Table 4 Performance of different classifiers in the second layer
From: 6mA-StackingCV: an improved stacking ensemble model for predicting DNA N6-methyladenine site
Second-layer classifier | ACC (95%CI) | AUC (95%CI) |
|---|---|---|
random forest | 0.9448 (0.9425–0.9471) | 0.9817 (0.9794–0.9839) |
logistic regression | 0.9483 (0.9446–0.9521) | 0.9855 (0.9840–0.9869) |
decision tree | 0.9172 (0.9132–0.9212) | 0.9172 (0.9132–0.9212) |
XGBoost | 0.9476 (0.9447–0.9505) | 0.9849 (0.9836–0.9862) |
Gradient boosting | 0.9486 (0.9455–0.9517) | 0.9853 (0.9836–0.9870) |
LightGBM | 0.9490 (0.9455–0.9526) | 0.9854 (0.9839–0.9870) |
SVM | 0.9488 (0.9445–0.9531) | 0.9616 (0.9586–0.9646) |