“…Machine learning models can be used to predict hepatotoxicity given the molecular descriptor of a compound as input. We mainly focused on the following machine learning algorithms to develop binary classification models, among several methods that have been applied in QSAR modeling: Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Logistic Regression (LR), Random Forest (RF), XG Boosting (XGB), K-Nearest Neighbors (KNN), Naive Bayes (NB) and Decision Tree (DT) classifier [ 27 , 32 , 33 , 53 , 55 , 56 ]. These robust algorithms are highly efficient and can accommodate numerous features.…”