Accurate and generalizable protein-ligand binding affinity prediction with geometric deep learning
Author(s)
Li, Krinos
Xiao, Xianglu
Zhong, Zijun
Yang, Guang
Type
Journal Article
Abstract
Goal: Protein-ligand binding complexes are ubiquitous and essential to life. Protein-ligand binding affinity prediction (PLA) quantifies the binding strength between ligands and proteins, providing crucial insights for discovering and designing potential candidate ligands. While recent advances have been made in predicting protein-ligand complex structures, existing algorithms for interaction and affinity prediction suffer from a sharp decline in performance when handling ligands bound with novel unseen proteins. Methods: We propose IPBind, a geometric deep learning-based computational method, enabling robust predictions by leveraging interatomic potential between complex's bound and unbound status. Results: Experimental results on widely used binding affinity prediction benchmarks demonstrate the effectiveness and universality of IPBind. Meanwhile, it provids atom-level insights into prediction. Conclusions: This work highlight the advantage of leveraging machine learning interatomic potential for predicting protein-ligand binding affinity.
Date Issued
2026-02-23
Date Acceptance
2026-02-18
Citation
IEEE Open Journal of Engineering in Medicine and Biology, 2026, 7, pp.86-93
ISSN
2644-1276
Publisher
IEEE
Start Page
86
End Page
93
Journal / Book Title
IEEE Open Journal of Engineering in Medicine and Biology
Volume
7
Copyright Statement
© 2026 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
License URL
Identifier
10.1109/OJEMB.2026.3667030
Publication Status
Published
Date Publish Online
2026-02-23