Mimyr: Generative Modeling of Missing Tissue in Spatial Transcriptomics

Spatial transcriptomics enables the study of how gene expression is organized across tissues, revealing cell interactions within their native microenvironments in health and disease. However, tissue damage during sectioning and the allocation of intermediate slices to other assays often result in regions or entire planes missing from the data, limiting downstream analysis. Here, we introduce Mimyr, a generative framework for reconstructing realistic spatial transcriptomics data in unmeasured tissue regions. Mimyr addresses this challenge through three coupled components: predicting cell locations via guided diffusion, assigning cell types through supervised classification, and generating gene expression profiles with a transformer conditioned on spatial and cellular context. Mimyr accurately reconstructs held-out regions in mouse brain data and generalizes across experimental conditions, including variations in gene panels and slicing orientations. After finetuning on limited Alzheimer's disease data, Mimyr captures disease-associated transcriptional changes in unmeasured brain regions. By enabling high-fidelity spatial imputation from limited training data, Mimyr extends the utility of spatial transcriptomics, allowing researchers to recover unmeasured tissue states and deepen the study of tissue spatial organization and dynamics.