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.

SINGLE-CELL MULTIOMICS

Interpretable multi-modal data integration

Nature Computational Science volume 2, pages 8–9 (2022)Cite this article

Subjects

Integrating multi-modal features is challenging due to the differences in the underlying distributions of each data type and the nonlinear associations across modalities. The deepManReg model improves the identification and interpretability of associations between modalities defining complex phenotypes.

Synchronized disruptions of the cells’ normal state lead to the development of diseases and changes in the regulatory networks that shape complex phenotypes. Identifying such changes requires the systematic characterization of cells’ features and their differences between control and affected groups. However, complex phenotypes are usually associated with the perturbation or changes in more than one feature type in patterns typically overlooked using a single data type analysis1. For that reason, recently, novel high-throughput technologies have been developed to describe the same biological process by measuring multiple cellular characteristics, including histone modifications, membrane proteins, the proteome, chromatin states, the transcriptome, and other cellular phenotypes such as electrophysiological signals, from the same single cell2. Integrating multiple sources of information describing the same biological process provides more robust and precise insight into the biological mechanisms that drive disease development and progression3. Nevertheless, it is not an easy task. Usually, each data type is better described using a different underlying distribution, the features are often associated across modalities, and in the case of single-cell features, the data is also highly sparse. Writing in Nature Computational Science, Nam D. Nguyen and colleagues introduce deepManReg, an interpretable Python-based deep manifold-regularized learning model for multi-modal data integration3.

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

Access options

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Learn more

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

Fig. 1: An example of single-cell multi-modal data integration through deepManReg.

References

  1. Zhu, C., Preissl, S. & Ren, B. Nat. Methods 17, 11–14 (2020).

    Article  Google Scholar 

  2. Cadwell, C. R. et al. Nat. Protoc. 12, 2531–2553 (2017).

    Article  Google Scholar 

  3. Nguyen, N. D., Huang, J. & Wang, D. Nat. Comput. Sci. https://doi.org/10.1038/s43588-021-00185-x (2022).

  4. Lähnemann, D. et al. Genome Biol. 21, 1–35 (2020).

    Article  Google Scholar 

  5. Joshi, G., Walambe, R. & Kotecha, K. IEEE Access 9, 59800–59821 (2021).

    Article  Google Scholar 

  6. Welch, J. D., Hartemink, A. J. & Prins, J. F. Genome Biol. 18, 1–19 (2017).

    Article  Google Scholar 

  7. Nguyen, N. D., Blaby, I. K. & Wang, D. BMC Genomics 20, 1003 (2019).

    Article  Google Scholar 

  8. Osorio, D. et al. Patterns 1, 100139 (2020).

    Article  Google Scholar 

  9. Efremova, M. & Teichmann, S. A. Nat. Methods 17, 14–17 (2020).

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Norwegian Centre for Molecular Medicine, University of Oslo, Oslo, Norway

    Daniel Osorio

Authors
  1. Daniel Osorio
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Daniel Osorio.

Ethics declarations

Competing interests

The author declares no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Osorio, D. Interpretable multi-modal data integration. Nat Comput Sci 2, 8–9 (2022). https://doi.org/10.1038/s43588-021-00186-w

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s43588-021-00186-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