The emergence of single-cell spatial transcriptomics technologies has transformed our understanding of the composition and function of diverse cell populations across various environments and organs. As these technologies advance, they generate vast volumes of multi-omics data. For instance, Stereo-seq and Stereo-cell technologies are now producing tens of terabytes of data from a single chip, including transcriptomics and proteomics, posing substantial challenges and opportunities for understanding biology and clinical applications from multidimensional.
To address these challenges, we developed bioinformatic solutions tailored specifically for single-cell spatiotemporal multi-omics data analysis. These include Generative Bio-intelligence (GBI) model, a deep learning models trained with multi-omics data uncovered complex patterns and relationships among cells, genes, and proteins in a high-dimensional space. Using these solutions, we demonstrated how large-scale scStereo-seq data analysis can uncover valuable insights into the spatial organization of cell types, cellular interactions, and the molecular architecture of tissues.