Zhang, Z.; Zhang, Y.; Li, X.; Bian, J.; Shen, J.; Liu, Y.

Spatial multi-omics integration requires balancing cross-omics consensus with modality-specific signals whose importance varies across tissue locations. We present GatorPrism, a self-supervised coalition graph mixture-of-experts framework that explicitly separates cross-omics consensus from modality-specific structure and adaptively integrates their contributions across tissue locations. A joint expert encodes an intersection-based consensus graph, while modality-private experts capture mixed spatial-molecular structures; a prototype-conditioned router assigns spot-specific coalition weights. GatorPrism is trained end-to-end to preserve shared and modality-specific neighborhoods, align co-registered modalities, maintain spatial coherence, and prevent routing collapse. Across eight spatial multi-omics datasets, GatorPrism achieved strong performance across nine clustering metrics against nine competing methods. In human tonsil, inferred domains were supported by concordant RNA and ADT markers and distinct functional programs. In embryonic mouse brain, routing profiles revealed anatomically localized shared, RNA-private, and ATAC-private states supported by transcriptomic, chromatin-accessibility, and motif evidence. These results establish GatorPrism as an accurate and interpretable framework that reveals how shared and modality-specific molecular signals organize tissue structure. Source code is available at https://github.com/Gator-Group/GatorPrism.