Mosaic integration of spatial multi-omics with SpaMosaic

With the advent of spatial multi-omics, we can mosaic integrate such datasets with partially overlapping modalities to construct higher dimensional views of the source tissue. SpaMosaic is a spatial multi-omics mosaic integration tool that employs contrastive learning and graph neural networks to construct a modality-agnostic and batch-corrected latent space suited for analyses like spatial domain identification and imputing missing omes. Using simulated and experimentally acquired datasets, we benchmarked SpaMosaic against single-cell multi-omics mosaic integration methods. The experimental spatial omics data encompassed RNA and protein abundance, chromatin accessibility or histone modifications, acquired from brain, embryo, tonsil, and lymph node tissues. SpaMosaic achieved superior performance over existing methods in identifying known spatial domains while reducing noise and batch effects. We also integrated a set of five mouse brain datasets of RNA and different epigenomic modalities, and imputed the missing omes. We found the genes in the imputed omes enriched in the correct tissue specific biological processes, supporting the imputation accuracy.