def align_sequence(muscle_exe, sequence, rif=None, ):
"""sequence is a datatypes.Sequence, rif"""
if rif is None:
rif = datatypes.Sequence('RSRS', consts.RCRS)
seq_diff = NGclassify.SequenceDiff()
#print "Aligning sequence %s" % sequence.name
seq_diff.gen_diff(muscle_exe, rif, datatypes.Sequence(sequence.name, str(sequence)))
#print "-"*30
return seq_diff
def load_fasta_file(fname):
f = open(fname, 'r')
name = f.readline()[1:-1].strip()
seq = []
for line in f:
seq.append(line.strip())
return datatypes.Sequence(name, ''.join(seq).upper())
contig_seq_diff.regions.append([contig_seq_diff.start, contig_seq_diff.end])
else:
incoming_seqdiff = align_sequence(muscle_exe, contig)
incoming_seqdiff.find_segment()
contig_seq_diff.diff_list.extend(incoming_seqdiff.diff_list)
contig_seq_diff.regions.append([incoming_seqdiff.start, incoming_seqdiff.end])
print "\nSequence haplogroup assignment\n"
seq_classify = h_analysis(htrees, contig_seq_diff, contig_seq_diff.regions, mhcs_dict)
seq_classify.sample_name = sample_name
#print "\nSequence functional annotation\n"
print "Contig alignment to MHCS and rCRS"
m = list(seq_classify.mhcss)[0]
print "Aligning contigs to MHCS SeqDiff object"
its_mhcs = datatypes.Sequence(m, mhcs_dict[m])
#contig_mhcs_total_seqdiff = []
for x, contig in enumerate(contig_array):
if x == 0:
contig_mhcs_seq_diff = align_sequence(muscle_exe, contig, its_mhcs)
contig_mhcs_seq_diff.find_segment()
contig_mhcs_seq_diff.regions.append([contig_seq_diff.start, contig_seq_diff.end])
else:
incoming_mhcs_seqdiff = align_sequence(muscle_exe, contig, its_mhcs)
incoming_mhcs_seqdiff.find_segment()
contig_mhcs_seq_diff.diff_list.extend(incoming_mhcs_seqdiff.diff_list)
contig_mhcs_seq_diff.regions.append([incoming_mhcs_seqdiff.start, incoming_mhcs_seqdiff.end])
print "rCRS SeqDiff object"
rcrs = datatypes.Sequence('rCRS', consts.rcrs)
for x, contig in enumerate(contig_array):