Skip to main content

Table 7 Comparison with embedding-based methods

From: A multitask transfer learning framework for the prediction of virus-human protein–protein interactions

Dataset

Model

AUC

AP

Precision

Recall

F1

Zhou’s H1N1

doc2vec

0.9601

0.9674

89.04

89.34

89.19

MotifTransformer

0.945

86.50

MTT

0.9461

0.9589

86.28

86.51

86.40

Zhou’s Ebola

Doc2vec

0.9781

0.9832

91.99

92.67

92.33

MotifTransformer

0.968

89.6

MTT

0.9680

0.9766

90.93

91.53

91.23

Denovo_slim

doc2vec

0.9644

0.9681

88.60

88.87

88.73

MTT

0.9221

0.9324

83.92

84.12

84.02

Barman

doc2vec

0.8671

0.8922

79.95

80.37

80.16

MTT

0.9804

0.9802

93.53

94.05

93.79

Bacillus

doc2vec

0.9900

0.9739

96.29

96.32

96.31

MTT

0.9997

0.9992

98.75

98.78

98.76

Yersina

doc2vec

0.9814

0.9510

94.50

94.52

94.51

MTT

0.9988

0.9971

97.32

97.34

97.32

Franci

doc2vec

0.9878

0.9606

96.77

96.84

96.81

MTT

0.9998

0.9996

98.95

99.03

98.99

  1. The bold font is used to highlight highest scores corresponding to each dataset