Saved in:
Bibliographic Details
Main Authors: Wang, Jianhui, Zhu, Wenyu, Gao, Bowen, Hong, Xin, Zhang, Ya-Qin, Ma, Wei-Ying, Lan, Yanyan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.15480
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918216464334848
author Wang, Jianhui
Zhu, Wenyu
Gao, Bowen
Hong, Xin
Zhang, Ya-Qin
Ma, Wei-Ying
Lan, Yanyan
author_facet Wang, Jianhui
Zhu, Wenyu
Gao, Bowen
Hong, Xin
Zhang, Ya-Qin
Ma, Wei-Ying
Lan, Yanyan
contents Protein-ligand binding prediction is central to virtual screening and affinity ranking, two fundamental tasks in drug discovery. While recent retrieval-based methods embed ligands and protein pockets into Euclidean space for similarity-based search, the geometry of Euclidean embeddings often fails to capture the hierarchical structure and fine-grained affinity variations intrinsic to molecular interactions. In this work, we propose HypSeek, a hyperbolic representation learning framework that embeds ligands, protein pockets, and sequences into Lorentz-model hyperbolic space. By leveraging the exponential geometry and negative curvature of hyperbolic space, HypSeek enables expressive, affinity-sensitive embeddings that can effectively model both global activity and subtle functional differences-particularly in challenging cases such as activity cliffs, where structurally similar ligands exhibit large affinity gaps. Our mode unifies virtual screening and affinity ranking in a single framework, introducing a protein-guided three-tower architecture to enhance representational structure. HypSeek improves early enrichment in virtual screening on DUD-E from 42.63 to 51.44 (+20.7%) and affinity ranking correlation on JACS from 0.5774 to 0.7239 (+25.4%), demonstrating the benefits of hyperbolic geometry across both tasks and highlighting its potential as a powerful inductive bias for protein-ligand modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15480
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Protein-Ligand Binding in Hyperbolic Space
Wang, Jianhui
Zhu, Wenyu
Gao, Bowen
Hong, Xin
Zhang, Ya-Qin
Ma, Wei-Ying
Lan, Yanyan
Machine Learning
Protein-ligand binding prediction is central to virtual screening and affinity ranking, two fundamental tasks in drug discovery. While recent retrieval-based methods embed ligands and protein pockets into Euclidean space for similarity-based search, the geometry of Euclidean embeddings often fails to capture the hierarchical structure and fine-grained affinity variations intrinsic to molecular interactions. In this work, we propose HypSeek, a hyperbolic representation learning framework that embeds ligands, protein pockets, and sequences into Lorentz-model hyperbolic space. By leveraging the exponential geometry and negative curvature of hyperbolic space, HypSeek enables expressive, affinity-sensitive embeddings that can effectively model both global activity and subtle functional differences-particularly in challenging cases such as activity cliffs, where structurally similar ligands exhibit large affinity gaps. Our mode unifies virtual screening and affinity ranking in a single framework, introducing a protein-guided three-tower architecture to enhance representational structure. HypSeek improves early enrichment in virtual screening on DUD-E from 42.63 to 51.44 (+20.7%) and affinity ranking correlation on JACS from 0.5774 to 0.7239 (+25.4%), demonstrating the benefits of hyperbolic geometry across both tasks and highlighting its potential as a powerful inductive bias for protein-ligand modeling.
title Learning Protein-Ligand Binding in Hyperbolic Space
topic Machine Learning
url https://arxiv.org/abs/2508.15480