Skip to main navigation Skip to search Skip to main content

Learning Protein–Ligand Binding in Hyperbolic Space

  • Jianhui Wang (Co-first Author)
  • , Wenyu Zhu (Co-first Author)
  • , Bowen Gao (Co-first Author)
  • , Xin Hong
  • , Ya-Qin Zhang
  • , Wei-Ying Ma
  • , Yanyan Lan*
  • *Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

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 model 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. © 2026, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Original languageEnglish
Title of host publicationProceedings of the 40th Annual AAAI Conference on Artificial Intelligence
EditorsSven Koenig, Chad Jenkins, Matthew Taylor
Place of PublicationWashington, DC
PublisherAAAI Press
Pages1150-1158
Number of pages9
ISBN (Print)978-1-57735-906-7, 1-57735-906-2
DOIs
Publication statusPublished - 2026
Externally publishedYes
Event40th Annual AAAI Conference on Artificial Intelligence (AAAI-26) - , Singapore
Duration: 20 Jan 2026 → 27 Jan 2026
Conference number: 26
https://aaai.org/conference/aaai/aaai-26/

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
Number2
Volume40
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

Conference40th Annual AAAI Conference on Artificial Intelligence (AAAI-26)
Abbreviated titleAAAI-26
PlaceSingapore
Period20/01/26 → 27/01/26
Internet address

Funding

This work was supported by the National Key R&D Program of China No. 2025ZD1802501, the National Natural Science Foundation of China (NSFC) No. 62506193, and the Beijing Academy of Artificial Intelligence.

Fingerprint

Dive into the research topics of 'Learning Protein–Ligand Binding in Hyperbolic Space'. Together they form a unique fingerprint.

Cite this