# This pre-prunes the count file to get it to a size that's more easily managed by R.

import gzip
OHANDLE=gzip.open("genic_subcounts.tsv.gz", "wb")
for line in gzip.open("genic_counts.tsv.gz", "rU"):
    segments=line.strip().split("\t")
    if segments[0]=="GeneID" or segments[0][1:3]=="ENS":
        OHANDLE.write(line)
    else:
        total=0
        for x in segments[2:]:
            total+=int(x)
        if total >= 10:
            OHANDLE.write(line)

OHANDLE.close()