Skip to main content

Table 3 Hyperparameter tuning experiments

From: TEC-miTarget: enhancing microRNA target prediction based on deep learning of ribonucleic acid sequences

 

Accuracy (%)

Sensitivity (%)

Specificity (%)

PPV (%)

NPV (%)

F1 score (%)

Score

\({n}_{h}\)

       

1

96.47

95.85

97.10

97.06

95.90

96.45

5.7883

2

94.89

94.47

95.30

95.25

94.53

94.86

5.6930

4

96.46

95.43

97.48

97.42

95.53

96.42

5.7874

8

93.74

94.71

92.78

92.90

94.62

93.80

5.6255

\({d}_{1}\)

       

128

95.33

95.72

94.94

94.98

95.69

95.35

5.7201

256

96.47

95.85

97.10

97.06

95.90

96.45

5.7883

512

93.21

93.60

92.82

92.87

93.56

93.23

5.5929

1024

96.31

96.07

96.56

96.53

96.10

96.30

5.7787

\(ks\)

       

1

87.47

93.26

81.69

83.57

92.39

88.15

5.2653

5

96.28

96.20

96.36

96.35

96.21

96.28

5.7768

9

96.47

95.85

97.10

97.06

95.90

96.45

5.7883

13

95.28

95.46

95.10

95.11

95.45

95.29

5.7169

\({p}_{0}\)

       

0.25

93.13

94.97

91.29

91.59

94.78

93.25

5.5901

0.5

96.47

95.85

97.10

97.06

95.90

96.45

5.7883

0.75

95.91

94.79

97.03

96.96

94.91

95.86

5.7546

1.0

95.97

96.50

95.44

95.48

96.47

95.99

5.7585

  1. The bold font indicates the best performance