Created
April 27, 2012 21:32
-
-
Save ypandit/2513421 to your computer and use it in GitHub Desktop.
Solution for pseudogene issue in GFF3 for Artemis
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys, os | |
if len(sys.argv) != 2: | |
print 'You seem to have forgotten to provide the input GGF3 file.' | |
exit() | |
if __name__ == "__main__": | |
found = False | |
END = outofbound = issues = 0 | |
outfile = open(os.path.basename(sys.argv[1]).replace(".gff", "_corrected.gff"), 'w') | |
with open (sys.argv[1], 'r') as file: | |
for line in file: | |
if line.startswith('##sequence-region') is True: | |
END = (line.split(' '))[2].rstrip() | |
try: | |
row = line.split('\t') | |
if found and row[2] == 'exon': | |
issues += 1 | |
continue | |
if row[2] == 'pseudogene': | |
found = True | |
if row[2] == 'gap' and row[3] > END: | |
outofbound += 1 | |
continue | |
outfile.write(line) | |
except IndexError: | |
outfile.write(line) | |
outfile.close() | |
#print "# of issues = %d" % issues | |
#print "# Out of bound gaps = %d" % outofbound |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment