TopoLa: A Universal Framework to Enhance Cell Representations for Single-cell and Spatial Omics through Topology-encoded Latent Hyperbolic Geometry

TL;DR

TopoLa introduces a novel hyperbolic geometry-based framework that enhances cell representations by capturing topological relationships, significantly improving performance in various single-cell and spatial transcriptomics tasks.

Contribution

The paper presents TopoLa, a new framework utilizing hyperbolic geometry and a novel distance metric to better encode cellular topologies in cell representations.

Findings

Improves clustering accuracy in scRNA-seq data

Enhances spatial domain identification in spatial transcriptomics

Demonstrates robustness across multiple biological tasks

Abstract

Recent advances in cellular research demonstrate that scRNA-seq characterizes cellular heterogeneity, while spatial transcriptomics reveals the spatial distribution of gene expression. Cell representation is the fundamental issue in the two fields. Here, we propose Topology-encoded Latent Hyperbolic Geometry (TopoLa), a computational framework enhancing cell representations by capturing fine-grained intercellular topological relationships. The framework introduces a new metric, TopoLa distance (TLd), which quantifies the geometric distance between cells within latent hyperbolic space, capturing the network's topological structure more effectively. With this framework, the cell representation can be enhanced considerably by performing convolution on its neighboring cells. Performance evaluation across seven biological tasks, including scRNA-seq data clustering and spatial transcriptomics domain identification, shows that TopoLa significantly improves the performance of several state-of-the-art models. These results underscore the generalizability and robustness of TopoLa, establishing it as a valuable tool for advancing both biological discovery and computational methodologies.