Steamboat: Attention-based multiscale delineation of cellular interactions in tissues

Spatial-omics technologies profile cells in their native spatial context within tissues, enabling more complete understanding of cellular properties. However, a key computational challenge remains: identifying cellular interactions that underlie cell types and states – interactions that are essential for spatial organization and provide a biologically grounded framework for understanding cell identities and spatial patterns. These interactions span different distances and thus require multiscale modeling, which remains a major gap in existing methods. Here, we introduce S<sc>teamboat</sc>, an interpretable machine learning framework that leverage a self-supervised, multi-head attention model to uniquely decompose gene expression of a cell into multiple key factors: intrinsic cell programs, neighboring cell communication, and long-range interactions. By applying S<sc>teamboat</sc>to diverse tissues in health and disease across various spatial-omics technologies, we demonstrate its ability to uncover critical multiscale cellular interactions, capturing classical contact signaling and revealing previously unrecognized patterns of cellular communication. S<sc>teamboat</sc>provides a powerful approach for spatial-omics analysis, offering new insights into the multiscale spatial organization of cells and their communication across a wide range of biological contexts.