraph'):
numHeaderLines = 1
else:
numHeaderLines = 0
headerLine = f.readline()
while headerLine.startswith('#'):
numHeaderLines += 1
headerLine = f.readline()
self._numHeaderLines = numHeaderLines
def __init__(self, fn, *args, **kwArgs):
GenomeElementSource.__init__(self, fn, *args, **kwArgs)
f = open(fn)
trackDef = f.readline()
if trackDef.startswith('track type=bedGraph'):
numHeaderLines = 1
else:
numHeaderLines = 0
headerLine = f.readline()
while headerLine.startswith('#'):
numHeaderLines += 1
headerLine = f.readline()
self._numHeaderLines = numHeaderLines
def __new__(cls,
regSpec,
binSpec,
genome=None,
categoryFilterList=None,
strictMatch=True,
includeExtraChrs=False): #,fileType):
if regSpec in ['file', 'track'] + getSupportedFileSuffixesForBinning():
#if fileType != 'bed':
# raise NotImplementedError
assert genome is not None
from gtrackcore.input.core.GenomeElementSource import GenomeElementSource
if regSpec == 'file':
geSource = GenomeElementSource(binSpec, genome=genome)
elif regSpec == 'track':
from gtrackcore.input.adapters.TrackGenomeElementSource import FullTrackGenomeElementSource
trackName = convertTNstrToTNListFormat(binSpec)
geSource = FullTrackGenomeElementSource(genome,
trackName,
allowOverlaps=False)
else:
geSource = GenomeElementSource(binSpec,
genome=genome,
suffix=regSpec)
if categoryFilterList is not None:
from gtrackcore.input.wrappers.GECategoryFilter import GECategoryFilter
geSource = GECategoryFilter(geSource,
categoryFilterList,
strict=strictMatch)
return cls._applyEnvelope(geSource)
else:
if binSpec == '*':
binSize = None
else:
binSize = parseShortenedSizeSpec(binSpec)
from gtrackcore.input.userbins.AutoBinner import AutoBinner
return AutoBinner(
parseRegSpec(regSpec,
genome,
includeExtraChrs=includeExtraChrs), binSize)
def __init__(self, fn, *args, **kwArgs):
GenomeElementSource.__init__(self, fn, *args, **kwArgs)
f = open(fn)
trackDef = f.readline().replace('\'','"')
if not trackDef.startswith('track type="array"'):
raise InvalidFormatError('Track definition line must start with: track type="array". Line: ' + trackDef)
header = self._parseHeader(trackDef)
if not all(key in header for key in ['expScale', 'expStep', 'expNames']):
raise InvalidFormatError('Track definition line must define values for expScale, expStep and expNames: ' + trackDef)
expNames = header['expNames']
if not all(expNames[i] == '"' for i in [0,-1]):
raise InvalidFormatError('expNames does not start and end in quote marks: ' + trackDef)
self._globExpCount = len( [x for x in expNames[1:-2].split(',') if x != ''] )
if self._globExpCount < 3:
raise InvalidFormatError('Microarray data must have at least 3 experiments. Length of expNames: ' + str(self._globExpCount))
def getGESource(fullFn,
fileSuffix,
extTrackName=None,
genome=None,
printWarnings=False):
from gtrackcore.input.core.GenomeElementSource import GenomeElementSource
return GenomeElementSource(fullFn,
suffix=fileSuffix,
forPreProcessor=True,
genome=genome,
trackName=extTrackName,
external=True,
printWarnings=printWarnings)
def _allGESources(self, trackName):
baseDir = createOrigPath(self._genome, trackName)
self._status = 'Trying os.listdir on: ' + baseDir
for relFn in sorted(os.listdir(baseDir)):
fn = os.sep.join([baseDir, relFn])
self._status = 'Checking file: ' + fn
if os.path.isdir(fn):
continue
fnPart = os.path.split(fn)[-1]
if fnPart[0] in ['.', '_', '#'] or fnPart[-1] in [
'~', '#'
]: #to avoid hidden files..
