Skip to main content

Table 5 Comparative results of SSF-DDI on the DrugBank dataset in transductive setting (%)

From: SSF-DDI: a deep learning method utilizing drug sequence and substructure features for drug–drug interaction prediction

Method

ACC

AUC

F1

Prec

Rec

AP

CNN-DDI

94.65

98.35

94.81

92.06

97.72

97.93

MR-GNN

93.23

97.31

93.39

91.14

95.76

96.45

SSI-DDI

92.48

97.01

92.65

90.59

94.8

96.11

GAT-DDI

92.03

96.28

92.29

89.47

95.29

94.64

GMPNN-CS

95.31

98.45

95.4

93.58

97.29

97.91

DGNN-DDI

96.09

98.94

96.16

94.72

97.88

98.51

SSF-DDI (ours)

96.45

98.92

96.5

95.22

97.89

98.53

  1. The best results are highlighted in bold
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us