def clean_reference_alignment(region, refname,
VERBOSE=0,
subtype='B',
):
'''Clean reference alignment'''
from hivwholeseq.reference import load_custom_reference
from Bio import SeqIO
from Bio.Align import MultipleSeqAlignment
from hivwholeseq.cross_sectional.filenames import (
get_subtype_reference_alignment_filename)
fn = get_subtype_reference_alignment_filename(region, subtype=subtype,
refname=refname,
VERBOSE=VERBOSE)
ali = AlignIO.read(fn, 'fasta')
nseqs = len(ali)
ali = MultipleSeqAlignment(filter(filter_sequence, ali))
nseqsnew = len(ali)
if VERBOSE >= 2:
print refname, region, subtype+':', nseqsnew, 'of', nseqs, 'seqs kept'
return ali
def clean_reference_alignment(
region,
refname,
VERBOSE=0,
subtype='B',
):
'''Clean reference alignment'''
from hivwholeseq.reference import load_custom_reference
from Bio import SeqIO
from Bio.Align import MultipleSeqAlignment
from hivwholeseq.cross_sectional.filenames import (
get_subtype_reference_alignment_filename)
fn = get_subtype_reference_alignment_filename(region,
subtype=subtype,
refname=refname,
VERBOSE=VERBOSE)
ali = AlignIO.read(fn, 'fasta')
nseqs = len(ali)
ali = MultipleSeqAlignment(filter(filter_sequence, ali))
nseqsnew = len(ali)
if VERBOSE >= 2:
print refname, region, subtype + ':', nseqsnew, 'of', nseqs, 'seqs kept'
return ali
def get_subtype_reference_alignment(region, subtype='B',
refname='HXB2',
type='nuc',
VERBOSE=0):
'''Get the observables from subtype B reference alignments'''
from Bio import AlignIO
ali_fn = get_subtype_reference_alignment_filename(region,
subtype=subtype,
refname=refname,
type=type,
VERBOSE=VERBOSE)
ali = AlignIO.read(ali_fn, 'fasta')
return ali
def get_subtype_reference_alignment(region,
subtype='B',
refname='HXB2',
type='nuc',
VERBOSE=0):
'''Get the observables from subtype B reference alignments'''
from Bio import AlignIO
ali_fn = get_subtype_reference_alignment_filename(region,
subtype=subtype,
refname=refname,
type=type,
VERBOSE=VERBOSE)
ali = AlignIO.read(ali_fn, 'fasta')
return ali
# Script
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Align to reference',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--region', required=True,
help='Region to anign (e.g. V3)')
parser.add_argument('--reference', default='HXB2',
help='Reference to use for alignment')
parser.add_argument('--verbose', type=int, default=0,
help='Verbosity level [0-4]')
parser.add_argument('--subtype', default='B',
help='Subtype to analyze')
args = parser.parse_args()
region = args.region
refname = args.reference
VERBOSE = args.verbose
subtype = args.subtype
ali = clean_reference_alignment(region, refname,
subtype=subtype,
VERBOSE=VERBOSE)
fn = get_subtype_reference_alignment_filename(region, subtype=subtype,
refname=refname,
VERBOSE=VERBOSE)
AlignIO.write(ali, fn, 'fasta')
description='Align to reference',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--region',
required=True,
help='Region to anign (e.g. V3)')
parser.add_argument('--reference',
default='HXB2',
help='Reference to use for alignment')
parser.add_argument('--verbose',
type=int,
default=0,
help='Verbosity level [0-4]')
parser.add_argument('--subtype', default='B', help='Subtype to analyze')
args = parser.parse_args()
region = args.region
refname = args.reference
VERBOSE = args.verbose
subtype = args.subtype
ali = clean_reference_alignment(region,
refname,
subtype=subtype,
VERBOSE=VERBOSE)
fn = get_subtype_reference_alignment_filename(region,
subtype=subtype,
refname=refname,
VERBOSE=VERBOSE)
AlignIO.write(ali, fn, 'fasta')
