Last active
September 7, 2018 20:03
-
-
Save dinovski/684f012fbb21a552d9d568a4c1d04637 to your computer and use it in GitHub Desktop.
change IUPAC nucleotide code to nucleotide
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 | |
usage=""" | |
iupac_change.py <infile> <outfile> | |
change IUPAC nucleotide codes for tab delimited file with CHR, ID, REF, ALT columns | |
""" | |
import sys | |
import os | |
if len(sys.argv) < 3: | |
print usage | |
vcf_file = sys.argv[1] | |
f = open(vcf_file, "r") | |
outfile = open(sys.argv[2], "w") | |
for line in f.readlines(): | |
delim = line.split('\t') | |
alt = delim[4] | |
ref = delim[3] | |
if alt == "A" or alt == "T" or alt =="C" or alt == "G": | |
alt = alt | |
elif alt == "K" and ref == "G": | |
alt = "T" | |
elif alt =="K" and ref == "T": | |
alt = "G" | |
elif alt == "M" and ref == "A": | |
alt = "C" | |
elif alt == "M" and ref == "C": | |
alt = "A" | |
elif alt == "R" and ref == "A": | |
alt = "G" | |
elif alt == "R" and ref == "G": | |
alt = "A" | |
elif alt == "S" and ref == "G": | |
alt = "C" | |
elif alt == "S" and ref == "C": | |
alt = "G" | |
elif alt == "W" and ref == "A": | |
alt = "T" | |
elif alt == "W" and ref == "T": | |
alt = "A" | |
elif alt == "Y" and ref == "C": | |
alt = "T" | |
elif alt == "Y" and ref == "T": | |
alt = "C" | |
delim[4] = alt | |
#convert delim list to string | |
line = "\t".join(delim) | |
outfile.write(line) | |
f.close() | |
outfile.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment