Skip to main content

Table 3 Cross-validated classification accuracy of all models. Average accuracy of categorical prediction in the 3- and 8-class problems is given as measured by the accuracy metric Q k , the Matthews correlation, r(), and SOV. All predictions are for 10-fold cross-validation on the training set (set-174). When standard errors are given in parentheses, the predicted value is the mean of five randomized repeats of cross-validation. The best results are shown in bold.

From: Prediction of protein continuum secondary structure with probabilistic models based on NMR solved structures

model 3-class problem 8-class problem
  Q 3 r(H) r(E) r(C) SOV Q 8
NBDP 61.2 0.40 0.34 0.41 52.9 46.1
PNN 76.4 (0.09) 0.68 0.62 0.57 67.4 61.4 (0.09)
CPNN 77.3 (0.07) 0.69 0.63 0.58 73.8 62.8 (0.05)
CCNN 77.2 (0.08) 0.69 0.63 0.59 72.8 62.5 (0.15)