Abstract:Predicting protein-ligand binding affinity remains intractable for multi-domain proteins, where inter-domain dynamics govern molecular recognition. Existing geometric deep learning methods typically treat proteins as monolithic static graphs, suffering from rigid-body assumptions and aleatoric noise in flexible regions. To address this, we introduced HCLBind, a self-supervised framework that decouples geometric representation learning from affinity regression. HCLBind leverages a general-to-specific pre-training paradigm on the Q-BioLiP database to learn a robust physical grammar of binding. We propose a novel hierarchical decoy strategy: the model learns local physicochemical constraints through protein coordinate perturbation in single-domain proteins and global conformational geometry through inter-domain rotation in multi-domain complexes. Our hybrid architecture integrates a domain-gated graph attention network and cross-modal attention to explicitly prioritize domain interfaces. Furthermore, we employ LoRA on protein and ligand foundation models, ensuring efficient optimization while preserving evolutionary knowledge. Experiments on PDBBind demonstrate that HCLBind effectively learns discriminative interface features and provides robust uncertainty estimation, overcoming the limitations of standard supervised learning. The code is available at this https URL.
| Comments: | Accepted by ISBRA2026 |
| Subjects: | Machine Learning (cs.LG); Quantitative Methods (q-bio.QM) |
| Cite as: | arXiv:2605.19902 [cs.LG] |
| (or arXiv:2605.19902v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.19902 arXiv-issued DOI via DataCite (pending registration) |
From: Shuo Zhang [view email]
[v1]
Tue, 19 May 2026 14:33:02 UTC (3,212 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。