TopoLIA: Topology-Inspired Latent Interaction Attention for Drug Discovery
Abstract
The growing sophistication of drug discovery calls for new advances in artificial intelligence (AI). Transformers have underpinned recent breakthroughs in AI, yet their conventional source-target attention mechanism can become a bottleneck for modeling complex interactions. Here, we introduce TopoLIA, a topology-inspired latent interaction attention mechanism that learns not only how much information should be exchanged between interaction partners, but also how that information should be transformed. Source-target-dependent attention is mediated through a compact latent interaction space, providing a structured representation of complex interactions. We further incorporate topological spectral representations to capture multiscale data geometry and extract algebraic relationships. TopoLIA thus incorporates topological principles into both data representation and neural network architecture. We demonstrate TopoLIA on protein-ligand binding, where persistent spectra encode multiscale topological and geometric patterns in 3D protein-ligand complexes, while latent interaction attention (LIA) enables structured, source-target-dependent information exchange. We pretrain TopoLIA by reconstructing masked multiscale spectral tokens from unlabeled molecular structures, yielding transferable structural representations without task-specific annotations. Across multiple scoring and docking benchmarks, TopoLIA achieves state-of-the-art performance and consistently outperforms its standard-attention counterpart. Rank analyses show that compact latent dimensions yield the best performance, supporting compact interaction spaces as an effective inductive bias for biomolecular learning. More broadly, LIA provides a general framework for structured, source-target-dependent information exchange that is applicable to diverse scientific and AI problems involving complex heterogeneous interactions.
Related
- STRIVE: interpretable multimodal subtype discovery in Women’s cancers using an attention-weighted joint variational autoencoder
- Recommendation system-inspired learning of crossmodal interaction patterns between chromatin accessibility and gene expression
- Decoding enzyme-substrate interaction topology reveals principles underlying catalytic efficiency and mutational outcomes
- Expanding Macrocyclic Topology through Cysteine-to-N-Terminal Cyclisation Enables Covalent Peptide Inhibitor Discovery
- StrucNS reveals interaction-weighted network topology as the driving predictor of absolute stability of natural and de novo proteins
BibTeX
@misc{liu2026topolia,
title = {{TopoLIA: Topology-Inspired Latent Interaction Attention for Drug Discovery}},
author = {Xiang Liu and Yiming Ren and Mustafa Hajij and Pietro Liò and Guo-Wei Wei},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.13006},
eprint = {2610.13006},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.13006},
}
RIS
TY - UNPB
TI - TopoLIA: Topology-Inspired Latent Interaction Attention for Drug Discovery
AU - Xiang Liu
AU - Yiming Ren
AU - Mustafa Hajij
AU - Pietro Liò
AU - Guo-Wei Wei
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2610.13006
UR - https://arxiv.org/abs/2610.13006
AB - The growing sophistication of drug discovery calls for new advances in artificial intelligence (AI). Transformers have underpinned recent breakthroughs in AI, yet their conventional source-target attention mechanism can become a bottleneck for modeling complex interactions. Here, we introduce TopoLIA, a topology-inspired latent interaction attention mechanism that learns not only how much information should be exchanged between interaction partners, but also how that information should be transformed. Source-target-dependent attention is mediated through a compact latent interaction space, providing a structured representation of complex interactions. We further incorporate topological spectral representations to capture multiscale data geometry and extract algebraic relationships. TopoLIA thus incorporates topological principles into both data representation and neural network architecture. We demonstrate TopoLIA on protein-ligand binding, where persistent spectra encode multiscale topological and geometric patterns in 3D protein-ligand complexes, while latent interaction attention (LIA) enables structured, source-target-dependent information exchange. We pretrain TopoLIA by reconstructing masked multiscale spectral tokens from unlabeled molecular structures, yielding transferable structural representations without task-specific annotations. Across multiple scoring and docking benchmarks, TopoLIA achieves state-of-the-art performance and consistently outperforms its standard-attention counterpart. Rank analyses show that compact latent dimensions yield the best performance, supporting compact interaction spaces as an effective inductive bias for biomolecular learning. More broadly, LIA provides a general framework for structured, source-target-dependent information exchange that is applicable to diverse scientific and AI problems involving complex heterogeneous interactions.
ER -