Created
June 6, 2014 17:33
-
-
Save adamrp/309966469128b495f23c to your computer and use it in GitHub Desktop.
Calculates the GC content across all sequences in an input fasta file
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
#!/usr/bin/env python | |
from sys import argv | |
from skbio.parse.sequences.fasta import parse_fasta | |
def calculate_gc_content(input_fasta): | |
gc = 0 | |
total_length = 0 | |
for _, seq in parse_fasta(input_fasta): | |
seq = seq.lower() | |
total_length += len(seq) | |
gc += seq.count('g') | |
gc += seq.count('c') | |
return 1.0 * gc / total_length | |
if __name__ == '__main__': | |
with open(argv[1], 'U') as input_fasta: | |
gc_content = calculate_gc_content(input_fasta) | |
print 'The total fraction of G/C in the input FASTA file is:', gc_content | |
print 'Note that this calculation not take into account degeneracies.' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment