blob: 12ce35e99cc411a888814f696ddc12a759f93d45 (
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
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
|
#!/usr/bin/python
"""
Convert data dryad files to a BIMBAM _geno and _snps file
"""
import sys
sys.path.append("..")
def read_dryad_file(filename):
exclude_count = 0
marker_list = []
sample_dict = {}
sample_list = []
geno_rows = []
with open(filename, 'r') as the_file:
for i, line in enumerate(the_file):
if i > 0:
if line.split(" ")[1] == "no":
sample_name = line.split(" ")[0]
sample_list.append(sample_name)
sample_dict[sample_name] = line.split(" ")[2:]
else:
exclude_count += 1
else:
marker_list = line.split(" ")[2:]
for i, marker in enumerate(marker_list):
this_row = []
this_row.append(marker)
this_row.append("X")
this_row.append("Y")
for sample in sample_list:
this_row.append(sample_dict[sample][i])
geno_rows.append(this_row)
print(exclude_count)
return geno_rows
#for i, marker in enumerate(marker_list):
# this_row = []
# this_row.append(marker)
# this_row.append("X")
# this_row.append("Y")
# with open(filename, 'r') as the_file:
# for j, line in enumerate(the_file):
# if j > 0:
# this_row.append(line.split(" ")[i+2])
# print("row: " + str(i))
# geno_rows.append(this_row)
#
#return geno_rows
def write_bimbam_files(geno_rows):
with open('/home/zas1024/cfw_data/CFW_geno.txt', 'w') as geno_fh:
for row in geno_rows:
geno_fh.write(", ".join(row) + "\n")
def convert_dryad_to_bimbam(filename):
geno_file_rows = read_dryad_file(filename)
write_bimbam_files(geno_file_rows)
if __name__=="__main__":
input_filename = "/home/zas1024/cfw_data/" + sys.argv[1] + ".txt"
convert_dryad_to_bimbam(input_filename)
|
