def _embl_convert_fasta(in_handle, out_handle, alphabet=None):
"""Fast EMBL to FASTA (PRIVATE)."""
#We don't need to parse the features...
from Bio.GenBank.Scanner import EmblScanner
records = EmblScanner().parse_records(in_handle, do_features=False)
#For FASTA output we can ignore the alphabet too
return SeqIO.write(records, out_handle, "fasta")
def EmblCdsFeatureIterator(handle, alphabet=Alphabet.generic_protein):
"""Breaks up a EMBL 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 EmblScanner(debug=0).parse_cds_features(handle, alphabet)
def EmblIterator(handle):
"""Breaks up an EMBL 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 EmblScanner(debug=0).parse_records(handle)
def EmblIterator(handle):
"""Breaks up an EMBL 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 EMBL file format:
>>> from Bio import SeqIO
>>> for record in SeqIO.parse("EMBL/epo_prt_selection.embl", "embl"):
... print(record.id)
...
A00022.1
A00028.1
A00031.1
A00034.1
A00060.1
A00071.1
A00072.1
A00078.1
CQ797900.1
Equivalently,
>>> with open("EMBL/epo_prt_selection.embl") as handle:
... for record in EmblIterator(handle):
... print(record.id)
...
A00022.1
A00028.1
A00031.1
A00034.1
A00060.1
A00071.1
A00072.1
A00078.1
CQ797900.1
"""
# This calls a generator function:
return EmblScanner(debug=0).parse_records(handle)
