SAMGCN: A spatially-augmented multi-view graph convolutional network for identifying spatial domains

Recent innovations in spatial transcriptomics have enabled the measurement of gene expression profiles while preserving the spatial organization of cells. This provides extensive opportunities to explore gene expression patterns in the tissue microenvironment. However, it remains a challenge to combine spatial information with gene expression to accurately identify spatial domains. In this study, a spatially-augmented multi-view graph convolutional network for identifying spatial domains (SAMGCN) is proposed. First, SAMGCN reconstructs gene expression data by incorporating spatial neighborhood information, which enhances gene expression features. It improves the quality of gene expression data and augments the characterization of spatial domains through the construction of spatial graphs, feature graphs, and spatial expression-weighted graphs. By extracting spatial information and gene expression data via convolutional operations, SAMGCN learns multi-view-specific embeddings and employs a contrastive strategy to refine and augment spatial neighborhood relationships, addressing limitations in spatial gene expression data. An attention mechanism is then employed to flexibly merge these embeddings, generating the final spot embedding. Additionally, a zero-inflated negative binomial decoder is used to capture the global probability distribution of gene expression profiles. Finally, the performance of SAMGCN has been validated across various platforms and spatial transcriptomics datasets of different scales, demonstrating its exceptional capability to process spatial transcriptomics data.