Integrating spatial and single-cell transcriptomics data using deep generative models with SpatialScope

Xiaomeng Wan; Jiashun Xiao; Sindy Sing Ting Tam; Mingxuan Cai; Ryohichi Sugimura; Yang Wang; Xiang Wan; Zhixiang Lin; Angela Ruohao Wu; Can Yang

doi:10.1038/s41467-023-43629-w

Integrating spatial and single-cell transcriptomics data using deep generative models with SpatialScope

Nat Commun. 2023 Nov 29;14(1):7848. doi: 10.1038/s41467-023-43629-w.

Authors

Xiaomeng Wan^#¹, Jiashun Xiao^#², Sindy Sing Ting Tam³, Mingxuan Cai⁴, Ryohichi Sugimura⁵, Yang Wang^{1

6

7}, Xiang Wan², Zhixiang Lin⁸, Angela Ruohao Wu^{9

10

11

12}, Can Yang^{13

14

15}

Affiliations

¹ Department of Mathematics, The Hong Kong University of Science and Technology, Hong Kong SAR, China.
² Shenzhen Research Institute of Big Data, Shenzhen, 518172, China.
³ Division of Life Science, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong SAR, China.
⁴ Department of Biostatistics, City University of Hong Kong, Hong Kong SAR, China.
⁵ Li Ka Shing Faculty of Medicine, School of Biomedical Sciences, University of Hong Kong, Hong Kong SAR, China.
⁶ Guangdong-Hong Kong-Macao Joint Laboratory for Data-Driven Fluid Mechanics and Engineering Applications, The Hong Kong University of Science and Technology, Hong Kong SAR, China.
⁷ Big Data Bio-Intelligence Lab, The Hong Kong University of Science and Technology, Hong Kong SAR, China.
⁸ Department of Statistics, The Chinese University of Hong Kong, Hong Kong SAR, China. zhixianglin@cuhk.edu.hk.
⁹ Division of Life Science, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong SAR, China. angelawu@ust.hk.
¹⁰ Department of Chemical and Biological Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China. angelawu@ust.hk.
¹¹ Center for Aging Science, The Hong Kong University of Science and Technology, Hong Kong SAR, China. angelawu@ust.hk.
¹² State Key Laboratory of Molecular Neuroscience, The Hong Kong University of Science and Technology, Hong Kong SAR, China. angelawu@ust.hk.
¹³ Department of Mathematics, The Hong Kong University of Science and Technology, Hong Kong SAR, China. macyang@ust.hk.
¹⁴ Guangdong-Hong Kong-Macao Joint Laboratory for Data-Driven Fluid Mechanics and Engineering Applications, The Hong Kong University of Science and Technology, Hong Kong SAR, China. macyang@ust.hk.
¹⁵ Big Data Bio-Intelligence Lab, The Hong Kong University of Science and Technology, Hong Kong SAR, China. macyang@ust.hk.

^# Contributed equally.

Abstract

The rapid emergence of spatial transcriptomics (ST) technologies is revolutionizing our understanding of tissue spatial architecture and biology. Although current ST methods, whether based on next-generation sequencing (seq-based approaches) or fluorescence in situ hybridization (image-based approaches), offer valuable insights, they face limitations either in cellular resolution or transcriptome-wide profiling. To address these limitations, we present SpatialScope, a unified approach integrating scRNA-seq reference data and ST data using deep generative models. With innovation in model and algorithm designs, SpatialScope not only enhances seq-based ST data to achieve single-cell resolution, but also accurately infers transcriptome-wide expression levels for image-based ST data. We demonstrate SpatialScope's utility through simulation studies and real data analysis from both seq-based and image-based ST approaches. SpatialScope provides spatial characterization of tissue structures at transcriptome-wide single-cell resolution, facilitating downstream analysis, including detecting cellular communication through ligand-receptor interactions, localizing cellular subtypes, and identifying spatially differentially expressed genes.

MeSH terms

Algorithms
Cell Communication
Gene Expression Profiling*
In Situ Hybridization, Fluorescence
Sequence Analysis, RNA
Single-Cell Analysis
Transcriptome*