Current streamline of precision medicine uses histomorphological and molecular information to indicate individual phenotypes and genotypes to achieve optimal outcome of treatment. The knowledge of detected mutations and alteration can hardly describe molecular interaction and biological process which can finally be manifested as a disease. With molecular diagnosis revising the modalities of disease, there is a trend in precision medicine to apply multi-omic and multi-dimensional information to decode tumors, regarding heterogeneity, pathogenesis, prognosis, etc. Emerging state-of-art spatiotemporal omics provides a novel vision for in discovering clinicopathogenesis associated findings, some of which show a promising potential to be translated to facilitate clinical practice. Here, we summarize the available spatiotemporal omic technologies and algorithms, highlight the novel scientific findings and explore potential applications in the clinical scenario. Spatiotemporal omics present the ability to provide impetus to rewrite clinical pathology and to answer outstanding clinical questions. This review emphasizes the novel vision of spatiotemporal omics to refine the landscape of precision medicine in the clinic.

To simultaneously detect whole transcriptomes and protein markers on the same tissue section, we combined Cellular Indexing of Transcriptomes and Epitopes by Sequencing (CITE-seq) and Stereo-seq to develop the Stereo-CITE-seq workflow. Here, we demonstrated that Stereo-CITE-seq can co-detect mRNAs and proteins in immune organs with high spatial resolution, reproducibility and accuracy.

Integration of multiple data modalities in a spatially informed manner remains an unmet need for exploiting spatial multi-omics data. Here, we introduce SpatialGlue, a novel graph neural network with dual-attention mechanism, to decipher spatial domains by capturing the significance of each modality and neighbor graph in cross-omics and intra-omics integration. We demonstrate that SpatialGlue can accurately aggregate cell types into spatial domains at a higher resolution across different tissue types and technology platforms, as well as gain biological insights into cross-modality spatial correlations.

Integration of multiple data modalities in a spatially informed manner remains an unmet need for exploiting spatial multi-omics data. We introduce SpatialGlue, a graph neural network with dual-attention mechanism, to learn each modality's significance at cross-omics and intra-omics integration. We demonstrate that SpatialGlue can accurately aggregate cell types into spatial domains at a higher resolution on different tissue types and technology platforms, as well as gain insights into cross-modality spatial correlations.