Track genomics, neuroscience and molecular biology.
Search papers, labs, and topics across Lattice.
TopoLIA introduces a novel topology-inspired latent interaction attention mechanism for drug discovery, addressing the bottleneck of conventional source-target attention in modeling complex interactions by mediating information exchange through a compact latent space. By incorporating topological spectral representations to capture multiscale data geometry and algebraic relationships, TopoLIA learns both the quantity and transformation of information between interaction partners. The approach achieves state-of-the-art performance on protein-ligand binding benchmarks, outperforming standard attention and demonstrating the efficacy of compact latent interaction spaces as an inductive bias for biomolecular learning.
Topological spectral representations and latent interaction attention unlock structured, source-target-dependent information exchange for biomolecular learning, achieving SOTA drug discovery performance.
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.