def _genbank_convert_fasta(in_handle, out_handle, alphabet=None):
"""Fast GenBank to FASTA (PRIVATE)."""
#We don't need to parse the features...
from Bio.GenBank.Scanner import GenBankScanner
records = GenBankScanner().parse_records(in_handle, do_features=False)
#For FASTA output we can ignore the alphabet too
return SeqIO.write(records, out_handle, "fasta")
def GenBankCdsFeatureIterator(handle, alphabet=Alphabet.generic_protein):
"""Breaks up a Genbank file into SeqRecord objects for each CDS feature.
Every section from the LOCUS line to the terminating // can contain
many CDS features. These are returned as with the stated amino acid
translation sequence (if given).
"""
#This calls a generator function:
return GenBankScanner(debug=0).parse_cds_features(handle, alphabet)
def GenBankIterator(handle):
"""Breaks up a Genbank file into SeqRecord objects.
Every section from the LOCUS line to the terminating // becomes
a single SeqRecord with associated annotation and features.
Note that for genomes or chromosomes, there is typically only
one record."""
#This calls a generator function:
return GenBankScanner(debug=0).parse_records(handle)
def reformat_genbank_first_line(first_line_inp, test_line=True):
str_out = ''
error_name = None
line_parts = first_line_inp.split()
if not 'LOCUS' in line_parts[0]:
error_name = 'Massive error: LOCUS not on first line'
return str_out, error_name
try:
bp_index = line_parts.index('bp')
except ValueError:
error_name = 'Missing bp'
return str_out, error_name
name_slice = line_parts[1:bp_index - 1]
name = '_'.join(name_slice)
padding_data = ' '.join([x.lower() for x in line_parts[bp_index - 1:]])
total_len = 12 + len(name) + len(padding_data)
if total_len >= 80:
extra_space = ' '
else:
extra_space = ' ' * (80 - total_len)
str_out = 'LOCUS' + ' ' + name + extra_space + padding_data + '\n'
print(str_out.split())
if test_line:
consumer = _FeatureConsumer(use_fuzziness=1,
feature_cleaner=FeatureValueCleaner())
try:
GenBankScanner(debug=1)._feed_first_line(consumer, str_out)
except Exception as err:
error_name = err
return str_out, error_name
def GenBankIterator(handle):
"""Breaks up a Genbank file into SeqRecord objects.
Every section from the LOCUS line to the terminating // becomes
a single SeqRecord with associated annotation and features.
Note that for genomes or chromosomes, there is typically only
one record.
This gets called internally by Bio.SeqIO for the GenBank file format:
>>> from Bio import SeqIO
>>> for record in SeqIO.parse("GenBank/cor6_6.gb", "gb"):
... print(record.id)
...
X55053.1
X62281.1
M81224.1
AJ237582.1
L31939.1
AF297471.1
Equivalently,
>>> with open("GenBank/cor6_6.gb") as handle:
... for record in GenBankIterator(handle):
... print(record.id)
...
X55053.1
X62281.1
M81224.1
AJ237582.1
L31939.1
AF297471.1
"""
# This calls a generator function:
return GenBankScanner(debug=0).parse_records(handle)