Clean up a FASTA file that has unwanted characters in the description lines

clean_fasta_descs.py

import re
infile = 'dsim-all-chromosome-r1.3.reassembly1.updated_wsu1.fasta'

ref_count = 0
for line in open(infile,'r'):
	if line.startswith('>'):
		ref_count += 1
		print '>' + re.sub(r'[^0-9a-zA-Z_]', '', line)[:50]
	else:
		print line,