Skip to main content

Table 6 Experimental results of different classifiers based on 10-fold cross-validation

From: Predicting potential microbe-disease associations based on auto-encoder and graph convolution network

Dataset:

MDAID

Experiments

Acc(%)

Pre (%)

Recall (%)

F1-score (%)

AUC (%)

AUPR (%)

MLP

90.25

90.24

90.26

90.24

96.54

96.30

LR

85.10

85.10

85.09

85.08

92.87

92.05

SVM

89.67

89.67

89.65

89.654

95.54

94.84

NB

79.47

79.75

79.47

79.40

85.66

86.89

DT

85.49

85.48

85.48

85.47

90.04

91.22

ABC

84.61

84.61

84.59

84.59

92.91

92.28

GBC

88.53

88.55

88.53

88.51

95.45

94.99

KNN

87.51

87.67

87.52

87.48

94.01

94.23

RF

90.38

90.38

90.39

90.37

96.68

96.48

DF

90.89

90.89

90.88

90.87

97.00

96.90

Dataset:

HMDAD

Experiments

Acc(%)

Pre (%)

Recall (%)

F1-score (%)

AUC (%)

AUPR (%)

MLP

88.11

88.20

88.14

88.08

95.48

95.87

LR

86.67

83.93

83.71

83.59

89.61

84.37

SVM

87.78

88.19

87.94

87.73

94.27

91.89

NB

77.44

78.11

77.46

77.30

84.48

85.82

DT

84.00

84.28

84.01

83.94

89.40

90.92

ABC

85.33

85.65

85.43

85.28

93.47

91.96

GBC

86.44

86.61

86.50

86.40

95.45

95.87

KNN

87.00

87.22

87.03

86.95

93.83

94.34

RF

87.44

87.63

87.47

87.41

95.41

95.86

DF

88.11

88.35

88.21

88.08

96.32

96.72

  1. The bold result indicates the best one in each column