continue
self._status = 'Trying to create geSource from fn: ' + fn
yield GenomeElementSource(fn, self._genome, forPreProcessor=True)
def __init__(self, *args, **kwArgs):
GenomeElementSource.__init__(self, *args, **kwArgs)
self._boundingRegionTuples = []
self._chr = None
def __init__(self, *args, **kwArgs):
GenomeElementSource.__init__(self, *args, **kwArgs)
self._boundingRegionTuples = []
if self._getFile().read(1) != '>':
raise InvalidFormatError('FASTA file does not start with the ">" character.')
def getPrefixList(self):
return GenomeElementSource.getPrefixList(self)
def _getStrandFromString(cls, val):
if val == '?':
return BINARY_MISSING_VAL
else:
return GenomeElementSource._getStrandFromString(val)
def __init__(self, *args, **kwArgs):
GenomeElementSource.__init__(self, *args, **kwArgs)
self._returnedOneElement = False
def parseFirstDataLine(self):
return GenomeElementSource.parseFirstDataLine(self)
def parseFirstDataLine(self):
return GenomeElementSource.parseFirstDataLine(self)
def __init__(self, genome, trackName, region, valSlice, valDataType='float64'):
GenomeElementSource.__init__(self, None, genome=genome, trackName=trackName)
self._returnedOneElement = False
self._valSlice = valSlice
self._region = region
self._valDataType = valDataType
def __init__(self, windowSource, genome, trackName, chr, func):
GenomeElementSource.__init__(self, None, genome=genome, trackName=trackName)
self._windowSource = windowSource
self._windowIter = None
self._genomeElement.chr = chr
self._func = func
def __init__(self, fn, *args, **kwArgs):
GenomeElementSource.__init__(self, fn, *args, **kwArgs)
self._initAll()
self._handleTrackDefinitionLineIfPresent(self._getFile().readline())
self._parseFirstDeclarationLine()
def _checkBoundingRegionSortedPair(self, lastBoundingRegion, br):
GenomeElementSource._checkBoundingRegionSortedPair(self, lastBoundingRegion, br)
if br.start is not None and br.end is not None:
if lastBoundingRegion.end == br.start:
raise InvalidFormatError("Error: bounding regions '%s' and '%s' are adjoining (there is no gap between them)." % (lastBoundingRegion, br))
def __init__(self, *args, **kwArgs):
GenomeElementSource.__init__(self, *args, **kwArgs)
self._returnedOneElement = False
def _commonStandardizeGtrackFile(fn, genome, suffix=None):
geSource = GenomeElementSource(fn, genome, suffix=suffix)
composedFile = StdGtrackComposer(
GtrackElementStandardizer(geSource)).returnComposed()
return expandHeadersOfGtrackFileAndReturnComposer(
'', genome, strToUseInsteadOfFn=composedFile)
def _getStrandFromString(cls, val):
if val == '?':
return BINARY_MISSING_VAL
else:
return GenomeElementSource._getStrandFromString(val)
def __init__(self, *args, **kwArgs):
GenomeElementSource.__init__(self, *args, **kwArgs)
self._boundingRegionTuples = []
self._chr = None
def __init__(self, geSource, genome=None):
from gtrackcore.input.wrappers.GEDependentAttributesHolder import GEDependentAttributesHolder
geSource = GEDependentAttributesHolder(geSource)
GESourceWrapper.__init__(self, geSource)
GenomeElementSource.__init__(self, '', genome=genome)
def __init__(self, geSource, genome=None):
from gtrackcore.input.wrappers.GEDependentAttributesHolder import GEDependentAttributesHolder
geSource = GEDependentAttributesHolder(geSource)
GESourceWrapper.__init__(self, geSource)
GenomeElementSource.__init__(self, '', genome=genome)
def getPrefixList(self):
return GenomeElementSource.getPrefixList(self)
def __init__(self, fn, *args, **kwArgs):
GenomeElementSource.__init__(self, fn, *args, **kwArgs)
self._initAll()
self._handleTrackDefinitionLineIfPresent(self._getFile().readline())
self._parseFirstDeclarationLine()
