Minimal GeneSeqer to GFF3 converter

gsq2gff3.py

#!/usr/bin/env python
import re, sys

# Usage: gsq2gff3 < in.gsq > out.gff3

print "##gff-version   3"
for line in sys.stdin:
  line = line.rstrip()
  matches = re.search("hqPGS_(.+)[+-]_(.+)([+-])\s\((.+)\)", line)
  if not matches:
    continue

  template = "%s\tGeneSeqer\tEST_match\t%%s\t%%s\t.\t%c\t.\tID=%s" % (matches.group(1), matches.group(3), matches.group(2))
  for alignpart in matches.group(4).split(","):
    coords = alignpart.split("  ")
    print template % (coords[0], coords[1])