Skip to main content

Table 1 The prediction performance comparison of PCA-EELM with PCA-SVM

From: Prediction of protein-protein interactions from amino acid sequences with ensemble extreme learning machines and principal component analysis

Classification Model

Test set

Sens. (%)

Prec. (%)

Accu. (%)

MCC (%)

Testing Time (Seconds)

PCA-EELM

1

86.60

87.32

87.03

77.42

45.1482

 

2

85.97

87.34

86.77

77.04

45.4615

 

3

85.95

87.68

86.95

77.30

46.7825

 

4

86.60

88.10

87.47

78.07

43.2015

 

5

85.64

87.52

86.73

76.97

44.1237

 

Average

86.15+0.43

87.59+0.32

87.00+0.29

77.36+0.44

44.9435+1.36

PCA-SVM

1

81.76

82.86

82.16

70.69

52.6035

 

2

85.77

81.65

83.37

72.25

51.7143

 

3

87.52

80.67

83.10

71.78

51.7143

 

4

85.77

82.44

83.77

72.79

51.8547

 

5

85.48

79.09

81.74

70.09

51.4335

 

Average

85.26+2.12

81.34+1.51

82.82+0.85

71.52+1.1

.51.8641+0.44