Easy Illumina Index Counter

index_counter.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
(c) 2014 Brant Faircloth || http://faircloth-lab.org/
All rights reserved.

This code is distributed under a 3-clause BSD license. Please see
LICENSE.txt for more information.

Created on 14 October 2014 09:35 CDT (-0500)
"""

import gzip
from collections import Counter

barcode_combo_count = Counter()
with gzip.open('Undetermined_S0_L001_R1_001.fastq.gz', 'rb') as infile:
    for line in infile:
        if line.startswith('@'):
            ls =line.strip().split(' ')
            barcodes = ls[-1]
            barcode_combo_count.update([barcodes.split(":")[-1]])


# get most common 10
barcode_combo_count.most_common(10)
# get total count of all reads
sum(barcode_combo_count.values())

# get a subset of reads matching some barcode pattern - this
# assumes dual-indexes
new_counter = Counter({i:j for i,j in barcode_combo_count.iteritems() if "+AGATCTCG" in i})