QSAR Classification Modeling Using Machine Learning with a Consensus-Based Approach for Multivariate Chemical Hazard End Points.

This study introduces an innovative computational approach using hybrid machine learning models to predict toxicity across eight critical end points: cardiac toxicity, inhalation toxicity, dermal toxicity, oral toxicity, skin irritation, skin sensitization, eye irritation, and respiratory irritation. Leveraging advanced cheminformatics tools, we extracted relevant features from curated data sets, incorporating a range of descriptors such as Morgan circular fingerprints, MACCS keys, Mordred calculation descriptors, and physicochemical properties. The consensus model was developed by selecting the best-performing classifier-Random Forest (RF), eXtreme Gradient Boosting (XGBoost), or Support Vector Machines (SVM)-for each descriptor, optimizing predictive accuracy and robustness across the end points. The model obtained strong predictive performance, with area under the curve (AUC) scores ranging from 0.78 to 0.90. This framework offers a reliable, ethical, and effective in silico approach to chemical safety assessment, underscoring the potential of advanced computational methods to support both regulatory and research applications in toxicity prediction.