Fig. 2From: PredAOT: a computational framework for prediction of acute oral toxicity based on multiple random forest modelsCross-validation prediction performances of the MPNN, MPNN with MF, MPNN with MD, RF, SVM, and ANN models for the AOT classifier using mouse (A) and rat (B) datasets. Each performance metric value was calculated by five-fold cross-validation. MPNN, message passing neural network; MF, molecular fingerprint; MD, molecular descriptor; RF, random forest; SVM, support vector machine; ANN, artificial neural networkBack to article page