def inverseAssoc(self, gene):
"""Returns terms associated with gene"""
gene = Gene.canonicalName(gene)
for term in self.associations:
if gene in self[term]:
yield term
def fromFile(cls, inputFileName, taxons=None, dataset=None):
"""Decides file type and reads relevant data."""
debug("Reading gene associations file %s...%s" %
(inputFileName,
("" if dataset is None else " Dataset size is %d." %
len(dataset))))
#open = gzip.open if inputFileName.endswith(".gz") else __builtins__.open
if inputFileName.endswith('.pickle') or inputFileName.endswith(
'.pickle_reserved'):
# Serialized data = much faster
with open(inputFileName, 'rb') as f:
associations, alltaxons = pickle.load(f)
else:
associations = defaultdict(set)
alltaxons = set()
with open(inputFileName, 'rb') as associationFile:
for line in associationFile.read().decode('utf8').splitlines():
if line.startswith('!'): continue
line = line.split('\t')
taxon = {int(x.split(':')[1]) for x in line[12].split('|')}
alltaxons.update(taxon)
gene = Gene.canonicalName(line[2])
term = line[4]
if (taxons is None or taxons.intersection(taxon)) and \
(dataset is None or gene in dataset):
associations[term].add(gene)
debug("Finished reading gene associations file %s... " % inputFileName)
#if dataset is not None:
# d = dataset.difference(allgenes)
# if d:
# debug("Missing genes: %s!!!" % ", ".join(d))
return cls(associations, alltaxons, dataset)
def fromFile(cls, inputFileName, taxons = None, dataset = None):
"""Decides file type and reads relevant data."""
debug("Reading gene associations file %s...%s" % (inputFileName, ("" if dataset is None else " Dataset size is %d." % len(dataset))))
#open = gzip.open if inputFileName.endswith(".gz") else __builtins__.open
if inputFileName.endswith('.pickle') or inputFileName.endswith('.pickle_reserved'):
# Serialized data = much faster
with open(inputFileName, 'rb') as f:
associations, alltaxons = pickle.load(f)
else:
associations = defaultdict(set)
alltaxons = set()
with open(inputFileName, 'rb') as associationFile:
for line in associationFile.read().decode('utf8').splitlines():
if line.startswith('!'): continue
line = line.split('\t')
taxon = {int(x.split(':')[1]) for x in line[12].split('|')}
alltaxons.update(taxon)
gene = Gene.canonicalName(line[2])
term = line[4]
if (taxons is None or taxons.intersection(taxon)) and \
(dataset is None or gene in dataset):
associations[term].add(gene)
debug("Finished reading gene associations file %s... " % inputFileName)
#if dataset is not None:
# d = dataset.difference(allgenes)
# if d:
# debug("Missing genes: %s!!!" % ", ".join(d))
return cls(associations, alltaxons, dataset)
def inverseAssoc(self, gene):
"""Returns terms associated with gene"""
gene = Gene.canonicalName(gene)
for term in self.associations:
if gene in self[term]:
yield term