# Leveraging Spot–Gene Heterogeneous Graphs for Unified Spatially Resolved Transcriptomics Domain Detection on Single-Slice and Multi-Slice Data

## TL;DR

This paper introduces stHGCL, a new method for accurately identifying spatial domains in transcriptomics data using a graph-based approach that works for both single and multi-slice datasets.

## Contribution

The novel stHGCL method uses a spot–gene heterogeneous graph and contrastive learning to improve spatial domain detection in SRT data.

## Key findings

- stHGCL outperformed existing methods on seven benchmark datasets with higher ARI and NMI scores.
- It successfully detected spatial domains in unaligned multi-slice datasets.
- Ablation studies confirmed the effectiveness of its key components.

## Abstract

Background: Spatially resolved transcriptomics (SRT) enables simultaneous measurement of gene expression and spatial location, but the existing domain detection methods are limited by over-reliance on spot-to-spot proximity, rigid pre-alignment requirements for multi-slice datasets, and inadequate mitigation of batch effects. This study aims to develop a unified method for accurate spatial domain identification across both single-slice and multi-slice SRT datasets. Methods: We propose a novel method named spatially resolved transcriptomics heterogeneous graph contrastive learning (stHGCL), which integrates a spot–gene heterogeneous graph, a dual-stage encoder (comprising LightGCN and GCN), and a neighborhood-driven contrastive learning module. The heterogeneous graph captures high-order structural information through spot–gene connections mediated by shared genes; the dual-stage encoder refines spot embeddings by fusing gene expression and spatial location; contrastive learning enhances intra-cluster compactness and mitigates batch effects. Results: stHGCL was validated on seven benchmark datasets from platforms including 10x Visium, BaristaSeq, STARmapSeq, Slide-seq, and Stereo-seq. It outperformed nine single-slice and eight multi-slice state-of-the-art methods. It achieved the highest mean Adjusted Rand Index (ARI) and Normalized Mutual Information (NMI) scores and could accurately delineate complex spatial domains with distinct boundaries, and even achieved cross-slice spatial domain detection for unaligned multi-slice datasets. Ablation studies confirmed the effectiveness of its main modules. Conclusions: stHGCL effectively captures high-order structural and spatial information and mitigates batch effects. It provides a robust scalable solution for unified spatial domain detection in SRT, facilitating insights into the spatial domains across both single-slice and multi-slice experimental paradigms.