def ccds_parser(self, ccds_file_handle, splice_padding):
"""Parse a ccds line"""
genes = {}
exons = {}
for line in ccds_file_handle:
if not line.startswith('#') and len(line) > 1:
line = line.split('\t')
chrom = line[0].lstrip('chr')
transcript_id = line[1]
gene_id = line[2]
if is_number(line[7]) and is_number(line[8]):
feature_start = int(line[7])
feature_stop = int(line[8])
#TODO raise exception?
self.add_gene(genes, chrom, feature_start, feature_stop,
gene_id)
for interval in line[9][1:-1].split(','):
boundaries = (interval.split('-'))
exon_start = int(boundaries[0].lstrip())
exon_stop = int(boundaries[1].lstrip())
return genes, exons
def ccds_parser(self, ccds_file_handle, splice_padding):
"""Parse a ccds line"""
genes = {}
exons = {}
for line in ccds_file_handle:
if not line.startswith('#') and len(line) > 1:
line = line.split('\t')
chrom = line[0].lstrip('chr')
transcript_id = line[1]
gene_id = line[2]
if is_number(line[7]) and is_number(line[8]):
feature_start = int(line[7])
feature_stop = int(line[8])
#TODO raise exception?
self.add_gene(
genes,
chrom,
feature_start,
feature_stop,
gene_id
)
for interval in line[9][1:-1].split(','):
boundaries = (interval.split('-'))
exon_start = int(boundaries[0].lstrip())
exon_stop = int(boundaries[1].lstrip())
return genes, exons
def gff_parser(self, gff_file_handle, splice_padding, id_key='ID'):
"""Parse a gtf file"""
genes = {}
exons = {}
for line in gff_file_handle:
line = line.rstrip()
if not line.startswith('#') and len(line) > 1:
if line.startswith('>'):
break
transcript_id = ''
gene_id = ''
gene_name = ''
feature_start = 0
feature_stop = 0
line = line.split('\t')
if len(line) < 5:
line = line.split()
chrom = line[0].lstrip('chr')
if is_number(line[3]) and is_number(line[4]):
feature_start = int(line[3])
feature_stop = int(line[4])
#TODO Raise exception?
for information in line[8].split(';'):
entry = information.split('=')
if entry[0] == 'transcript_id':
transcript_id = entry[1][1:-1]
if entry[0] == 'gene_id':
gene_id = entry[1][1:-1]
if entry[0] == 'gene_name':
gene_name = entry[1][1:-1]
if entry[0] == id_key:
gene_id = entry[1]
if line[2] in ['gene', 'CDS']:
self.add_gene(
genes,
chrom,
feature_start,
feature_stop,
gene_id
)
elif line[2] == 'exon':
self.add_exon(
exons,
chrom,
feature_start,
feature_stop,
transcript_id,
splice_padding
)
return genes,exons
def ccds_parser(ccds_file_handle, splice_padding=2):
"""
Parser a file in the ccds format.
Arguments:
ccds_file_handle (file_handle): An opened file in ccds format
splice_padding (int): An integer that describes how we should expand
the exons
Returns:
genes (dict): A dictionary chromosome ids as keys and gene dictionarys
as values.
exons (dict): A dictionary chromosome ids as keys and exon dictionarys
as values.
"""
genes = {}
exons = {}
for line in ccds_file_handle:
if not line.startswith('#') and len(line) > 1:
line = line.split('\t')
chrom = line[0].lstrip('chr')
transcript_id = line[1]
gene_id = line[2]
if chrom not in genes:
genes[chrom] = {}
if chrom not in exons:
exons[chrom] = {}
if is_number(line[7]) and is_number(line[8]):
feature_start = int(line[7])
feature_stop = int(line[8])
#TODO raise exception?
