Hierarchical Contrastive Learning for Multi-Domain Protein-Ligand Binding

TL;DR

HCLBind is a self-supervised hierarchical framework that improves multi-domain protein-ligand binding affinity prediction by learning from geometric and conformational data, leveraging domain-specific attention and efficient fine-tuning.

Contribution

The paper introduces HCLBind, a novel hierarchical contrastive learning approach that decouples geometric representation from affinity regression for multi-domain proteins.

Findings

HCLBind effectively learns discriminative interface features.

The model provides robust uncertainty estimation.

It outperforms standard supervised methods on PDBBind.

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 https://github.com/jiankliu/HCLBind.