Deep generative model embedding of single-cell RNA-Seq profiles on hyperspheres and hyperbolic spaces

Single-cell RNA-Seq (scRNA-seq) is invaluable for studying biological systems. Dimensionality reduction is a crucial step in interpreting the relation between cells in scRNA-seq data. However, current dimensionality reduction methods are often confounded by multiple simultaneous technical and biological variability, result in crowding of cells in the center of the latent space, or inadequately capture temporal relationships. Here, we introduce scPhere, a scalable deep generative model to embed cells into low-dimensional hyperspherical or hyperbolic spaces to accurately represent scRNA-seq data. ScPhere addresses multi-level, complex batch factors, facilitates the interactive visualization of large datasets, resolves cell crowding, and uncovers temporal trajectories. We demonstrate scPhere on nine large datasets in complex tissue from human patients or animal development. Our results show how scPhere facilitates the interpretation of scRNA-seq data by generating batch-invariant embeddings to map data from new individuals, identifies cell types affected by biological variables, infers cells' spatial positions in pre-defined biological specimens, and highlights complex cellular relations. Single-cell RNA-seq allows the study of tissues at cellular resolution. Here, the authors demonstrate how deep learning can be used to gain biological insight from such data by accounting for biological and technical variability. Data exploration is improved by accurately visualizing cells on an interactive 3D surface.

Automated summary

scPhere is a scalable deep generative model that accurately embeds cells into low-dimensional hyperspherical or hyperbolic spaces to represent scRNA-seq data. By addressing multi-level technical and biological variability, resolving cell crowding, and uncovering temporal trajectories, scPhere facilitates the interpretation and analysis of biological data.