Dataset and Code of SpaMGCL Project

The rapid development of spatial transcriptomics (ST) has enabled researchers to simultaneously capture gene expression profiles and spatial localization, offering unprecedented insights into tissue structure and function. However, spatial domain identification remains a critical challenge in ST data analysis, as current methods often struggle to fully capture the complex interplay between gene expression and spatial topology. To address this challenge, we propose SpaMGCL (Spatial Masked Graph Contrastive Learning), a novel self-supervised learning framework that integrates a masking mechanism with a contrastive learning strategy to jointly optimize gene expression and spatial information for more discriminative latent representation learning.