Accelerating Discovery of Leukemia Inhibitors with AI-Driven QSAR Modeling (Preprint)

BACKGROUND Leukemia treatment remains a major challenge in oncology. While Thiadiazolidinone (TDZD) analogs show potential to inhibit leukemia cell proliferation, they often lack sufficient potency and selectivity. Traditional drug discovery struggles to efficiently explore the vast chemical landscape, highlighting the need for innovative computational strategies. Machine learning (ML)-enhanced QSAR modeling offers a promising route to identify and optimize inhibitors with improved activity and specificity. OBJECTIVE To develop and validate an integrated machine learning–enhanced QSAR modeling workflow for the rational design and prediction of Thiadiazolidinone (TDZD) analogs with improved anti-leukemia activity, by systematically evaluating molecular descriptors and algorithmic approaches to identify key determinants of potency and guide future inhibitor optimization. METHODS We analyzed 35 TDZD derivatives with confirmed anti-leukemia activity, removing outliers for data quality. Using Schrödinger MAESTRO, we calculated 220 molecular descriptors (1D–4D). Seventeen ML models, including Random Forests, XGBoost, and Neural Networks, were trained on 70% of data and tested on 30%, using stratified sampling. Model performance was assessed with 12 metrics, including MSE, R², and SHAP values, and optimized via hyperparameter tuning and 5-fold cross-validation. RESULTS Ensemble methods, especially LightGBM and Random Forest, showed superior predictive performance (LightGBM: MSE = 0.00063 ± 0.00012; R² = 0.971 ± 0.0084). Isotonic Regression ranked second, outperforming baseline models by over 15% in explained variance. SHAP analysis identified hydrogen bond acceptor count (r_qp_accptHB), electronic properties, and solubility as key features for anti-leukemia activity. CONCLUSIONS Integrating ML with QSAR modeling refines leukemia inhibitors and enhances prediction accuracy while revealing underlying mechanisms. This approach accelerates identification of potent compounds and offers a pathway to overcome therapeutic resistance in leukemia.