get_0_mismatches_from_merge.py

# This script takes a merged fasta file as an input, and puts reads that merged with 0 mismatch
# at the overlapped region into another fasta file. example commandline:
# 
# python get_0_mismatches_from_merge.py INPUT_FASTA OUTPUT_FASTA
#

import sys

sys.path.append('/bioware/pythonmodules/fastalib/')

import fastalib as u

fasta = u.SequenceSource(sys.argv[1])
output = u.FastaOutput(sys.argv[2])

while fasta.next():
    if fasta.pos % 10000 == 0:
        sys.stdout.write('\r[%s] %d reads processed so far' % (sys.argv[2], fasta.pos))
        sys.stdout.flush()
    if fasta.id.endswith('mismatches:0') and fasta.seq.find('n') == -1:
        output.store(fasta, split = False)

fasta.close()
print