Skip to main content

Table 3 Comparison of performance with different repeated times of RCNN unit for sub-classifiers \(f_{5}, f_{10}, f_{15}\)

From: Protein–protein interaction prediction based on ordinal regression and recurrent convolutional neural networks

Times

Accuracy (%)

Precision (%)

Sensitivity (%)

Specificity (%)

\(F_{1}\)Score (%)

Sub-classifier \(f_{5}\)

1

82.31

88.55

88.72

60.39

88.64

2

88.19

92.88

91.85

72.59

92.25

3

89.29

93.01

93.23

76.16

93.12

4

90.00

93.47

93.69

77.77

93.58

5

90.35

93.25

94.42

79.61

93.83

Sub-classifier \(f_{10}\)

1

78.62

77.10

83.56

80.57

80.20

2

84.86

86.09

84.41

83.58

85.24

3

87.71

88.05

88.25

87.34

88.15

4

88.29

88.27

89.27

88.32

88.77

5

89.15

89.24

89.90

89.05

89.57

Sub-classifier \(f_{15}\)

1

81.38

69.28

50.50

84.20

58.42

2

92.30

81.32

91.21

96.79

85.98

3

95.86

91.84

92.21

97.27

92.03

4

95.90

92.70

91.36

97.00

92.03

5

96.17

93.03

92.10

97.25

92.57

  1. The values in each column represents the experimental results for each criterion of performance. Maximal values in each column is shown in bold