Skip to main content

Table 1 The performance of various SVM models of Pg-activators (SAK, SK, tPA and UK) with non Pg- activators, was developed using AC, DC,PSSM profiles and Hybrid models in five-fold cross validation

From: Support vector machine (SVM) based multiclass prediction with basic statistical analysis of plasminogen activators

 

ACC(%)

SN(%)

SP(%)

MCC

Parameters

Methods

    

γ

C

AC

88.37

95.24

83.50

0.87

25

450

DC

84.32

97.01

75.31

0.83

3

375

PSSM

87.61

95.77

81.81

0.86

3

400

Hybrid (AC + DC)

85.63

97.71

77.06

0.85

1

450

  1. AC- Amino acid composition, DC dipeptide composition, PSSM position specific scoring matrix, ACC accuracy, SN- Sensitivity, SP- specificity, MCC- Mathews correlation coefficient,C: tradeoff value, γ- gamma factor (a parameter in RBF kernel).
Back to article page

BMC Research Notes

ISSN: 1756-0500

Contact us