Network models for bridging denoising and identifying spatial domains of spatially resolved transcriptomics

Spatially resolved transcriptomics (SRT) enables the simultaneous capture of gene expression profiles and spatial localization, providing valuable insights into tissue architecture. However, the preservation of spatial information requires additional experimental procedures, which often introduce substantial technical noise. Existing methods typically perform denoising and spatial domain identification in separate steps, leading to suboptimal performance and limiting their applicability. To address this limitation, we propose an integrative network model, stACN ( spatial transcriptomics Attribute Cell Network), that jointly denoises gene expression data and identifies spatial domains in SRT. Specifically, stACN first learns clean dual cell networks using a graph noise model, and then derives compatible cell features through joint tensor decomposition of the denoised networks. Experimental results demonstrate that stACN effectively enhances data quality, as measured by clustering agreement with reference annotations (Adjusted Rand Index, ARI), and facilitates spatial domain analysis in SRT datasets.Author summary: Spatially resolved transcriptomics (SRT) simultaneously captures gene expression and spatial localization within intact tissues, providing a powerful tool for studying tissue organization and disease progression in fields such as developmental biology and oncology. However, the additional experimental procedures required to retain spatial context often introduce substantial technical noise, resulting in data that are typically sparse and noisy, thereby posing significant challenges for downstream analysis. To address these issues, we propose a network-based integrative model, stACN, for denoising and identifying spatial domains in SRT data by leveraging the topological structure of cell networks. Specifically, stACN constructs spatial and expression graphs through representation learning, denoises the data via graph-based modeling, performs joint feature learning through matrix decomposition, and identifies spatial domains by exploiting the structure of the cell affinity graph. Extensive experiments across diverse SRT platforms demonstrate that stACN effectively delineates spatial domains, identifies domain-specific gene markers, and generalizes well across datasets. These results highlight the potential of stACN as a robust framework for the integrated analysis and denoising of SRT data.