def get_introns(self):
"""Returns a list of coordinates that represent the introns for
this transcript"""
introns = []
for i in range(len(self.exons)-1):
ex1 = self.exons[i]
ex2 = self.exons[i+1]
if self.strand == -1:
intron = Coord(self.chrom, ex2.end+1, ex1.start-1,
strand=self.strand)
else:
intron = Coord(self.chrom, ex1.end+1, ex2.start-1,
strand=self.strand)
intron.exon_5p = ex1
intron.exon_3p = ex2
introns.append(intron)
if self.intron_scores is not None:
intron.score = self.intron_scores[i]
if self.known_intron_flags is not None:
if self.known_intron_flags[i] == "1":
intron.is_known = True
else:
intron.is_known = False
return introns
def get_introns(self):
"""Returns a list of coordinates that represent the introns for
this transcript"""
introns = []
for i in range(len(self.exons) - 1):
ex1 = self.exons[i]
ex2 = self.exons[i + 1]
if self.strand == -1:
intron = Coord(self.chrom,
ex2.end + 1,
ex1.start - 1,
strand=self.strand)
else:
intron = Coord(self.chrom,
ex1.end + 1,
ex2.start - 1,
strand=self.strand)
intron.exon_5p = ex1
intron.exon_3p = ex2
introns.append(intron)
if self.intron_scores is not None:
intron.score = self.intron_scores[i]
if self.known_intron_flags is not None:
if self.known_intron_flags[i] == "1":
intron.is_known = True
else:
intron.is_known = False
return introns
def read_transcripts(path, chrom_dict):
"""Retrives all transcripts from the specified transcript file"""
f = open(path, "r")
transcripts = []
for row in txtfile.read_rows(f):
if row['ID'] == "NA":
tr_id = None
else:
tr_id = int(row['ID'])
if row["NAME"] == "NA":
name = None
else:
name = row['NAME']
# parse CDS start/end
if row['CDS.START'] == 'NA':
cds_start = None
else:
cds_start = int(row['CDS.START'])
if row['CDS.END'] == 'NA':
cds_end = None
else:
cds_end = int(row['CDS.END'])
strand = int(row['STRAND'])
chrom = chrom_dict[row['CHROM']]
# parse exons
exon_starts = [int(x) for x in row['EXON.STARTS'].split(",")]
exon_ends = [int(x) for x in row['EXON.ENDS'].split(",")]
if "EXON.SCORES" in row:
exon_scores = [float(x) for x in row['EXON.SCORES'].split(",")]
if len(exon_scores) != len(exon_starts):
raise ValueError("Expected %d exon scores, got %d" %
(len(exon_starts), len(exon_scores)))
else:
exon_scores = None
if ("INTRON.SCORES" in row) and (row['INTRON.SCORES'] != 'NA'):
intron_scores = [float(x) for x in row['INTRON.SCORES'].split(",")]
if len(intron_scores) != len(exon_starts) - 1:
raise ValueError("Expected %d intron scores, got %d" %
(len(exon_starts)-1, len(intron_scores)))
else:
intron_scores = None
if ("KNOWN.INTRON" in row) and (row['KNOWN.INTRON'] != "NA"):
intron_flags = row['KNOWN.INTRON'].split(",")
else:
intron_flags = None
exons = []
for i in range(len(exon_starts)):
exon = Coord(chrom, exon_starts[i], exon_ends[i], strand)
if exon_scores is not None:
exon.score = exon_scores[i]
exons.append(exon)
tr = Transcript(name=name, exons=exons,
cds_start=cds_start, cds_end=cds_end,
intron_scores=intron_scores,
known_intron_flags=intron_flags,
idnum=tr_id)
transcripts.append(tr)
f.close()
return transcripts
def read_transcripts(path, chrom_dict):
"""Retrives all transcripts from the specified transcript file"""
f = open(path, "r")
transcripts = []
for row in txtfile.read_rows(f):
if row['ID'] == "NA":
tr_id = None
else:
tr_id = int(row['ID'])
if row["NAME"] == "NA":
name = None
else:
name = row['NAME']
# parse CDS start/end
if row['CDS.START'] == 'NA':
cds_start = None
else:
cds_start = int(row['CDS.START'])
if row['CDS.END'] == 'NA':
cds_end = None
else:
cds_end = int(row['CDS.END'])
strand = int(row['STRAND'])
chrom = chrom_dict[row['CHROM']]
# parse exons
exon_starts = [int(x) for x in row['EXON.STARTS'].split(",")]
exon_ends = [int(x) for x in row['EXON.ENDS'].split(",")]
if "EXON.SCORES" in row:
exon_scores = [float(x) for x in row['EXON.SCORES'].split(",")]
if len(exon_scores) != len(exon_starts):
raise ValueError("Expected %d exon scores, got %d" %
(len(exon_starts), len(exon_scores)))
else:
exon_scores = None
if ("INTRON.SCORES" in row) and (row['INTRON.SCORES'] != 'NA'):
intron_scores = [float(x) for x in row['INTRON.SCORES'].split(",")]
if len(intron_scores) != len(exon_starts) - 1:
raise ValueError("Expected %d intron scores, got %d" %
(len(exon_starts) - 1, len(intron_scores)))
else:
intron_scores = None
if ("KNOWN.INTRON" in row) and (row['KNOWN.INTRON'] != "NA"):
intron_flags = row['KNOWN.INTRON'].split(",")
else:
intron_flags = None
exons = []
for i in range(len(exon_starts)):
exon = Coord(chrom, exon_starts[i], exon_ends[i], strand)
if exon_scores is not None:
exon.score = exon_scores[i]
exons.append(exon)
tr = Transcript(name=name,
exons=exons,
cds_start=cds_start,
cds_end=cds_end,
intron_scores=intron_scores,
known_intron_flags=intron_flags,
idnum=tr_id)
transcripts.append(tr)
f.close()
return transcripts
