Multi-level, multi-body atomic interaction graphs for machine learning-based prediction of protein-ligand binding energies

Abstract

Accurate prediction of binding affinity is crucial for rational drug design and discovery. This work proposes a novel scoring function that models multi-level, multi-body atomic interactions using graph-based representations. The method constructs interaction graphs with both pairwise and triplet-wise atomic features and uses feature fusion to improve accuracy while maintaining model simplicity. Across PDBbind v2013, PDBbind v2016, PDBbind v2020, CSAR-NRC-HiQ, and PDBbind-Redocked, the model consistently outperforms state-of-the-art scoring functions, achieving Pearson correlation coefficients up to 0.877, while remaining robust under strict data-leakage controls and realistic docking conditions.

Tram Le

Master’s Student (co-advised)

Placeholder bio — replace with Tram Le’s short biography.

Duc Nguyen

Associate Professor of Mathematics

Duc Nguyen develops mathematical and AI frameworks for molecular bioscience, drug discovery, and scientific computing. His group blends differential geometry, graph theory, and machine learning to build high-fidelity models for biomolecular systems, with notable wins in the D3R Grand Challenges and collaborations with Pfizer and Bristol Myers Squibb. Supported by multiple NSF awards, he has advised students and postdocs across theory and applications of AI-driven drug design.