CoChat
Sign Up
Cited by 761Single-cell and spatial transcriptomicsGene expression and cancer classificationSpatial and Panel Data Analysis

Deciphering spatial domains from spatially resolved transcriptomics with an adaptive graph attention auto-encoder

Open access
Dong, Kangning, Zhang, Shihua·2022·Nature Communications
DOI 10.1038/s41467-022-29439-6PMC PMC8976049

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Recent advances in spatially resolved transcriptomics have enabled comprehensive measurements of gene expression patterns while retaining the spatial context of the tissue microenvironment. Deciphering the spatial context of spots in a tissue needs to use their spatial information carefully. To this end, we develop a graph attention auto-encoder framework STAGATE to accurately identify spatial domains by learning low-dimensional latent embeddings via integrating spatial information and gene expression profiles. To better characterize the spatial similarity at the boundary of spatial domains, STAGATE adopts an attention mechanism to adaptively learn the similarity of neighboring spots, and an optional cell type-aware module through integrating the pre-clustering of gene expressions. We validate STAGATE on diverse spatial transcriptomics datasets generated by different platforms with different spatial resolutions. STAGATE could substantially improve the identification accuracy of spatial domains, and denoise the data while preserving spatial expression patterns. Importantly, STAGATE could be extended to multiple consecutive sections to reduce batch effects between sections and extracting three-dimensional (3D) expression domains from the reconstructed 3D tissue effectively.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41467-022-29439-6

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Various methods have been developed to integrate single cells with different omics, uncover regulatory networks of single-cell datasets, or combine gene expression profiles with spatial information.

    “Various methods have been developed to integrate single cells with different omics [22], uncover the regulatory networks of single-cell datasets [23], or combine gene expression profiles with spatial information [24].”

    From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [24]

  • STAGATE utilized the graph attention autoencoder model to learn integrated spatial and gene expression profiles.

    “STAGATE utilized the graph attention autoencoder model to learn the integrated spatial and gene expression profiles [24].”

    From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [24]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 36

