OrgaCCC: Orthogonal graph autoencoders for constructing cell-cell communication networks on spatial transcriptomics data

Cell-cell communication (CCC) is a fundamental biological process essential for maintaining the functionality of multicellular organisms. It allows cells to coordinate their activities, sustain tissue homeostasis, and adapt to environmental changes. However, understanding the mechanisms underlying intercellular communication remains challenging. The rapid advancements in spatial transcriptomics (ST) have enabled the analysis of CCC within its spatial context. Despite the development of several computational methods for inferring CCCs from ST data, most rely on literature-curated gene or protein interaction lists, which are often inadequate due to the restricted gene coverage. In this work, we propose OrgaCCC, an orthogonal graph autoencoders approach for cell-cell communication inference based on deep generative models. OrgaCCC leverages the information of gene expression profiles, spatial locations and ligand-receptor relationships. It captures both cell/spot and gene features using two orthogonally coupled variational graph autoencoders across cell/spot and gene dimensions and combines them by maximizing the similarity between their reconstructed cell/spot features. Numerical experiments on five ST datasets demonstrate the superiority of OrgaCCC compared with state-of-the-art methods in CCC inference at the cell-type level, cell/spot level, and ligand-receptor level, in terms of inference accuracy and reliability.Author summary: Cell-cell communication is vital for tissue function and homeostasis, but understanding its mechanisms is challenging due to the complexity of interactions. While spatial transcriptomics (ST) offers a powerful approach to study CCC in its spatial context, existing computational methods often rely on limited gene interaction data, failing to capture the full complexity of spatial and cellular relationships. We introduce OrgaCCC, a deep generative model designed to infer cell-cell communication from spatial transcriptomics (ST) data using orthogonal graph autoencoders. The model employs two distinct autoencoders operating at the cell/spot and gene levels, respectively. These autoencoders integrate gene expression, spatial localization, and ligand-receptor interactions to capture both cellular and molecular features. By maximizing the similarity between reconstructed cell/spot features, OrgaCCC improves the accuracy and reliability of CCC inference, offering a more precise framework for identifying intercellular interactions in spatially resolved tissues.