Trustworthy Protein-Ligand Binding Affinity Prediction via Reliability-Aware Multi-Engine Fusion
2026-07-20 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors developed a new method called RELIABLE-BA to predict how strongly drugs bind to proteins using multiple prediction tools. Instead of treating all tool predictions equally, their method estimates how reliable each tool's prediction is based on the specific protein and drug, then combines these informed predictions to improve accuracy. They tested their approach on standard datasets and real drug targets, showing better uncertainty estimates and the ability to filter out less trustworthy predictions, which lowered errors. This work helps make AI predictions in drug discovery more reliable by understanding and using uncertainty better.
protein-ligand binding affinitydocking enginesevidential fusionNormal-Inverse-Gamma distributionepistemic uncertaintyuncertainty calibrationPDBBind datasetSARS-CoV-2 Mpromulti-engine predictionreliability estimation
Authors
Yongchan Hong, Defu Cao, Wenjin Liu, Thomas Ku, Jordy Homing Lam, Emily Nguyen, Willie Neiswanger, Vsevolod Katritch, Yan Liu
Abstract
Accurate protein-ligand binding affinity prediction is central to computational drug discovery, yet modern docking engines frequently disagree without indicating which prediction to trust. Consensus scoring and ensemble methods improve mean accuracy but treat all predictions identically without interpretable confidence measures or uncertainty decomposition, ignoring the chemical context of each protein-ligand pair. To address this limitation, we introduce RELIABLE-BA (RELIABiLity-aware Evidential fusion for Binding Affinity), an evidential framework for multi-engine binding affinity prediction. Our model comprises three steps: (1) modeling each engine as an evidential expert via Normal-Inverse-Gamma distributions, (2) scaling epistemic uncertainty through learned reliability from molecular context while preserving each expert's predictive mean, and (3) fusing experts through closed-form aggregation that captures both individual uncertainty and inter-engine disagreement. Experiments on the PDBBind and BDB2020+ benchmarks demonstrate competitive point prediction with substantially improved uncertainty calibration, and additional validation on the SARS-CoV-2 Mpro dataset and 5HT2A receptor demonstrates applicability to clinically relevant drug targets. Crucially, these uncertainty estimates enable reliable filtering of protein-ligand pairs, reducing prediction error by up to 25% when retaining only high-confidence pairs. To our knowledge, RELIABLE-BA is the first multi-engine binding affinity prediction framework to combine evidential fusion with context-dependent reliability, offering a principled path toward trustworthy AI-guided drug discovery. Our code is publicly available at https://github.com/yongchand/RELIABLE-BA.