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

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

^*Corresponding author for this work

Department of Biostatistics

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

107 Citations (Scopus)

59 Downloads (CityUHK Scholars)

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. © The Author(s) 2023.

Original language	English
Article number	7848
Journal	Nature Communications
Volume	14
Online published	29 Nov 2023
DOIs	https://doi.org/10.1038/s41467-023-43629-w
Publication status	Published - 2023

Funding

We acknowledge the following grants: Hong Kong Research Grant Council grants nos. 16301419, 16308120, 16307221 and 16307322, Hong Kong University of Science and Technology Startup Grants R9405 and Z0428 from the Big Data Institute, Guangdong-Hong Kong-Macao Joint Laboratory grant no. 2020B1212030001 and the RGC Collaborative Research Fund grant no. C6021-19EF to C.Y.; Shenzhen Science and Technology Program JCYJ20220818103001002), and the Guangdong Provincial Key Laboratory of Big Data Computing, The Chinese University of Hong Kong, Shenzhen to Xiang W.; Shenzhen Research Institute of Big Data Internal Project J00220230008 to J.X.; Chinese University of Hong Kong startup grant (4930181), the Chinese University of Hong Kong Science Faculty’s Collaborative Research Impact Matching Scheme (CRIMS 4620033), and Hong Kong Research Grant Council (24301419, 14301120) to Z.L.; Hong Kong Research Grant Council grant no. 16209820, the Innovation and Technology Commission (ITCPD/17-9), Lo Ka Chung Foundation through the Hong Kong Epigenomics Project, Chau Hoi Shuen Foundation, the SpatioTemporal Omics Consortium (STOC) and the STOmics Grant Program to A.R.W.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

RGC Funding Information

RGC-funded

Access Output

10.1038/s41467-023-43629-w

180189581.pdfFinal Published version, 6.55 MBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{2206d033398245d0832140eba25a8de6,

title = "Integrating spatial and single-cell transcriptomics data using deep generative models with SpatialScope",

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{\textquoteright}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. {\textcopyright} The Author(s) 2023.",

author = "Xiaomeng Wan and Jiashun Xiao and Tam, \{Sindy Sing Ting\} and Mingxuan Cai and Ryohichi Sugimura and Yang Wang and Xiang Wan and Zhixiang Lin and Wu, \{Angela Ruohao\} and Can Yang",

year = "2023",

doi = "10.1038/s41467-023-43629-w",

language = "English",

volume = "14",

journal = "Nature Communications",

issn = "2041-1723",

publisher = "Springer Nature",

}

TY - JOUR

T1 - Integrating spatial and single-cell transcriptomics data using deep generative models with SpatialScope

AU - Wan, Xiaomeng

AU - Xiao, Jiashun

AU - Tam, Sindy Sing Ting

AU - Cai, Mingxuan

AU - Sugimura, Ryohichi

AU - Wang, Yang

AU - Wan, Xiang

AU - Lin, Zhixiang

AU - Wu, Angela Ruohao

AU - Yang, Can

PY - 2023

Y1 - 2023

N2 - 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. © The Author(s) 2023.

AB - 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. © The Author(s) 2023.

UR - https://www.scopus.com/pages/publications/85178251110

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85178251110&origin=recordpage

U2 - 10.1038/s41467-023-43629-w

DO - 10.1038/s41467-023-43629-w

M3 - RGC 21 - Publication in refereed journal

C2 - 38030617

SN - 2041-1723

VL - 14

JO - Nature Communications

JF - Nature Communications

M1 - 7848

ER -

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

Abstract

Funding

UN SDGs

Publisher's Copyright Statement

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this