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.

  • Article
  • Published:

Integrative deep learning of spatial multi-omics with SWITCH

Nature Computational Science volume 5, pages 1051–1063 (2025)Cite this article

Subjects

Abstract

Advancements in spatial omics permit spatially resolved measurements across several biological modalities. The high cost of acquiring co-profiled multimodal data limits the analysis. This underscores the necessity for computational methods to integrate unpaired spatial multi-omics data and perform cross-modal predictions on single-modality data. The integration of spatial omics is challenging due to typically low signal-to-noise ratios. Here we introduce SWITCH (Spatially Weighted Multi-omics Integration and Cross-modal Translation with Cycle-mapping Harmonization), a deep generative model for spatial multi-omics integration. SWITCH presents a cycle-mapping mechanism that produces dependable cross-modal translations without requiring additional paired data. These cross-modal translations function as pseudo-pairs to provide supplementary signals. Systematic evaluations demonstrate that SWITCH outperforms existing methods in terms of integration accuracy and achieves more precise spatial domain delineation, resolving brain cortical structures at higher resolution. The reliability of cross-modal translations was validated, facilitating various downstream analyses such as differential analysis, trajectory inference and gene regulatory network inference.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Architecture of SWITCH framework.
Fig. 2: Benchmarking the integration performance of SWITCH.
Fig. 3: SWITCH achieves reliable cross-modal imputation and uncertainty estimation.
Fig. 4: Cross-modal imputation in unpaired mouse embryo data enables diverse downstream analyses.
Fig. 5: SWITCH integrates ST and single-cell ATAC data to infer spatial chromatin accessibility.

Similar content being viewed by others

Data availability

Source data are available with this paper. All datasets used in this study are publicly available. Detailed information about the datasets, as well as the accessible code and links, can be found in Supplementary Table 2. The processed datasets are freely available at https://doi.org/10.5281/zenodo.15602076 (ref. 43).

Code availability

The source code of SWITCH, along with Jupyter notebooks for reproducing the results in this study, is available at https://github.com/zzli123/SWITCH/ and https://doi.org/10.5281/zenodo.16522594 (ref. 44).

References

  1. Chen, K. H., Boettiger, A. N., Moffitt, J. R., Wang, S. & Zhuang, X. Spatially resolved, highly multiplexed RNA profiling in single cells. Science 348, aaa6090 (2015).

    Article  Google Scholar 

  2. Rodriques, S. G. et al. Slide-seq: a scalable technology for measuring genome-wide expression at high spatial resolution. Science 363, 1463–1467 (2019).

    Article  Google Scholar 

  3. Liu, Y. et al. High-spatial-resolution multi-omics sequencing via deterministic barcoding in tissue. Cell 183, 1665–1681 (2020).

    Article  Google Scholar 

  4. Chen, A. et al. Spatiotemporal transcriptomic atlas of mouse organogenesis using DNA nanoball-patterned arrays. Cell 185, 1777–1792 (2022).

    Article  Google Scholar 

  5. Deng, Y. et al. Spatial-CUT&tag: spatially resolved chromatin modification profiling at the cellular level. Science 375, 681–686 (2022).

    Article  Google Scholar 

  6. Deng, Y. et al. Spatial profiling of chromatin accessibility in mouse and human tissues. Nature 609, 375–383 (2022).

    Article  Google Scholar 

  7. Lu, T., Ang, C. E. & Zhuang, X. Spatially resolved epigenomic profiling of single cells in complex tissues. Cell 185, 4448–4464 (2022).

    Article  Google Scholar 

  8. Goltsev, Y. et al. Deep profiling of mouse splenic architecture with codex multiplexed imaging. Cell 174, 968–981 (2018).

    Article  Google Scholar 

  9. He, S. et al. High-plex imaging of RNA and proteins at subcellular resolution in fixed tissue by spatial molecular imaging. Nat. Biotechnol. 40, 1794–1806 (2022).

    Article  Google Scholar 

  10. Liu, Y. et al. High-plex protein and whole transcriptome co-mapping at cellular resolution with spatial CITE-seq. Nat. Biotechnol. 41, 1405–1409 (2023).

    Article  Google Scholar 

  11. Zhang, D. et al. Spatial epigenome–transcriptome co-profiling of mammalian tissues. Nature 616, 113–122 (2023).

    Article  Google Scholar 

  12. Jiang, F. et al. Simultaneous profiling of spatial gene expression and chromatin accessibility during mouse brain development. Nat. Methods 20, 1048–1057 (2023).

    Article  Google Scholar 

  13. Vandereyken, K., Sifrim, A., Thienpont, B. & Voet, T. Methods and applications for single-cell and spatial multi-omics. Nat. Rev. Genet. 24, 494–515 (2023).

