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.

  • Tools of the Trade
  • Published:

A nuclear morphology-based machine learning algorithm for senescence detection

Nature Reviews Molecular Cell Biology volume 25, page 949 (2024)Cite this article

Subjects

Senescence is a protective cellular response aimed at limiting the proliferation of old, cancerous or damaged cells. In response to various stressors, senescent cells enter stable cell cycle arrest, secrete bioactive factors such as chemokines as part of the senescence-associated secretory phenotype, and acquire characteristic phenotypic and gene expression signatures. Although senescent cells can be cleared by the immune system, their abnormal accumulation contributes to chronic inflammation, age-related pathologies and cancer progression.

To overcome the shortcomings of existing approaches, several labs, including ours, have developed machine learning algorithms based on nuclear morphological changes that are associated with senescence. Our approach utilizes high-throughput nuclear feature extraction along with robust classification and random forest algorithms, enabling the development of generalizable models without relying on computationally intensive operations. Using high-throughput microscopy, we generated training sets based on cancer cell lines and fibroblasts treated with known senescence inducers. The resulting group of algorithms identified senescence induced by different stresses and in different cell types based solely on nuclear morphology. Importantly, we validated these results with nuclear features obtained from open-source software (CellProfiler), from which we developed similarly performing algorithms, ensuring the accessibility and replicability of our protocol.

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

References

Original article

Related article

  • Duran, I. et al. The promise of machine learning approaches to capture cellular senescence heterogeneity. Nat. Aging 4, 1167–1170 (2024)

    Article  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. MRC Laboratory of Medical Sciences (LMS), London, UK

    Imanol Duran

  2. Institute of Clinical Sciences (ICS), Faculty of Medicine, Imperial College London, London, UK

    Imanol Duran

Authors
  1. Imanol Duran
    View author publications

    Search author on:PubMed Google Scholar

Corresponding author

Correspondence to Imanol Duran.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Duran, I. A nuclear morphology-based machine learning algorithm for senescence detection. Nat Rev Mol Cell Biol 25, 949 (2024). https://doi.org/10.1038/s41580-024-00796-y

Download citation

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41580-024-00796-y

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