genes[chrom][gene_id] = get_coordinates(
genes[chrom],
feature_start,
feature_stop,
gene_id
)
for interval in line[9][1:-1].split(','):
boundaries = (interval.split('-'))
exon_start = int(boundaries[0].lstrip())
exon_stop = int(boundaries[1].lstrip())
exon_id = str(exon_start)+str(exon_stop)
if not exon_id in exons[chrom]:
exons[chrom][exon_id] = [
exon_start - splice_padding,
exon_stop + splice_padding,
exon_id
]
return genes, exons
def gtf_parser(self, gtf_file_handle, splice_padding):
"""Parse a gtf file"""
genes = {}
exons = {}
for line in gtf_file_handle:
if not line.startswith('#') and len(line) > 1:
transcript_id = ''
gene_id = ''
gene_name = ''
line = line.split('\t')
if len(line) < 5:
line = line.split()
chrom = line[0].lstrip('chr')
if is_number(line[3]) and is_number(line[4]):
feature_start = int(line[3])
feature_stop = int(line[4])
#TODO Raise exception?
info_field = line[8].split(';')[:-1]
for information in info_field:
entry = information.split()
if entry[0] == 'transcript_id':
transcript_id = entry[1][1:-1]
if entry[0] == 'gene_id':
gene_id = entry[1][1:-1]
if entry[0] == 'gene_name':
gene_name = entry[1][1:-1]
if line[2] == 'gene':
self.add_gene(
genes,
chrom,
feature_start,
feature_stop,
gene_id
)
elif line[2] == 'exon':
self.add_exon(
exons,
chrom,
feature_start,
feature_stop,
transcript_id,
splice_padding
)
return genes,exons
def gff_parser(self, gff_file_handle, splice_padding, id_key='ID'):
"""Parse a gtf file"""
genes = {}
exons = {}
for line in gff_file_handle:
line = line.rstrip()
if not line.startswith('#') and len(line) > 1:
if line.startswith('>'):
break
transcript_id = ''
gene_id = ''
gene_name = ''
feature_start = 0
feature_stop = 0
line = line.split('\t')
if len(line) < 5:
line = line.split()
chrom = line[0].lstrip('chr')
if is_number(line[3]) and is_number(line[4]):
feature_start = int(line[3])
feature_stop = int(line[4])
#TODO Raise exception?
for information in line[8].split(';'):
entry = information.split('=')
if entry[0] == 'transcript_id':
transcript_id = entry[1][1:-1]
if entry[0] == 'gene_id':
gene_id = entry[1][1:-1]
if entry[0] == 'gene_name':
gene_name = entry[1][1:-1]
if entry[0] == id_key:
gene_id = entry[1]
if line[2] in ['gene', 'CDS']:
self.add_gene(genes, chrom, feature_start, feature_stop,
gene_id)
elif line[2] == 'exon':
self.add_exon(exons, chrom, feature_start, feature_stop,
transcript_id, splice_padding)
return genes, exons
def gtf_parser(self, gtf_file_handle, splice_padding):
"""Parse a gtf file"""
genes = {}
exons = {}
for line in gtf_file_handle:
if not line.startswith('#') and len(line) > 1:
transcript_id = ''
gene_id = ''
gene_name = ''
line = line.split('\t')
if len(line) < 5:
line = line.split()
chrom = line[0].lstrip('chr')
if is_number(line[3]) and is_number(line[4]):
feature_start = int(line[3])
feature_stop = int(line[4])
#TODO Raise exception?
info_field = line[8].split(';')[:-1]
for information in info_field:
entry = information.split()
if entry[0] == 'transcript_id':
transcript_id = entry[1][1:-1]
if entry[0] == 'gene_id':
gene_id = entry[1][1:-1]
if entry[0] == 'gene_name':
gene_name = entry[1][1:-1]
if line[2] == 'gene':
self.add_gene(genes, chrom, feature_start, feature_stop,
gene_id)
elif line[2] == 'exon':
self.add_exon(exons, chrom, feature_start, feature_stop,
transcript_id, splice_padding)
return genes, exons
def test_int():
"""Test if is_number behave as suspected"""
obj = 2
assert is_number(obj) == True
def test_str_float():
"""Test if is_number behave as suspected"""
obj = '1.3'
assert is_number(obj) == True
def test_non_number():
"""Test if is_number behave as suspected"""
obj = 'a'
assert is_number(obj) == False
def test_float():
"""Test if is_number behave as suspected"""
obj = 2.5
assert is_number(obj) == True
def test_str_float():
"""Test if is_number behave as suspected"""
obj = '1.3'
assert is_number(obj) == True
def test_non_number():
"""Test if is_number behave as suspected"""
obj = 'a'
assert is_number(obj) == False
def gtf_parser(gtf_file_handle, splice_padding=2):
"""
Parse a file in the gtf format.
