Skip to main content

Table 7 Performance comparison of various prediction methods on PDNA-62 by five-fold cross-validation

From: EL_PSSM-RT: DNA-binding residue prediction by integrating ensemble learning with PSSM Relation Transformation

Methods

ACC (%)

MCC

SN (%)

SP (%)

ST (%)

AUC

Dps-pred

79.10

−

40.30

81.80

61.10

−

Dbs-pssm

66.40

−

68.20

66.00

67.10

−

BindN

70.30

−

69.40

70.50

69.95

0.752

Dp-bind

78.10

0.49

79.20

77.20

78.20

−

DP-Bind

77.20

−

76.40

76.60

76.50

−

BindN-RF

78.20

−

78.10

78.20

78.15

0.861

BindN+

79.00

0.44

77.30

79.30

78.30

0.859

PreDNAa

79.40

0.42

76.80

79.70

78.30

−

EL_PSSM-RT

80.82

0.51

85.04

80.10

82.57

0.901

  1. adenotes PreDNA without using structure features