Deep learning was applied to cellular images to predict senescence on the basis of nuclear morphology. These methods recognize senescence in diverse cell types, show increasing senescence with age in liver and dermis, and suggest that higher rates of senescence associate with several age-related diseases but reduced cancer risk.
This is a preview of subscription content, log in via an institution to check access.
References
Kirkland, J. L. & Tchkonia, T. Cellular senescence: a translational perspective. EBioMedicine 21, 21–28 (2017). This Review provides background on senescence and discusses therapeutics.
Childs, B. G. et al. Senescent cells: an emerging target for diseases of ageing. Nat. Rev. Drug Discov. 16, 718–735 (2017). This Review gives an overview of the role of senescence in disease and the potential for therapeutics.
Pathak, R. U., Soujanya, M. & Mishra, R. K. Deterioration of nuclear morphology and architecture: a hallmark of senescence and aging. Ageing Res. Rev. 67, 101264 (2021). This Review discusses how nuclear morphology changes in aging and disease.
Kusumoto, D. et al. Anti-senescent drug screening by deep learning-based morphology senescence scoring. Nat. Commun. 12, 257 (2021). This paper shows that deep learning can detect senescence in cell culture.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This is a summary of: Heckenbach, I. et al. Nuclear morphology is a deep learning biomarker of cellular senescence. Nat. Aging https://doi.org/10.1038/s43587-022-00263-3 (2022)
Rights and permissions
About this article
Cite this article
Predicting senescence across tissues and species using deep learning. Nat Aging 2, 688–689 (2022). https://doi.org/10.1038/s43587-022-00265-1
Published:
Issue Date:
DOI: https://doi.org/10.1038/s43587-022-00265-1
- Springer Nature America, Inc.