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
70
71
72
73
74
75
76
|
# Author: Hui Lan <lanhui@zjnu.edu.cn>
class Overlap:
''' Compare two networks and compute hit rate '''
def __init__(self, predicted_edges={}, tau1=None, gold_standard_edges={}, tau2=None):
''' predicted_edges: dictionary {'TF * Target': score}
gold_standard_edges: dictionary {'TF * Target': score}
'''
def get_edges_above_threshold(d, tau):
d2 = {}
for k in d:
if d[k] > tau:
d2[k] = d[k]
return d2
self.pred = predicted_edges
self.true = gold_standard_edges
if tau1 != None:
self.pred = get_edges_above_threshold(self.pred, tau1)
if tau2 != None:
self.true = get_edges_above_threshold(self.true, tau2)
def getTP(self):
tp = 0
for k in self.pred:
if k in self.true:
tp += 1
return tp
def getFP(self):
fp = 0
for k in self.pred:
if not k in self.true:
fp += 1
return fp
def getNumberOfPositivesInPred(self):
return len(self.pred)
def getNumberOfPositivesInTrue(self):
return len(self.true)
if __name__ == '__main__':
f = open('../Data/temp/AtRegNet.20210208.csv')
AtRegNet_dict = {}
for line in f:
line = line.strip()
lst = line.split(',')
if lst[0] != 'TFName' and len(lst) > 4:
tf = lst[1].upper().strip()
target = lst[4].upper().strip()
AtRegNet_dict[tf+target] = 100
f.close()
f = open('../Data/temp/edges.txt')
BrainEdges_dict = {}
for line in f:
line = line.strip()
lst = line.split('\t')
tf = lst[1].split()[0]
target = lst[0].split()[0]
score = float(lst[8])
BrainEdges_dict[tf+target] = score
f.close()
overlap = Overlap(BrainEdges_dict, 3, AtRegNet_dict, 0)
print('TP:%d, PP:%d, Hit rate: %4.7f while comparing with AtRegNet.20210208.csv.' % (overlap.getTP(), overlap.getNumberOfPositivesInPred(), overlap.getTP()/overlap.getNumberOfPositivesInPred()))
|
