Skip to main content

Advertisement

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.