Skip to main content

Table 6 Validation (accuracy) percentage by SVM models trained on AAC, DC and hybrid features.

From: A Support Vector Machine based method to distinguish proteobacterial proteins from eukaryotic plant proteins

AAC

Serratia marcescens (127)

Acidovorax citrulli (314)

Rhizobium fredii (16)

Solanum lycopersicum (413)

Phaseolus vulgaris (159)

Cucurbita pepo (15)

30

78.74

98.09

75

93.46

94.97

100

50

70.87

96.18

75

94.19

96.23

100

90

70.87

97.77

75

93.46

96.86

100

DC

      

30

73.23

96.82

75

94.19

97.48

100

50

75.59

97.45

68.75

94.92

96.84

100

90

74.8

97.77

62.5

95.16

98.72

100

Hybrid (AAC+DC)

      

30

74.8

96.5

75

95.4

98.74

100

50

79.53

99.04

81.25

93.46

97.48

100

90

81.1

99.04

79.53

93.95

98.11

100

  1. The accuracy is calculated by dividing the number of correct predictions by total number of protein inputs. The numbers of reviewed proteins are shown in parentheses.