blob: 99e2290488fc6d1fe66dfadf9ec5a348b618c0e7 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
|
from __future__ import absolute_import, print_function, division
import os
import glob
import gzip
from base import webqtlConfig
def process_genofiles(geno_dir=webqtlConfig.GENODIR):
os.chdir(geno_dir)
for geno_file in glob.glob("*"):
if geno_file.lower().endswith(('.geno', '.geno.gz')):
#group_name = genofilename.split('.')[0]
sample_list = get_samplelist(geno_file)
def get_samplelist(geno_file):
genofilename = os.path.join(webqtlConfig.GENODIR, geno_file)
if os.path.isfile(genofilename + '.gz'):
genofilename += '.gz'
genofile = gzip.open(genofilename)
else:
genofile = open(genofilename)
for line in genofile:
line = line.strip()
if not line:
continue
if line.startswith(("#", "@")):
continue
break
headers = line.split()
if headers[3] == "Mb":
samplelist = headers[4:]
else:
samplelist = headers[3:]
return samplelist
|
