Biologically informed deep learning to query gene programs in single-cell atlases

Lotfollahi et al. present ExpiMap, a deep-learning model enabling interpretable reference mapping of RNA sequencing data using biologically defined entities, offering end-to-end analysis from dataset integration to functional interpretation. The increasing availability of large-scale single-cell atlases has enabled the detailed description of cell states. In parallel, advances in deep learning allow rapid analysis of newly generated query datasets by mapping them into reference atlases. However, existing data transformations learned to map query data are not easily explainable using biologically known concepts such as genes or pathways. Here we propose expiMap, a biologically informed deep-learning architecture that enables single-cell reference mapping. ExpiMap learns to map cells into biologically understandable components representing known 'gene programs'. The activity of each cell for a gene program is learned while simultaneously refining them and learning de novo programs. We show that expiMap compares favourably to existing methods while bringing an additional layer of interpretability to integrative single-cell analysis. Furthermore, we demonstrate its applicability to analyse single-cell perturbation responses in different tissues and species and resolve responses of patients who have coronavirus disease 2019 to different treatments across cell types.

Automated summary

Lotfollahi et al. propose ExpiMap, a biologically informed deep-learning model for interpretable reference mapping of RNA sequencing data. ExpiMap maps cells into biologically understandable components representing known 'gene programs', allowing for detailed analysis and interpretation of single-cell data.