Skip to main content

Table 5 Performance comparison between TEC-miTarget, miRAW, DeepMirTar, miTAR, and GraphTar on the DeepMirTar dataset

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

 

Accuracy (%)

Sensitivity (%)

Specificity (%)

PPV (%)

NPV (%)

F1 score (%)

DeepMirTar test set

      

miRAW

90.22

90.25

90.20

90.25

90.18

90.25

DeepMirTar

93.48

92.35

94.79

94.64

92.56

93.48

miTAR

92.74

92.74

92.74

92.80

92.67

92.77

GraphTar

92.22

92.21

92.23

92.26

92.16

92.23

TEC-miTarget

97.42

96.40

98.45

98.42

96.46

97.40

DeepMirTar independent test set

      

miRAW

40.63

40.63

NA

NA

NA

NA

DeepMirTar

50.00

50.00

NA

NA

NA

NA

miTAR

75.00

75.00

NA

NA

NA

NA

GraphTar

34.72

34.72

NA

NA

NA

NA

TEC-miTarget

81.25

81.25

NA

NA

NA

NA

  1. The bold font indicates the best performance
  2. NA represents that the value can’t be calculated because the corresponding dataset consists of only positive pairs