# SAGE: Spatially Aware Gene Selection and Dual‐View Embedding Fusion for Domain Identification in Spatial Transcriptomics

## TL;DR

SAGE is a new method for spatial transcriptomics that improves domain identification by combining gene selection and dual-view embedding fusion, revealing meaningful tissue structures and gene patterns.

## Contribution

SAGE introduces a unified framework that combines topic-driven gene selection with dual-view embedding fusion for accurate and interpretable spatial domain identification.

## Key findings

- SAGE outperforms existing methods in clustering accuracy across 34 datasets.
- SAGE reveals functionally coherent regions and interpretable gene expression patterns in cancer and melanoma.
- The method identifies spatial heterogeneity and shared vascular signatures in anatomically separate tissues.

## Abstract

Despite enabling high‐resolution mapping of gene expression within tissues, spatial transcriptomics (ST) still faces challenges in accurately segmenting spatial domains due to complex tissue architecture and limitations of current methods. Most approaches rely on local spatial priors, lack gene‐level interpretability, and fall short in capturing structure‐discriminative genes or long‐range functional relationships, limiting their ability to resolve biologically meaningful architectures. We present Spatially Aware Gene selection and dual‐view Embedding fusion (SAGE), a unified and reproducible framework for domain identification in spatial transcriptomics that combines topic‐driven gene selection with dual‐view embedding fusion to address these gaps. SAGE integrates non‐negative matrix factorization (NMF)‐based topic modeling with classifier‐based importance scoring to identify highly spatially informative genes, and fuses a local expression graph with a topic‐driven non‐local graph via consensus refinement and contrastive graph representation learning to jointly learn spatial and functional embeddings. Evaluated on 34 real‐world datasets, SAGE not only outperforms existing methods in clustering accuracy but also reveals functionally coherent regions and interpretable gene expression patterns. In case studies, SAGE reveals spatial heterogeneity associated with a pre‐malignant activation state in human breast cancer. Moreover, in zebrafish melanoma, it refines the tumor–muscle interface into transcriptionally distinct subdomains and uncovers shared vascular signatures between anatomically separate tissues. Together, these results demonstrate that SAGE can be used not only for accurate spatial domain delineation across diverse ST platforms, but also for dissecting microenvironmental niches and long‐range tissue interactions underlying disease progression.

SAGE is a unified framework for spatial domain identification in spatial transcriptomics that jointly models tissue architecture and gene programs. Topic‐driven gene selection (NMF plus classifier‐based scoring) highlights spatially informative genes, while dual‐view graph embedding fuses local expression and non‐local functional relations. Across 34 datasets, SAGE improves clustering and yields interpretable domains, revealing microenvironmental niches and long‐range tissue interactions in cancer and melanoma.