biostudies-literatureYang JSupporting Program of Southeast University Zhishan Yong ScholarNational Natural Science Foundation of China967https://www.ebi.ac.uk/biostudies/studies/S-EPMC12656142biostudies-literatureUnknown13(11)Quantum dots (QDs) possess unique optical and electronic properties, enabling wide applications in biomedicine and optoelectronics, but their nanoscale size and surface chemistry could pose potential toxicity risks. This study established a systematic, multi-endpoint framework for QD toxicity assessment. Physicochemical properties of various QDs and their multiple toxicity endpoints, including cell death, inflammation, and oxidative stress, were collected to build machine learning models (RF, XGBoost, KNN, SVM). The predictive toxic effects were then validated based on the brain organoid. Shapley Additive exPlanations (SHAP) analysis revealed that exposure dose and particle size were key cross-model drivers, while zeta potential and optical properties differentially affected specific toxicToxicsMachine Learning Framework for Multi-Endpoint Quantum Dot Toxicity Prediction with Organoid Validation and Drug Target Discovery.PMC126561422242025RCB002982574144, 82373617, 82103884Yang JHu DLiu KXia JQian YHe JZhang YWu TXing PYe ZfalseMachine Learning Framework for Multi-Endpoint Quantum Dot Toxicity Prediction with Organoid Validation and Drug Target Discovery.Quantum dots (QDs) possess unique optical and electronic properties, enabling wide applications in biomedicine and optoelectronics, but their nanoscale size and surface chemistry could pose potential toxicity risks. This study established a systematic, multi-endpoint framework for QD toxicity assessment. Physicochemical properties of various QDs and their multiple toxicity endpoints, including cell death, inflammation, and oxidative stress, were collected to build machine learning models (RF, XGBoost, KNN, SVM). The predictive toxic effects were then validated based on the brain organoid. Shapley Additive exPlanations (SHAP) analysis revealed that exposure dose and particle size were key cross-model drivers, while zeta potential and optical properties differentially affected specific toxic2025-01-01T00:00:00Z2025 Nov2026-05-20T03:16:33.807Z2026-05-20T03:13:10.032ZS-EPMC126561424130452110.3390/toxics13110967