Skip to main content

Table 3 Performance of Random Forest (RF) final models using Amino acid and Dipeptide composition as feature inputs for multiclass classification

From: Prediction of peptidoglycan hydrolases- a new class of antibacterial proteins

Class

Sensitivity

Specificity

Accuracy

MCC

 

AAC

DPC

AAC

DPC

AAC

DPC

AAC

DPC

A

62.52

71.12

98.55

99.47

93.90

95.77

0.70

0.80

B

61.10

54.91

99.95

99.98

98.62

98.45

0.77

0.73

C

59.73

53.49

98.72

99.66

94.19

94.34

0.68

0.69

D

40.41

38.19

99.97

99.98

99.55

99.55

0.60

0.60

E

98.99

99.93

64.50

62.92

90.14

90.18

0.73

0.74

  1. Where, A = N-acetylmuramoyl-L-alanine amidases, B = Peptidases, C = Enzymes acting on Peptidoglycan chain, D = Unclassified, and E = Negative Dataset