Table 7 The performance of the top 10 motifs on fp 10 developed using hybrid features (DPC-LEN and motif score) on all three datasets.

From: In Silico tool for predicting, designing and scanning IL-2 inducing peptides

Dataset

Classification

Sens

Spec

ACC

AUC

MCC

Main dataset

ET

0.75

0.73

73.76

0.82

0.48

ET + None

0.77

0.74

76

0.84

0.51

ET + KOOLMAN

0.77

0.73

75

0.83

0.50

ET + BETTS-RUSSELL

0.76

0.73

75

0.82

0.50

Alternate dataset 1

ET

0.79

0.83

79

0.89

0.60

ET + None

0.77

0.84

80

0.90

0.61

ET + KOOLMAN

0.75

0.83

79

0.87

0.59

ET + BETTS-RUSSELL

0.77

0.83

80

0.88

0.60

Alternate dataset 2

ET

0.70

0.71

70

0.79

0.41

ET + None

0.71

0.73

73

0.80

0.44

ET + KOOLMAN

0.70

0.73

72

0.79

0.43

ET + BETTS-RUSSELL

0.69

0.75

72

0.79

0.44

Back to article page