Arguments:
gtf_file_handle (file_handle): An opened file in gtf file format
splice_padding (int): An integer that describes how we should expand
the exons
Returns:
genes (dict): A dictionary chromosome ids as keys and gene dictionarys
as values.
exons (dict): A dictionary chromosome ids as keys and exon dictionarys
as values.
"""
genes = {}
exons = {}
for line in gtf_file_handle:
if not line.startswith('#') and len(line) > 1:
transcript_id = ''
gene_id = ''
gene_name = ''
line = line.split('\t')
if len(line) < 5:
line = line.split()
chrom = line[0].lstrip('chr')
feature_type = line[2]
if is_number(line[3]) and is_number(line[4]):
feature_start = int(line[3])
feature_stop = int(line[4])
info_field = line[8].split(';')[:-1]
for information in info_field:
entry = information.split()
if entry[0] == 'transcript_id':
transcript_id = entry[1].strip('"')
if entry[0] == 'gene_id':
gene_id = entry[1].strip('"')
if entry[0] == 'gene_name':
gene_name = entry[1].strip('"')
if feature_type == 'gene':
if chrom not in genes:
genes[chrom] = {}
genes[chrom][gene_id] = get_coordinates(
genes[chrom],
feature_start,
feature_stop,
gene_id
)
elif feature_type == 'exon':
if chrom not in exons:
exons[chrom] = {}
exon_id = str(feature_start) + str(feature_stop)
exons[chrom][exon_id] = [
feature_start - splice_padding,
feature_stop + splice_padding,
exon_id
]
return genes,exons
def gff_parser(gff_file_handle, splice_padding=2, id_key='ID'):
"""
Parse a file in the gff format.
Arguments:
gff_file_handle (file_handle): An opened file in gff file format
splice_padding (int): An integer that describes how we should expand
the exons
id_key (str): The key that defines the gene id in the info string
Returns:
genes (dict): A dictionary chromosome ids as keys and gene dictionarys
as values.
exons (dict): A dictionary chromosome ids as keys and exon dictionarys
as values.
"""
genes = {}
exons = {}
for line in gff_file_handle:
line = line.rstrip()
if not line.startswith('#') and len(line) > 1:
if line.startswith('>'):
break
transcript_id = ''
gene_id = ''
gene_name = ''
feature_start = 0
feature_stop = 0
line = line.split('\t')
if len(line) < 5:
line = line.split()
chrom = line[0].lstrip('chr')
feature_type = line[2]
if is_number(line[3]) and is_number(line[4]):
feature_start = int(line[3])
feature_stop = int(line[4])
#TODO Raise exception?
for information in line[8].split(';'):
entry = information.split('=')
if entry[0] == 'transcript_id':
transcript_id = entry[1][1:-1]
if entry[0] == 'gene_id':
gene_id = entry[1][1:-1]
if entry[0] == 'gene_name':
gene_name = entry[1][1:-1]
if entry[0] == id_key:
gene_id = entry[1]
if feature_type in ['gene', 'CDS', 'exon']:
if chrom not in genes:
genes[chrom] = {}
if chrom not in exons:
exons[chrom] = {}
if feature_type in ['gene', 'CDS']:
genes[chrom][gene_id] = get_coordinates(
genes[chrom],
feature_start,
feature_stop,
gene_id
)
elif line[2] == 'exon':
exon_id = str(feature_start) + str(feature_stop)
exon_feature = [
feature_start - splice_padding,
feature_stop + splice_padding,
exon_id
]
print(exon_feature)
exons[chrom][exon_id] = exon_feature
return genes,exons