    Article  Google Scholar 

  14. Stuart, T. et al. Comprehensive integration of single-cell data. Cell 177, 1888–1902 (2019).

    Article  Google Scholar 

  15. Welch, J. D. et al. Single-cell multi-omic integration compares and contrasts features of brain cell identity. Cell 177, 1873–1887 (2019).

    Article  Google Scholar 

  16. Dou, J. et al. Bi-order multimodal integration of single-cell data. Genome Biol. 23, 112 (2022).

    Article  Google Scholar 

  17. Cao, Z. J. & Gao, G. Multi-omics single-cell data integration and regulatory inference with graph-linked embedding. Nat. Biotechnol. 40, 1458–1466 (2022).

    Article  Google Scholar 

  18. Xiong, L. et al. Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding space. Nat. Commun. 13, 6118 (2022).

    Article  Google Scholar 

  19. Chen, H., Ryu, J., Vinyard, M. E., Lerer, A. & Pinello, L. SIMBA: single-cell embedding along with features. Nat. Methods 21, 1003–1013 (2024).

    Article  Google Scholar 

  20. Chen, S. et al. Integration of spatial and single-cell data across modalities with weakly linked features. Nat. Biotechnol. 42, 1096–1106 (2024).

    Article  Google Scholar 

  21. Samaran, J., Peyré, G. & Cantini, L. scConfluence: single-cell diagonal integration with regularized inverse optimal transport on weakly connected features. Nat. Commun. 15, 7762 (2024).

    Article  Google Scholar 

  22. Tang, Z. et al. Modal-nexus auto-encoder for multi-modality cellular data integration and imputation. Nat. Commun. 15, 9021 (2024).

    Article  Google Scholar 

  23. You, Y. et al. Systematic comparison of sequencing-based spatial transcriptomic methods. Nat. Methods 21, 1743–1754 (2024).

    Article  Google Scholar 

  24. Cohen Kalafut, N., Huang, X. & Wang, D. Joint variational autoencoders for multimodal imputation and embedding. Nat. Mach. Intell. 5, 631–642 (2023).

    Article  Google Scholar 

  25. Ashuach, T. et al. MultiVI: deep generative model for the integration of multimodal data. Nat. Methods 20, 1222–1231 (2023).

    Article  Google Scholar 

  26. Cao, Y. et al. scButterfly: a versatile single-cell cross-modality translation method via dual-aligned variational autoencoders. Nat. Commun. 15, 2973 (2024).

    Article  Google Scholar 

  27. Wu, K. E., Yost, K. E., Chang, H. Y. & Zou, J. Babel enables cross-modality translation between multiomic profiles at single-cell resolution. Proc. Natl Acad. Sci. USA 118, e2023070118 (2021).

    Article  Google Scholar 

  28. Liu, J., Huang, Y., Singh, R., Vert, J. P. & Noble, W. S. Jointly embedding multiple single-cell omics measurements. Algorithms Bioinform. 143, 10 (2019).

    Google Scholar 

  29. Sunkin, S. M. et al. Allen Brain Atlas: an integrated spatio-temporal portal for exploring the central nervous system. Nucleic Acids Res. 41, D996–D1008 (2012).

    Article  Google Scholar 

  30. Ma, N. X., Puls, B. & Chen, G. Transcriptomic analyses of NeuroD1-mediated astrocyte-to-neuron conversion. Dev. Neurobiol. 82, 375–391 (2022).

    Article  Google Scholar 

  31. Zhou, Y. et al. Cooperative integration of spatially resolved multi-omics data with COSMOS. Nature Commun. 16, 27 (2025).

    Article  Google Scholar 

  32. Cao, J. et al. The single-cell transcriptional landscape of mammalian organogenesis. Nature 566, 496–502 (2019).

    Article  Google Scholar 

  33. Englund, C. et al. Pax6, Tbr2, and Tbr1 are expressed sequentially by radial glia, intermediate progenitor cells, and postmitotic neurons in developing neocortex. J. Neurosci. 25, 247–251 (2005).

    Article  Google Scholar 

  34. Bayam, E. et al. Genome-wide target analysis of NEUROD2 provides new insights into regulation of cortical projection neuron migration and differentiation. BMC Genom. 16, 681 (2015).

    Article  Google Scholar 

  35. Bormuth, I. et al. Neuronal basic helix–loop–helix proteins Neurod2/6 regulate cortical commissure formation before midline interactions. J. Neurosci. 33, 641–651 (2013).

    Article  Google Scholar 

  36. Hahn, M. A. et al. Reprogramming of DNA methylation at NEURO2-bound sequences during cortical neuron differentiation. Sci. Adv. 5, eaax0080 (2019).

