GEOapplication/xmlftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE284nnn/GSE284032/primary200OKOtherMus musculusOtherhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE284032GEOGSEfalseIntegration and annotation of spatial multi-omic data with DIRAC highlights spatial organization of lymphoid organsSpatial multi-omics technologies enable simultaneous measurements of multiple omics modalities. Integration across spatial omics modalities followed by multi-omic spatial domain and cell-type annotation are two fundamental tasks for downstream analysis. We present Domain Invariant Representation through Adversarial Calibration (DIRAC), a geometric deep learning model that unifies both tasks by treating horizontal integration (different cells/spots, same omic modality) and vertical integration (same cells/spots, different omics modalities) under a generalized domain adaptation framework. DIRAC uses an adversarial domain discriminator to integrate multiple spatial omics modalities into a unified domain-invariant embedding space and to automate cell-type annotation by transferring labels from reference multi-omic data. DIRAC delineated more biologically meaningful spatial domains and improved clustering and cell-type annotation performance across omics modalities (histone marks, chromatin accessibility, RNA, and protein) and technology platforms (sequencing and imaging-based). We used DIRAC to build cellularly resolved spatial multi-omics atlases of mouse spleen and thymus, revealing the spatial migratory patterns of T cells in the thymus and the spatial organization of finely-resolved immune cell types in the spleen. DIRAC is substantially faster than existing multi-omic integration methods and scales to millions of cells.2026/07/01GSE284032GSM8740089GSM8740090GSM8676454GSM86764532833028457284032Mus musculus