  1. [1]Asp M Bergenstråhle J Lundeberg J Spatially resolved transcriptomes—next generation tools for tissue exploration BioEssays 2020 42 1900221 10.1002/bies.201900221 32363691 · DOI · Paper page
  2. [4]Rodriques SG Slide-seq: A scalable technology for measuring genome-wide expression at high spatial resolution Science 2019 363 1463 1467 10.1126/science.aaw1219 30923225 PMC6927209 · DOI · Paper page
  3. [5]Stickels RR Highly sensitive spatial transcriptomics at near-cellular resolution with Slide-seqV2 Nat. Biotechnol. 2021 39 313 319 10.1038/s41587-020-0739-1 33288904 PMC8606189 · DOI · Paper page
  4. [6]Chen, A. et al. Large field of view-spatially resolved transcriptomics at nanoscale resolution. bioRxiv.10.1101/2021.01.17.427004 (2021). · DOI
  5. [7]Fu, X. et al. Continuous polony gels for tissue mapping with high resolution and RNA capture efficiency. bioRxiv.10.1101/2021.03.17.435795 (2021). · DOI · Paper page
  6. [8]Maynard KR Transcriptome-scale spatial gene expression in the human dorsolateral prefrontal cortex Nat. Neurosci. 2021 24 425 436 10.1038/s41593-020-00787-0 33558695 PMC8095368 · DOI · Paper page
  7. [9]Blondel VD Guillaume J-L Lambiotte R Lefebvre E Fast unfolding of communities in large networks J. Stat. Mech. -Theory E. 2008 2008 P10008 10.1088/1742-5468/2008/10/P10008 · DOI · Paper page
  8. [10]Elosua-Bayes M Nieto P Mereu E Gut I Heyn H SPOTlight: Seeded NMF regression to deconvolute spatial transcriptomics spots with single-cell transcriptomes Nucleic Acids Res. 2021 49 e50 e50 10.1093/nar/gkab043 33544846 PMC8136778 · DOI · Paper page
  9. [11]Cable, D. M. et al. Robust decomposition of cell type mixtures in spatial transcriptomics. Nat. Biotechnol. 10.1038/s41587-021-00830-w (2021). PMC8606190 33603203 · DOI · Paper page
  10. [12]Zhao E Spatial transcriptomics at subspot resolution with BayesSpace Nat. Biotechnol 2021 39 1375 1384 10.1038/s41587-021-00935-2 34083791 PMC8763026 · DOI
  11. [13]Pham, D. et al. stLearn: integrating spatial location, tissue morphology and gene expression to find cell types, cell-cell interactions and spatial trajectories within undissociated tissues. bioRxiv.10.1101/2020.05.31.125658 (2020). · DOI
  12. [14]Chen, J. et al. Unsupervised spatially embedded deep representation of spatial transcriptomics. bioRxiv.10.1101/2021.06.15.448542 (2021). PMC10790257 38217035 · DOI
  13. [15]Dries R Giotto: a toolbox for integrative analysis and visualization of spatial expression data Genome Biol. 2021 22 1 31 10.1186/s13059-021-02286-2 33685491 PMC7938609 · DOI
  14. [16]Hu J SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network Nat. Methods 2021 18 1342 1351 10.1038/s41592-021-01255-8 34711970 · DOI · Paper page
  15. [17]Chang, Y. et al. Define and visualize pathological architectures of human tissues from spatially resolved transcriptomics using deep learning. bioRxiv.10.1101/2021.07.08.451210 (2021). PMC9440291 36090815 · DOI
  16. [18]Salehi, A. & Davulcu, H. Graph attention auto-encoders. in 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI). 989–996 (2020).
  17. [20]Fraley C Raftery AE Murphy T B. mclust version 4 for R: Normal mixture modeling for model-based clustering, classification, and density estimation R. J. 2012 8 289 317 PMC5096736 27818791
  18. [22]Gilmore EC Herrup K Cortical development: Layers of complexity Curr. Biol. 1997 7 R231 R234 10.1016/S0960-9822(06)00108-4 9162498 · DOI
  19. [23]Wolf FA PAGA: Graph abstraction reconciles clustering with trajectory inference through a topology preserving map of single cells Genome Biol. 2019 20 1 9 10.1186/s13059-019-1663-x 30890159 PMC6425583 · DOI · Paper page
  20. [25]Windhorst S Song K Gazdar AF Inositol-1, 4, 5-trisphosphate 3-kinase-A (ITPKA) is frequently over-expressed and functions as an oncogene in several tumor types Biochem. Pharmacol. 2017 137 1 9 10.1016/j.bcp.2017.03.023 28377279 PMC5555585 · DOI
  21. [26]Lennon MJ Jones SP Lovelace MD Guillemin GJ Brew BJ Bcl11b—A critical neurodevelopmental transcription factor—Roles in health and disease Front. Cell. Neurosci. 2017 11 89 10.3389/fncel.2017.00089 28424591 PMC5372781 · DOI
  22. [27]Laeremans A AMIGO2 mRNA expression in hippocampal CA2 and CA3a Brain Struct. Funct. 2013 218 123 130 10.1007/s00429-012-0387-4 22314660 · DOI
  23. [28]Siddiqui TJ An LRRTM4-HSPG complex mediates excitatory synapse development on dentate gyrus granule cells Neuron 2013 79 680 695 10.1016/j.neuron.2013.06.029 23911104 · DOI
  24. [29]Jouroukhin Y DISC1 regulates lactate metabolism in astrocytes: Implications for psychiatric disorders Transl. Psychiat. 2018 8 1 12 10.1038/s41398-018-0123-9 PMC5895599 29643356 · DOI
  25. [30]Schäfer I Müller C Luhmann HJ White R MOBP levels are regulated by Fyn kinase and affect the morphological differentiation of oligodendrocytes J. Cell Sci. 2016 129 930 942 26801084
  26. [32]Kadowaki K Phosphohippolin expression in the rat central nervous system Mol. Brain Res. 2004 125 105 112 10.1016/j.molbrainres.2004.03.021 15193427 · DOI
  27. [33]Zacharias DA Kappen C Developmental expression of the four plasma membrane calcium ATPase (Pmca) genes in the mouse BBA-Gen. Subj. 1999 1428 397 405 10.1016/S0304-4165(99)00058-6 10434059 · DOI
  28. [34]Zhang Y Association between NRGN gene polymorphism and resting-state hippocampal functional connectivity in schizophrenia BMC Psychiatry 2019 19 1 9 10.1186/s12888-018-1996-0 30953482 PMC6451258 · DOI
  29. [37]He Y ClusterMap for multi-scale clustering analysis of spatial gene expression Nat. Commun. 2021 12 1 13 10.1038/s41467-020-20314-w 34625546 PMC8501103 · DOI · Paper page
  30. [38]Petukhov, V. et al. Cell segmentation in imaging-based spatial transcriptomics. Nat. Biotechnol. 40, 345–354 (2022). 34650268
  31. [39]Zhu J Sun S Zhou X SPARK-X: non-parametric modeling enables scalable and robust detection of spatial expression patterns for large spatial transcriptomic studies Genome Biol. 2021 22 1 25 10.1186/s13059-021-02404-0 34154649 PMC8218388 · DOI
  32. [40]Besl PJ McKay ND A method for registration of 3-D shapes IEEE T. Pattern Anal. 1992 14 239 256 10.1109/34.121791 · DOI
  33. [41]Veličković, P. et al. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017). · arXiv
  34. [42]Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). · arXiv
  35. [43]Clevert, D.-A., Unterthiner, T. & Hochreiter, S. Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289 (2015). · arXiv
  36. [44]Ortiz C Molecular atlas of the adult mouse brain Sci. Adv. 2020 6 eabb3446 10.1126/sciadv.abb3446 32637622 PMC7319762 · DOI

Cited by

Sorted by citations

Authors
Dong, K., & Zhang, S.
Affiliations
Chinese Academy of Sciences (CN)
Corresponding author
Zhang, Shihua
ORCID
Venue
Nature Communications
Publisher
Springer Science and Business Media LLC
Published
2022-04-01
Volume
13
Issue
1
Pages
1739-1739
ISSN
2041-1723 (ISSN-L)
DOI
10.1038/s41467-022-29439-6
PMC
PMC8976049
OpenAlex
W4226192560
Cited by
761
References
7
Citations by year
2026: 252 · 2025: 230 · 2024: 188 · 2023: 70 · 2022: 21
FWCI
41.56
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Communications (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Natural Science Foundation of China (61621003, 12126605, 61621003, 12126605, 2019YFA0709501, XDPB17, 2020B1111190001, XDA16021400)
  • Chinese Academy of Sciences (QYZDB-SSW-SYS008, XDA16021400, XDPB17)
  • National Key Research and Development Program of China (XDA16021400, 2019YFA0709501, XDPB17)
  • National Ten Thousand Talent Program
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
  • Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Spatial and Panel Data Analysis
Keywords
spatial transcriptomics, spatial domain identification, spatial similarity, 3D tissue reconstruction, tissue microenvironment
MeSH terms
Cluster Analysis, Transcriptome

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review