Skip to main content

Table 3 Performance of the SVM using different feature subsets selected by mRMR

From: BLProt: prediction of bioluminescent proteins based on support vector machine and relieff feature selection

Feature subset

Sensitivity

(%)

Specificity

(%)

MCC

Test Accuracy (%)

CV Accuracy

100 features

65.96

84.21

0.5134

76.44

78.33

200 features

65.25

84.74

0.5132

76.44

78.5

300 features

65.96

83.68

0.5072

76.13

78.5

400 features

65.96

83.68

0.5072

76.13

78.33

500 features

65.96

83.68

0.5072

76.13

78.5

All features

63.12

78.19

0.4182

71.73

75.16

  1. MCC - Matthew's correlation coefficient, CV-Cross validation
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us