Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

COMPUTATIONAL GENOMICS

Graphing cell relations in spatial transcriptomics

Nature Computational Science volume 2, pages 354–355 (2022)Cite this article

Subjects

A graph neural network-based tool is introduced to perform unsupervised cell clustering using spatially resolved transcriptomics data that can uncover cell identities, interactions, and spatial organization in tissues and organs.

The functions and gene expression profiles of cells depend on their local environment within a tissue. Knowledge of relative locations of cells is therefore essential for understanding the role of different cell types in normal function and disease pathology. Single-cell RNA sequencing (scRNA-seq) has made it possible to characterize cellular gene expression at single-cell resolution, but it cannot uncover the physical relationship among cells. The lack of spatial context prohibits us from investigating the complicated transcriptional architecture of heterogeneous tissues. For example, subpopulations of cancer cells can vastly differ from each other in their gene expression profiles and cellular properties, depending on the tumor microenvironment. In another example, brain tissue comprises a multitude of highly specialized neuron and glial cells within close proximity of each other. Writing in Nature Computational Science, Jiachen Li and colleagues1 introduce CCST (Cell Clustering for Spatial Transcriptomics), a tool that can perform unsupervised cell clustering to identify spatial domains, to discover sub cell types, and to uncover cell interactions, based on a graph neural network approach.

Your institute does not have access to this article

Access options

Buy article

Get time limited or full article access on ReadCube.

$32.00

Buy

All prices are NET prices.

Fig. 1: Overview of the graph-based model approach, processing SRT data from the human dorsolateral prefrontal cortex generated with 10x Visium7 as an example input.

References

  1. Li, J., Chen, S., Pan, X., Yuan, Y. & Shen, H.-B. Nat. Comput. Sci. https://doi.org/10.1038/s43588-022-00266-5 (2022).

    Article  Google Scholar 

  2. Crosetto, N., Bienko, M. & van Oudenaarden, A. Nat. Rev. Genet. 16, 57–66 (2014).

    Article  Google Scholar 

  3. Burgess, D. J. Nat. Rev. Genet. 20, 317–317 (2019).

    Article  Google Scholar 

  4. Nat. Methods 18, 1 (2021).

  5. Xia, C., Fan, J., Emanuel, G., Hao, J. & Zhuang, X. Proc. Natl Acad. Sci. USA 116, 19490–19499 (2019).

    Article  Google Scholar 

  6. Eng, C. H. L. et al. Nature 568, 235–239 (2019).

    Article  Google Scholar 

  7. Maynard, K. R. et al. Nat. Neurosci. 24, 425–436 (2021).

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Biomedical Engineering, Vanderbilt University, Nashville, TN, USA

    Xin Zhou

  2. Department of Computer Science, Vanderbilt University, Nashville, TN, USA

    Xin Zhou

Authors
  1. Xin Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xin Zhou.

Ethics declarations

Competing interests

The author declares no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zhou, X. Graphing cell relations in spatial transcriptomics. Nat Comput Sci 2, 354–355 (2022). https://doi.org/10.1038/s43588-022-00269-2

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s43588-022-00269-2

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing