def check_consensus_length(data_folder, adaID, fragment, VERBOSE=0):
'''Check consensus length, and if too short or absent complain'''
from Bio import AlignIO
ali_fn = get_reference_consensus_ali_filename(data_folder, adaID, fragment)
if not os.path.isfile(ali_fn):
if VERBOSE >= 2:
print 'Consensus alignment to reference not found', adaID, fragment
return False
ali = AlignIO.read(ali_fn, 'fasta')
len_ref = len(ali[0].seq.ungap('-'))
len_cons = len(ali[1].seq.ungap('-'))
if len_cons < len_ref - 200:
if VERBOSE >= 2:
print 'Consensus alignment to reference too short: ref', len_ref, 'cons:', len_cons
return False
elif len_cons > len_ref + 200:
if VERBOSE >= 2:
print 'Consensus alignment to reference too long: ref', len_ref, 'cons:', len_cons
return False
if VERBOSE >= 2:
print 'Consensus checked, has approximately the right length: ref', len_ref, 'cons:', len_cons
return True
def check_consensus_length(data_folder, adaID, fragment, VERBOSE=0):
'''Check consensus length, and if too short or absent complain'''
from Bio import AlignIO
ali_fn = get_reference_consensus_ali_filename(data_folder, adaID, fragment)
if not os.path.isfile(ali_fn):
if VERBOSE >= 2:
print 'Consensus alignment to reference not found', adaID, fragment
return False
ali = AlignIO.read(ali_fn, 'fasta')
len_ref = len(ali[0].seq.ungap('-'))
len_cons = len(ali[1].seq.ungap('-'))
if len_cons < len_ref - 200:
if VERBOSE >= 2:
print 'Consensus alignment to reference too short: ref', len_ref, 'cons:', len_cons
return False
elif len_cons > len_ref + 200:
if VERBOSE >= 2:
print 'Consensus alignment to reference too long: ref', len_ref, 'cons:', len_cons
return False
if VERBOSE >= 2:
print 'Consensus checked, has approximately the right length: ref', len_ref, 'cons:', len_cons
return True
if VERBOSE >= 2:
print ali[:, :30]
print ali[:, -30:]
print 'Lenghts: ref', len(refseq), 'consensus', len(
consensusseq)
len_ali = ali.get_alignment_length()
n_diff = sum(ali[0, i] != ali[1, i] for i in xrange(len_ali))
print 'Differences from ref:', n_diff, '(' + '{:3.1f}'.format(
100.0 * n_diff / len_ali) + '%)'
# Ungap consensus
consensusseq = SeqRecord(ali[1].seq, id=name, name=name)
if '-' in consensusseq:
consensusseq.seq = consensusseq.seq.ungap('-')
# Write output
outfile = get_consensus_filename(data_folder,
adaID,
frag_out,
trim_primers=True)
SeqIO.write(consensusseq, outfile, 'fasta')
AlignIO.write(
ali,
get_reference_consensus_ali_filename(data_folder, adaID,
fragment), 'fasta')
if store_allele_counts:
allele_counts.dump(
get_allele_counts_filename(data_folder, adaID, frag_out))
ali = align_muscle(refseq, consensusseq, sort=True)
if ali[0][-1] == '-':
start_nongap = len(ali[0]) - len(ali[0].seq.lstrip('-'))
end_nongap = len(ali[0].seq.rstrip('-'))
ali = ali[:, start_nongap: end_nongap]
if VERBOSE >= 2:
print ali[:, :30]
print ali[:, -30:]
print 'Lenghts: ref', len(refseq), 'consensus', len(consensusseq)
len_ali = ali.get_alignment_length()
n_diff = sum(ali[0, i] != ali[1, i] for i in xrange(len_ali))
print 'Differences from ref:', n_diff, '('+'{:3.1f}'.format(100.0 * n_diff / len_ali)+'%)'
# Ungap consensus
consensusseq = SeqRecord(ali[1].seq, id=name, name=name)
if '-' in consensusseq:
consensusseq.seq = consensusseq.seq.ungap('-')
# Write output
outfile = get_consensus_filename(data_folder, adaID, frag_out, trim_primers=True)
SeqIO.write(consensusseq, outfile, 'fasta')
AlignIO.write(ali, get_reference_consensus_ali_filename(data_folder, adaID, fragment), 'fasta')
if store_allele_counts:
allele_counts.dump(get_allele_counts_filename(data_folder, adaID, frag_out))
