fasta_collapser.py

import sys

def get_next_fasta (fileObject):
	'''usage: for header, seq in get_next_fasta(fileObject):
	'''
	header = ''
	seq = ''
	#The following for loop gets the header of the first fasta
	#record. Skips any leading junk in the file
	for line in fileObject:
		if line.startswith('>'):
			header = line.strip()
			break

	for line in fileObject:
		if line.startswith('>'):
			yield header, seq
			header = line.strip()
			seq = ''
		else:
			seq += line.strip()
	#yield the last entry
	if header:
		yield header, seq

with open(sys.argv[1], 'r') as fasta, open(sys.argv[2], 'w') as outfile:
	seqset = set()
	count = 0
	for header, seq in get_next_fasta(fasta):
		if seq in seqset:
			continue
		else:
			seqset.add(seq)
			count += 1
			outfile.write(">%s\n%s\n" % (count, seq.upper()))