Skip to main content

Table 3 Performance of the prediction models on the training set TS270

From: MutaCYP: Classification of missense mutations in human cytochromes P450

Model

MCC

Q2, %

R, %

P, %

LDA 5-fold CV

0.54 ± 0.04

82.96 ± 3.19

94.47 ± 1.65

84.17 ± 4.96

NN 5-fold CV

0.46 ± 0.10

79.26 ± 4.12

87.24 ± 6.58

84.87 ± 2.20

LDA-cons

0.53

82.59

92.89

84.72

NN-cons

0.53

81.85

89.34

86.27

MutaCYP

0.70

88.52

93.40

91.09

PolyPhen2/HumVar

0.61

84.07

86.80

90.96

PolyPhen2/HumDiv

0.58

83.70

90.36

87.68

SIFT

0.49

76.33

77.70

85.71

  1. LDA – linear model based on linear discriminant analysis.
  2. NN – non-linear model based on neural networks.
  3. LDA-cons and NN-cons – consensus models based on simple majority voting of 5 LDA or NN based models.
Back to article page

BMC Medical Genomics

ISSN: 1755-8794

Contact us