Decoding Condition-Specific Cellular Crosstalk in Spatial Omics via Bilinear Edge Classification

Tissues are multicellular structured communities whose function emerges from a combination of individual cellular characteristics along with their corresponding spatial configuration, affecting their interactions and response patterns. During processes such as disease progression or aging, tissues can undergo structural reorganization, including changes in co-localization of different cell types, assembly or destruction of functional niches, and disruption of intercellular communication axes. Such changes can manifest primarily in the spatial reorganization of cells rather than in the transcriptional states of individual cells. While computational tools for spatial transcriptomics have made significant progress in characterizing tissue architecture, most approaches for characterizing changes in tissue states across biological conditions operate at the level of individual cells or rely on discrete cell type labels, thus limiting the ability to detect coordinated transcriptional changes between neighboring cells that distinguish one condition from another. We present CO_SCPLOWASEIC_SCPLOW, an interpretable bilinear edge classification framework comparing graphs across conditions, which directly models condition-specific cell-cell interactions in spatial omics data by focusing on interactions (edges), rather than cells (nodes), as the fundamental unit of inference. To capture such condition-specific signals, we leverage a model whose inductive bias aligns with cellular interactions through coordinated gene-gene relationships of neighboring cells, with learned weights that are directly interpretable as condition-specific gene-pair contributions. CO_SCPLOWASEIC_SCPLOW enables the discovery of condition-associated multicellular interactions and spatial expression programs, and characterizes the loss of multicellular function and structure. We evaluate CO_SCPLOWASEIC_SCPLOW on both controlled semi-synthetic spatial perturbations, where it outperforms node-level, edge-level, and graph neural network baselines, as well as on three real-world spatial omics datasets, where CO_SCPLOWASEIC_SCPLOW enabled extracting underlying cell-cell interactions and interaction-informative genes and cells. Applied to mammalian liver fibrosis, atherosclerosis, and brain aging, CO_SCPLOWASEIC_SCPLOW reveals biologically meaningful spatial reorganization, including the shift from endothelial-to macrophage-dominated networks in atherosclerotic plaques, disruption of hepatocyte zonation in fibrosis, and oligodendrocyte-microglia crosstalk in aging white matter.