Created
May 10, 2013 16:49
My code, with improvents Thomas Koch, and lelledumbo.
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 re | |
import string | |
def main(): | |
file = open("Homo_sapiens.GRCh37.67.dna_rm.chromosome.Y.fa","r") | |
a = 0 | |
t = 0 | |
g = 0 | |
c = 0 | |
for line in file: | |
if not line.startswith(">"): | |
g += line.count("G") | |
c += line.count("C") | |
a += line.count("A") | |
t += line.count("T") | |
totalBaseCount = a + t + c + g | |
gcCount = g + c | |
gcFraction = float(gcCount) / totalBaseCount | |
print( gcFraction * 100 ) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment