BANKSY unifies cell typing and tissue domain segmentation for scalable spatial omics data analysis

Nature Genetics volume  56, pages 431–441 (2024 )Cite this article

Spatial omics data are clustered to define both cell types and tissue domains. We present Building Aggregates with a Neighborhood Kernel and Spatial Yardstick (BANKSY), an algorithm that unifies these two spatial clustering problems by embedding cells in a product space of their own and the local neighborhood transcriptome, representing cell state and microenvironment, respectively. BANKSY’s spatial feature augmentation strategy improved performance on both tasks when tested on diverse RNA (imaging, sequencing) and protein (imaging) datasets. BANKSY revealed unexpected niche-dependent cell states in the mouse brain and outperformed competing methods on domain segmentation and cell typing benchmarks. BANKSY can also be used for quality control of spatial transcriptomics data and for spatially aware batch effect correction. Importantly, it is substantially faster and more scalable than existing methods, enabling the processing of millions of cell datasets. In summary, BANKSY provides an accurate, biologically motivated, scalable and versatile framework for analyzing spatially resolved omics data.

A fundamental property of solid tissues is the arrangement of individual cell types in stereotypical spatial patterns. Spatial omics technologies now facilitate the study of tissue structure by revealing both the spatial locations and molecular profiles of cells. These technologies provide highly multiplexed transcriptomic, genomic or proteomic profiles at up to single-cell resolution, together with their locations (for example, multiplexed fluorescence in situ hybridization (FISH)1,2,3, Slide-seq4, Slide-DNA-seq5, multiplexed ion beam imaging by time of flight6, CosMx7, CODEX8), and thus provide unprecedented insights into cellular states, functions and interactions within the tissue context.

Leave a Comment