D'Anna L, Contino S, Marinello R, Fares J, De Simone G, Monari A, Barbault F, Barone G, Terenzi A, Perricone U. · ACS omega · 2026

AGAPE (Computational G‑Quadruplex Stabilization Prediction): The First Machine Learning Workflow for G‑Quadruplex Stabilization Prediction.

Resumo original em inglês

AGAPE (computational G-quadruplex stabilization prediction) is a novel machine learning (ML)-based tool designed to predict the stabilizing potential of small molecules targeting G-quadruplexes (G4s). G4s, prevalent in telomeres and oncogene promoters, are promising therapeutic targets, but designing selective binders remains challenging. Building upon a curated data set of 1217 compounds labeled through Förster Resonance Energy Transfer (FRET) melting assay data, AGAPE integrates 5666 molecular descriptors, both classical and quantum chemical. It captures features relevant to G4 recognition, driving researchers to predict the potential G4 stabilization of small molecules, including both organic ligands and metal complexes. Among the trained ML models, XGBoost achieved the best performance with an accuracy of nearly 91%, using 489 selected features. SHAP analysis highlighted descriptors related to molecular topology, polarizability, and electrostatic potential as key contributors to the classification. AGAPE is deployed through a user-friendly web interface, http://agape.fondazionerimed.com/, supporting batch prediction and secure data handling, and provides a robust and interpretable tool to accelerate the discovery of G4-stabilizing compounds, integrating quantum chemical information within an ML-driven cheminformatics framework.