# STAHD: a scalable and accurate method to detect spatial domains in high-resolution spatial transcriptomics data

## TL;DR

STAHD is a new method that efficiently and accurately detects spatial domains in high-resolution spatial transcriptomics data.

## Contribution

STAHD introduces a scalable framework combining graph attention autoencoders and graph partitioning for improved spatial domain detection.

## Key findings

- STAHD outperforms existing methods in benchmarks on human and mouse datasets.
- It accurately identifies spatially distinct tumor microenvironments and functional regions.
- The method improves computational efficiency and clustering accuracy.

## Abstract

Spatial transcriptomics (ST) enables the study of spatial heterogeneity in tissues. However, current methods struggle with large-scale, high-resolution data, leading to reduced efficiency and accuracy in detecting spatial domains. A scalable, precise solution is urgently needed.

We present STAHD, a scalable and efficient framework for spatial domain detection in ST data. Combining a graph attention autoencoder with multilevel k-way graph partitioning, STAHD decomposes large graphs into compact subgraphs and generates low-dimensional embeddings. This improves computational efficiency and clustering accuracy. Benchmarks on human and mouse datasets show STAHD outperforms existing methods and accurately reveals spatially distinct tumor microenvironments and functional regions.

Source code and data are available at: https://github.com/Little-Eel/STAHD.