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

Accurate prediction of binding affinity is crucial for rational drug design and discovery. Traditional computational methods often rely on complex scoring functions that incorporate a multitude of physical and chemical descriptors, leading to high computational demands and sometimes limited generalizability. In this work, we propose a novel scoring function that models multi-level, multi-body atomic interactions using graph-based representations. Our method constructs comprehensive interaction graphs that incorporate both pairwise and triplet-wise atomic features that help capture cooperative spatial patterns essential for binding affinity prediction. By employing a feature fusion strategy, GMI-Score maintains model simplicity while enhancing accuracy. Extensive evaluation across multiple datasets, such as PDBbind v2013, PDBbind v2016, PDBbind v2020, CSAR-NRC-HiQ, and PDBbind-Redocked, demonstrates that our model consistently outperforms state-of-the-art scoring functions, achieving Pearson correlation coefficients up to 0.877. Furthermore, it retains strong predictive power under strict data leakage controls and realistic docking conditions to high-light its robustness and generalizability. Scientific ContributionIn this study, we present a scoring methodology that systematically captures higher-order atomic interactions within a unified graph framework, making a conceptual shift in cheminformatics scoring functions. Its consistent outperformances of existing methods and strong validity under redocked and withheld atascenarios demonstrate its utility for broad-scale molecular modeling applications and open heminformaticsworkflows.