Cooperative integration of spatially resolved multi-omics data with COSMOS

Nat Commun. 2025 Jan 2;16(1):27. doi: 10.1038/s41467-024-55204-y.

Abstract

Recent advancements in biological technologies have enabled the measurement of spatially resolved multi-omics data, yet computational algorithms for this purpose are scarce. Existing tools target either single omics or lack spatial integration. We generate a graph neural network algorithm named COSMOS to address this gap and demonstrated the superior performance of COSMOS in domain segmentation, visualization, and spatiotemporal map for spatially resolved multi-omics data integration tasks.