Created
April 3, 2018 15:13
-
-
Save lorenapr92/ce695fe80127b4b4a40a6d4521099571 to your computer and use it in GitHub Desktop.
Parsing python code for vcf files. We can use this to parse vcf file based on their POS for specific genes
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 sys | |
infile = 'chr7first300.vcf' | |
class ParseV: | |
def __init__(self,infile,List=None,samplestuff=None): | |
self.infile = infile | |
self.List = [] | |
self.samplestuff=[] # creates a new empty list, think this addresses the problem from last time where the mistaken use of class variable with a mutable data type? | |
with open ('chr7first300.vcf','r') as file: | |
for line in file.readlines(): | |
line=line.rstrip() | |
if line.startswith('##'): | |
continue | |
elif line.startswith('#'): | |
parts= line.split('\t') | |
self.samplestuff= parts[:] | |
#print(samplestuff) | |
else: | |
if line.startswith('7'): | |
P=line.split() | |
POS=P[1] | |
if '16692' <= POS <= '16742': | |
ID = P[2] | |
CHROM = P[0] | |
POSITION= P[1] | |
Ref = P[3] | |
ALT = P[4] | |
QUAL= P[5] | |
FILTER= P[6] | |
INFO= P[7] | |
FORMAT= P[8] | |
FIRST=P[9:] | |
self.List.append([CHROM,ID,POSITION,Ref,ALT,QUAL,FILTER,INFO,FORMAT,FIRST]) | |
#print(self.List) | |
#vcf.close # close file | |
#return List | |
def outfile(self): # need to work on this part | |
out = open('chr7foxp2.out','w') | |
out.write(str(self.samplestuff) +'\n'+ str(self.List)) | |
#for i in self.List: | |
# out.write(str(i[0]) + "\t" + str(i[1]) + "\t" + str(i[2]) + "\t" + str(i[3]) + "\t" + str(i[4]) + "\t" + str(i[5]) + "\t" + str(i[6]) + "\t" + str(i[7]) + "\t" + str(i[8]) + "\n") | |
out.close # close file | |
tired = ParseV(infile) | |
tired.outfile() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment