Skip to main content

Table 2 The performance of SVM modules developed for discriminating aaRSs and non-aaRSs.

From: Prediction and classification of aminoacyl tRNA synthetases using PROSITE domains

S. No.

Name of Approach

Sensitivity

Specificity

Accuracy

MCC

1

Domain-based model

61.41

90.65

76.08

0.54

2

Amino acid Composition

74.38

82.97

78.63

0.6

3

Dipeptide composition

87.14

80.15

83.74

0.68

4

Hybrid approach1*

80.36

79.64

79.93

0.6

5

Hybrid approach2**

83.73

87.1

85.49

0.72

  1. * Hybrid approach1 SVM model based on amino acid composition domain features
  2. **Hybrid approach2 SVM model based on selected dipeptide composition and domain features
Back to article page