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
|
# Make target_tf from AtRegNet.txt and from AtRegNet.csv (much bigger).
# Usage: python3 make_target_tf_agris.py > ../Data/information/target_tf_agris.txt
# Last modified on 16 Feb 2021 by Hui Lan <lanhui@zjnu.edu.cn>
import codecs, sys
class GeneIdValidator:
def __init__(self, organism):
self.org = organism
def isvalid(self, ID):
if self.org == 'ath':
return ID.startswith('AT') and len(ID) == 9 and ID[3] == 'G'
else:
return False
def make_dictionary(fname, separator):
sample_id = 'C0000000000001'
id_validator = GeneIdValidator('ath')
f = codecs.open(fname, encoding='utf-8', errors='ignore')
lines = f.readlines()
f.close()
d = {}
duplicate = 0
for line in lines[1:]:
line = line.strip()
lst = line.split(separator)
if len(lst) >= 5:
tf0 = lst[1].upper().strip()
target0 = lst[4].upper().strip()
tf_lst = [x.strip() for x in tf0.split('/') if id_validator.isvalid(x)]
target_lst = [x.strip() for x in target0.split('/') if id_validator.isvalid(x)]
for tf in tf_lst:
for target in target_lst:
k = target + '.' + tf
if k in d:
duplicate += 1
else:
d[k] = [target, tf, sample_id]
return duplicate, d
if __name__ == '__main__':
duplicate1, d = make_dictionary('../Data/information/AtRegNet.txt', '\t') # OSU AtRegNet, an older version. Most are confirmed tf target pairs???
duplicate2, d2 = make_dictionary('../Data/information/AtRegNet2.csv', ',') # OSU AtRegNet downloaded in Feb 2021. This file includes much more tf target pairs (confirmed, unconfirmed, dap-seq, etc)
d.update(d2) # combine two dictionaries into one.
print('pairs: %d' % len(d), file=sys.stderr)
print('duplicate: %d' % (duplicate1 + duplicate2), file=sys.stderr)
for k in sorted(d.keys()):
print('\t'.join(d[k]))
|
