Small python script to subset fastq files

subset_fastq.py

"""Trim start from sequences.

Usages:
    bcbio_python subset_fastq.py in.fastq num_bases > out.fastq
"""

import sys

from Bio import SeqIO

from bcbio import utils

with utils.open_gzipsafe(sys.argv[1]) as in_handle:
    in_recs = SeqIO.parse(in_handle, "fastq")
    def trimmed(in_recs):
        trim = int(sys.argv[2])
        for rec in in_recs:
            yield rec[:trim]
    SeqIO.write(trimmed(in_recs), sys.stdout, "fastq")