    Article  Google Scholar 

  37. Zu, S. et al. Single-cell analysis of chromatin accessibility in the adult mouse brain. Nature 624, 378–389 (2023).

    Article  Google Scholar 

  38. Chai, H et al. Tri-omic single-cell mapping of the 3D epigenome and transcriptome in whole mouse brains throughout the lifespan. Nat. Methods 22, 994–1007 (2025).

  39. Bogutz, A. B. et al. Transcription factor ASCL2 is required for development of the glycogen trophoblast cell lineage. PLoS Genet. 14, e1007587 (2018).

    Article  Google Scholar 

  40. Kunke, M. et al. SOX10-mediated regulation of enteric glial phenotype in vitro and its relevance for neuroinflammatory disorders. J. Mol. Neurosci. 75, 26 (2025).

    Article  Google Scholar 

  41. Forrest, M. P. et al. The psychiatric risk gene transcription factor 4 (TCF4) regulates neurodevelopmental pathways associated with schizophrenia, autism, and intellectual disability. Schizophr. Bull. 44, 1100–1110 (2018).

    Article  Google Scholar 

  42. Granja, J. M. et al. ArchR is a scalable software package for integrative single-cell chromatin accessibility analysis. Nat. Genet. 53, 403–411 (2021).

    Article  Google Scholar 

  43. Li, Z. Benchmark datasets for SWITCH. Zenodo https://doi.org/10.5281/zenodo.15602076 (2025).

  44. Zhongzhan, L. SWITCH: a deep generative model for spatial multi-omics integration and cross-modal prediction. Zenodo https://doi.org/10.5281/zenodo.16522594 (2025).

Download references

Acknowledgements

This work was supported by the National Key Research and Development Program of China (2022YFA1103102), the National Natural Science Foundation of China (32170589, 32370616, 32488101, 32330030), Xiaomi Young Talents Program and Shanghai Eastern Youth Talent Program.

Author information

Authors and Affiliations

  1. Clinical and Translational Research Center of Shanghai First Maternity and Infant Hospital, Frontier Science Center for Stem Cell Research, School of Life Sciences and Technology, Tongji University, Shanghai, China

    Zhongzhan Li, Haixin Liang, Ruohui Tang, Jiani Yang, Ziling Gan, Shaorong Gao & Yanping Zhang

  2. School of Computer Science and Technology, Tongji University, Shanghai, China

    Sanqing Qu, Xudong Zhang, Fan Lu & Guang Chen

Authors
  1. Zhongzhan Li
    View author publications

    Search author on:PubMed Google Scholar

  2. Sanqing Qu
    View author publications

    Search author on:PubMed Google Scholar

  3. Haixin Liang
    View author publications

    Search author on:PubMed Google Scholar

  4. Ruohui Tang
    View author publications

    Search author on:PubMed Google Scholar

  5. Xudong Zhang
    View author publications

    Search author on:PubMed Google Scholar

  6. Fan Lu
    View author publications

    Search author on:PubMed Google Scholar

  7. Jiani Yang
    View author publications

    Search author on:PubMed Google Scholar

  8. Ziling Gan
    View author publications

    Search author on:PubMed Google Scholar

  9. Shaorong Gao
    View author publications

    Search author on:PubMed Google Scholar

  10. Yanping Zhang
    View author publications

    Search author on:PubMed Google Scholar

  11. Guang Chen
    View author publications

    Search author on:PubMed Google Scholar

Contributions

G.C., Y.Z. and S.G. conceived and supervised the study. Z.L. and S.Q. designed the method with help of X.Z. and F.L. Z.L. conducted the experiment with the help of J.Y., R.T., H.L. and Z.G. Z.L. designed and created all main figures. Z.L., Y.Z., S.Q. and G.C. wrote the paper. All authors read and approved the paper.

Corresponding authors

Correspondence to Shaorong Gao, Yanping Zhang or Guang Chen.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Computational Science thanks Christopher A. Jackson, Michelle Y. Y. Lee and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Primary Handling Editor: Ananya Rastogi, in collaboration with the Nature Computational Science team. Peer reviewer reports are available.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Source data

Source Data Fig. 2 (download ZIP )

Statistical source data.

Source Data Fig. 3 (download ZIP )

Statistical source data.

Source Data Fig. 4 (download ZIP )

Statistical source data.

Source Data Fig. 5 (download ZIP )

Statistical source data.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, Z., Qu, S., Liang, H. et al. Integrative deep learning of spatial multi-omics with SWITCH. Nat Comput Sci 5, 1051–1063 (2025). https://doi.org/10.1038/s43588-025-00891-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s43588-025-00891-w

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