biostudies-literatureTian TNHGRI NIH HHSU.S. Department of Health & Human Services | National Institutes of Health (NIH)U.S. Department of Health & Human Services | National Institutes of Health1501-1513https://www.ebi.ac.uk/biostudies/studies/S-EPMC12410143biostudies-literatureUnknown21(8)Spatially resolved transcriptomics (SRT) technologies have significantly advanced biomedical research, but their data analysis remains challenging due to the discrete nature of the data and the high levels of noise, compounded by complex spatial dependencies. Here, we propose spaVAE, a dependency-aware, deep generative spatial variational autoencoder model that probabilistically characterizes count data while capturing spatial correlations. spaVAE introduces a hybrid embedding combining a Gaussian process prior with a Gaussian prior to explicitly capture spatial correlations among spots. It then optimizes the parameters of deep neural networks to approximate the distributions underlying the SRT data. With the approximated distributions, spaVAE can contribute to several analytical tasks thaNature methodsDependency-aware deep generative models for multitasking analysis of spatial omics data.PMC12410143R15 HG0120871R15HG012087-01Hakonarson HZhang JLin XTian TWei ZfalseDependency-aware deep generative models for multitasking analysis of spatial omics data.Spatially resolved transcriptomics (SRT) technologies have significantly advanced biomedical research, but their data analysis remains challenging due to the discrete nature of the data and the high levels of noise, compounded by complex spatial dependencies. Here, we propose spaVAE, a dependency-aware, deep generative spatial variational autoencoder model that probabilistically characterizes count data while capturing spatial correlations. spaVAE introduces a hybrid embedding combining a Gaussian process prior with a Gaussian prior to explicitly capture spatial correlations among spots. It then optimizes the parameters of deep neural networks to approximate the distributions underlying the SRT data. With the approximated distributions, spaVAE can contribute to several analytical tasks tha2024-01-01T00:00:00Z2024 Aug2026-05-29T21:50:34.084Z2026-04-08T06:08:22.292ZS-EPMC124101433878306710.1038/s41592-024-02257-y