Book

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

Yongchan Hong Defu Cao Wenjin Liu Thomas K.U J. Lam Emily Nguyen Willie Neiswanger V. Katritch Yan Liu

Jul 2026 · Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · 0 citations · 52 references

Computer Science

TL;DR

To the 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.

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.

DOI arXiv Semantic Scholar

View source

Similar papers

#artificial intelligence Preprint Aug 2026

CoMPASS: Collaborative Molecular Property Prediction via Adaptive Small-Large Model Synergy

CoMPASS is presented, a retrieval-calibrated framework for small-large model collaboration that retains a graph attention network as the predictive anchor, retrieves locally relevant training molecules, provides attention-grounded evidence to an LLM, and converts its proposal into a bounded correction through an agreement-aware gate.

Wen-Tao Li, Jiang-Jie Qiu, Yi-Jun Li et al. · 0 citations

Open access Jul 2026

A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation

This work proposes MochiBind, a sequence-only pairwise binding affinity predictor, and benchmark it against structure-derived baselines such as Boltz-2, GeoDock, and Graphinity, suggesting that sequence-based approaches can match or surpass structure-based models in generalization.

Yunrui Li, Yue Zhao, K. Sonmez et al. · iScience · 0 citations

Open access Aug 2026

Interpretable multilevel interaction modeling for robust protein–protein affinity

MIRAGE provides an interpretable and robust framework for structure-aware prediction, with potential applications in protein engineering and drug design, and explicitly modeling multi-level interactions is important for accurately capturing the determinants of binding affinity.

Shiwei Wu, Haoliang Liu, Ze-Peng Huang et al. · BMC Genomics · 0 citations

Jul 2026

Atomic Uncertainty Pinpoints Critical Failure Structures for Trustworthy Molecular Property Prediction

AUINet is introduced, an atomic uncertainty-aware iterative network that quantifies and refines uncertainty at the atomic scale and establishes a new paradigm for trustworthy molecular property prediction.

Jiayu Qian, Yukun Luo, Qingping Zhou et al. · Journal of Chemical Informat... · 0 citations

Aug 2026

Interpretable Prediction of Ligand-Protein Binding without Protein Structural Information.

Ananthan Sadagopan, Anurag Sodhi, William J. Gibson · Journal of Medicinal Chemist... · 0 citations

Jul 2026

Hierarchical Graph Representation Learning From a Statistical Perspective for Generalizable and Interpretable Protein-Ligand Binding Affinity Prediction.

Protein-ligand binding affinity (PLA) prediction aims to guide rational drug design by estimating the strength of interaction. The effectiveness of the representation learning of protein and ligand is key to successful PLA prediction. To this end, attention mechanism, as a powerful architectural paradigm, has been introduced and gradually emerged as the prevailing approach. However, intuitively, the classical attention paradigm based on similarity does not fit the biological mechanisms relevant for binding. Worse still, the cooperative and antagonistic effects among multiple atoms are deliberately disregarded in the classical formulation of attention mechanisms. Consequently, the rigid transplantation of classical architectures substantially undermines the PLA prediction performance. To address these challenges, we employ a hierarchical statistical attention model (HISA). Specifically, HISA employs a statistical attention mechanism (SAM) based on non-similarity computation to fit the biological prior and perceive the relationship of multiple atoms. In addition, we optimize HISA by employing clustering, enabling hierarchical representations of biomolecules. Extensive experiments demonstrate that HISA achieves state-of-the-art performance on multiple PLA benchmarks while simultaneously exhibiting generalizability and interpretability.

Changming Yao, Shunfanyi Li, Shanghui Deng et al. · IEEE transactions on computa... · 0 citations