def get_biotypes_from_attrs(attrs_tsv):
"""
Produces a set of biotypes from the biotype column of the attributes file.
This is the GeneType column, the 3rd column.
"""
# skip header line
return tuple(set(x[2] for x in iterRows(attrs_tsv, skipLines=1)))
def transcript_iterator(gp_file):
"""
Given a path to a standard genePred file return a list of GenePredTranscript objects
"""
with open(gp_file) as inf:
for tokens in iterRows(inf):
t = GenePredTranscript(tokens)
yield t.name, t
def psl_iterator(psl_file):
"""
Iterates over PSL file generating PslRow objects returning the name and the object itself
"""
with open(psl_file) as inf:
for tokens in iterRows(inf):
psl = PslRow(tokens)
yield psl.q_name, psl
def gp_chrom_filter(gp, filter_chrom=re.compile("(Y)|(chrY)")):
"""
Takes a genePred and lists all transcripts that match filter_chrom
"""
f_h = open(gp)
ret = set()
for x in iterRows(f_h):
if filter_chrom.match(x[1]):
ret.add(x[0])
return ret
def build_intervals_from_bed(bed, strand=None):
"""
Produces a sorted list of intervals from a BED
"""
r = set()
for l in iterRows(bed):
assert len(l) in [3, 4, 6, 12], 'Wrong BED format: {}'.format(len(l))
if strand is not None:
s = strand
elif len(l) < 6:
s = '.'
else:
s = l[5]
r.add(ChromosomeInterval(l[0], int(l[1]), int(l[2]), s))
r = sorted(r, key=lambda x: (x.chromosome, x.start))
return r
def find_num_rows(self):
return len(list(iterRows(open(self.input_file))))
def addTupleFile(self, fname, type=int, valCol=0, cntCol=1):
"add from a tab separated file of values of the specfied type and counts"
assert(self.isTupleData)
for row in iterRows(fname):
self.data.append((type(row[valCol]), int(row[cntCol])))
def addFile(self, fname, type=int, valCol=0):
"add from a tab separated file of values of the specfied type"
assert(not self.isTupleData)
for row in iterRows(fname):
self.data.append(type(row[valCol]))
def get_gp_ids(gp):
"""
Get all unique gene IDs from a genePred
"""
return {x[0] for x in iterRows(open(gp))}
def addTupleFile(self, fname, type=int, valCol=0, cntCol=1):
"add from a tab separated file of values of the specfied type and counts"
assert (self.isTupleData)
for row in iterRows(fname):
self.data.append((type(row[valCol]), int(row[cntCol])))
def addFile(self, fname, type=int, valCol=0):
"add from a tab separated file of values of the specfied type"
assert (not self.isTupleData)
for row in iterRows(fname):
self.data.append(type(row[valCol]))
def get_common_name_map(attrs):
common_name_map = {}
for x in iterRows(attrs, skipLines=1):
common_name_map[x[1]] = x[0]
return common_name_map
def get_tx_map(attrs):
tx_map = {}
for x in iterRows(attrs, skipLines=1):
tx_map[x[3]] = x[0]
return tx_map