Skip to main content

Table 1 The properties of the benchmark datasets

From: Does adding the drug–drug similarity to drug–target interaction prediction methods make a noticeable improvement in their efficiency?

Dataset

Nuclear Receptors

GPCR

Ion Channels

Enzymes

\(N_{D}\)

54

223

210

445

\(N_{T}\)

26

95

204

664

\(N_{I}\)

90

635

1476

2926

Density

0.0641

0.0299

0.0344

0.0099

\(AD_{T}\)

3.46

6.68

7.24

4.41

\(AT_{D}\)

1.67

2.85

7.03

6.58

\(D_{1T}\)

72.22%

47.53%

38.57%

39.78%

\(T_{1D}\)

30.77%

35.79%

11.27%

43.37%