Table 2 Performance of amino acid composition-based SVM models for predicting hemotoxicity of peptides using five-fold cross-validation.

From: A Web Server and Mobile App for Computing Hemolytic Potency of Peptides

Approach

Sn (%)

Sp (%)

Acc (%)

MCC

HemoPI-1 main dataset

 NT10

93.8

92.9

93.3

0.86

 CT10

84.4

89.0

87.0

0.74

 NTCT10

95.7

94.0

94.9

0.90

 NT15

93.8

95.7

94.8

0.90

 CT15

89.7

93.8

91.8

0.84

 NTCT15

96.5

96.1

96.3

0.93

HemoPI-2 main dataset

 NT10

71.6

71.1

71.4

0.43

 CT10

67.7

70.1

68.8

0.38

 NTCT10

77.9

77.0

77.5

0.55

 NT15

74.9

73.9

74.5

0.49

 CT15

74.3

69.9

72.4

0.44

 NTCT15

77.7

76.2

77.0

0.54

  1. Sn: Sensitivity; Sp: Specificity; Acc: Accuracy; MCC: Matthews correlation coefficient; NT10: first 10 residues from N-terminus; CT10: last 10 residues from C-terminus; NTCT10: NT10+CT10.