Leveraging spatial transcriptomics data to recover cell locations in single-cell RNA-seq with CeLEry

• Authors: Jian Hu, Emory University; Q Zhang, School of Medicine; S Jiang, University of Pennsylvania Perelman School of Medicine; A Schroeder, University of Pennsylvania Perelman School of Medicine; K Li, Biogen Inc.; B Zhang, Biogen Inc.; D Dai, University of Pennsylvania; EB Lee, University of Pennsylvania; R Xiao, University of Pennsylvania Perelman School of Medicine; M Li, University of Pennsylvania Perelman School of Medicine
• Journal Title: Nature Communications
• Volume: Volume 14, Number 1
• Publisher: (publisher) | 2023-12-01, Pages 4050-4050
• Type of Work: Article
• Publisher DOI: http://doi.org/10.1038/s41467-023-39895-3
• Keywords: Transcriptome; Apium; Single-Cell Gene Expression Analysis; Sequence Analysis, RNA; Single-Cell Analysis; Gene Expression Profiling

Abstract

Single-cell RNA sequencing (scRNA-seq) has revolutionized our understanding of cellular heterogeneity in health and disease. However, the lack of physical relationships among dissociated cells has limited its applications. To address this issue, we present CeLEry (Cell Location recovEry), a supervised deep learning algorithm that leverages gene expression and spatial location relationships learned from spatial transcriptomics to recover the spatial origins of cells in scRNA-seq. CeLEry has an optional data augmentation procedure via a variational autoencoder, which improves the method’s robustness and allows it to overcome noise in scRNA-seq data. We show that CeLEry can infer the spatial origins of cells in scRNA-seq at multiple levels, including 2D location and spatial domain of a cell, while also providing uncertainty estimates for the recovered locations. Our comprehensive benchmarking evaluations on multiple datasets generated from brain and cancer tissues using Visium, MERSCOPE, MERFISH, and Xenium demonstrate that CeLEry can reliably recover the spatial location information for cells using scRNA-seq data.