Count and report the index sequences (aka barcode tags) in an Illumina FASTQ file

report_barcodes.py

#!/bin/env python
#
# Count and report the barcode tags in a fastq file from Illumina
# sequencing platform
#
import sys
import FASTQFile
fastq_file = sys.argv[1]
tags = {}
for read in FASTQFile.FastqIterator(fastq_file):
    tag = read.seqid.index_sequence
    if tag not in tags:
        tags[tag] = 1
    else:
        tags[tag] += 1
# Sort tags into order, most to least frequent
ordered_tags = sorted(tags,cmp=lambda x,y: cmp(tags[y],tags[x]))
print "Total # unique barcode sequences: %d" % len(ordered_tags)
for tag in ordered_tags:
    print "%s\t%d" % (tag,tags[tag])