An Integrative Multi-Network and Multi-Classifier Approach to Predict Genetic Interactions (original) (raw)
Figure 3
Classification on our SL dataset.
(A) Receiver operating characteristic (ROC) curves of six individual classifiers and the ensemble (MNMC) using SL-independent features. (B) ROC curves for the ensemble classifier for our data set using all features (MNMC.all; AUC = 0.837) and SL-independent features (MNMC.slif; AUC = 0.741). (C) Precision-recall curves using all features (MNMC.all) and SL-independent features (MNMC.slif). The corresponding ROC and precision-recall curves for a random classifier are also shown.