Trustworthy Protein-Ligand Binding Affinity Prediction via Reliability-Aware Multi-Engine Fusion

2026-07-20

AI Summary

This work addresses the lack of reliable confidence estimation in existing protein–ligand binding affinity prediction methods, which hinders the assessment of result credibility across different docking engines. The authors propose RELIABLE-BA, a novel framework that integrates evidential theory with context-aware reliability modeling. By employing a Normal-Inverse-Gamma distribution to construct an evidential expert model, the method dynamically evaluates the reliability of each docking engine within specific molecular contexts and introduces a closed-form uncertainty fusion algorithm enabling interpretable decomposition of predictive uncertainty. Evaluated on PDBBind and BDB2020+ benchmarks, RELIABLE-BA achieves both high-accuracy point predictions and well-calibrated uncertainty estimates. Validation on SARS-CoV-2 Mpro and 5HT2A targets demonstrates up to a 25% reduction in prediction error for high-confidence subsets, offering a robust pathway for AI-assisted drug discovery.

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.

Problem

• protein-ligand binding affinity
• uncertainty calibration
• docking engines
• trustworthy prediction
• computational drug discovery

Innovation

• evidential fusion
• reliability-aware learning
• binding affinity prediction
• uncertainty calibration
• multi-engine docking