dumbly concatenate paired end illumina sequences

cat_pairs.py

#!/usr/bin/env python
import gzip
import sys
from glob import glob
from os.path import basename
import re
from Bio import SeqIO

def gopen(fi, *args, **kwargs):
    if fi.endswith('.gz'):
        return gzip.open(fi, *args, **kwargs)
    else:
        return open(fi, *args, **kwargs)

def cat_reads(r1_fn, r2_fn, concat=False):
    cat_out = gopen(re.sub('_R1', '', basename(r1_fn)), 'wt')
    R1 = SeqIO.parse(gopen(r1_fn, 'rt'), "fastq")
    R2 = SeqIO.parse(gopen(r2_fn, 'rt'), "fastq")
    for r1, r2 in zip(R1, R2):
            SeqIO.write(r1 + r2.reverse_complement(), cat_out, 'fastq')

if __name__ == '__main__':
    filenames = [x for x in glob('./*.fq')]
    for r1, r2 in zip(filenames[0::2], filenames[1::2]):
        cat_reads(r1, r2)