Deep learning predicts mouse hematopoietic stem cell aging from chromatin architecture
A convolutional neural network named ChromAgeNet distinguished young from aged mouse stem cells using three-dimensional nuclear images and identified key structural markers of aging.
Aging cell · Picazo PI et al. · Paper published 28 Sep 2026
Researchers developed a convolutional neural network called ChromAgeNet to detect aging in murine hematopoietic stem cells. The team trained the model on three-dimensional microscope images of DAPI-stained cell nuclei to differentiate young stem cells from aged stem cells. The algorithm distinguished aged cells from young cells with an AUROC of 0.77 ± 0.03, outperforming traditional machine learning methods trained on handcrafted features. Using explainable artificial intelligence techniques, the authors identified chromatin entropy, peripheral heterochromatin, and chromatin condensates as key predictive markers of cellular age. Finally, the researchers evaluated the model as a phenotypic screening tool to detect rejuvenation signatures in aged stem cells treated with epigenetic drugs.
Why it matters
Changes in three-dimensional chromatin organization are hallmarks of aging that have remained difficult to measure systematically. This computational framework demonstrates that spatial chromatin reorganization can quantify stem cell aging states and screen candidate rejuvenation therapies.
Caveats
The study was conducted exclusively in mouse cells, meaning performance in human hematopoietic cells was not established. Additionally, the classifier demonstrated moderate predictive accuracy, achieving an AUROC of 0.77.
Written from the paper’s abstract, and every claim checked against it before publishing. Read the paper for the full methods and data.
The paper
Deep Learning Predicts Hematopoietic Stem Cell Aging From 3D Chromatin Images
Picazo PI, Mejía-Ramírez E, Di Bari D et al.
Aging cell · 28 Sep 2026 · Peer-reviewed
- Relevance
- Core geroscience
- News value
- Notable
- Evidence
- Cells
- Status
- Peer-reviewed
More on Aging clocks
See allBiological age uncertainty independently predicts mortality and health decline in humans
Researchers derived biological age uncertainty across UK Biobank participants, finding that higher uncertainty reflects reduced physiological coherence and predicts worse health outcomes.
medRxiv · Li Y et al.
Organ age acceleration and mortality risk reflect distinct biological processes
Multi-omics clocks across fourteen organs reveal divergent molecular programs and uncover thirteen candidate genes separating age acceleration from mortality.
Research Square · Na R et al.
Retinal imaging model predicts age and reveals sex differences in human aging
The retinal age gap correlates with mortality, disease risks, and sex-specific genetic pathways in more than 71,000 UK Biobank participants.
Nature communications · Trofimova O et al.
Blood cell composition explains substantial variation in DNA methylation age
Cell counts explain less variation in age acceleration and only modestly affect its links to mortality and 176 incident health outcomes.
Genome medicine · Jonkman TH et al.
Kidney tubular epithelial cells drive accelerated epigenetic aging in disease
A cross-species single-cell atlas links injured human kidney cells and aged mouse kidneys to shared chromatin reorganization and impaired repair.
Nature aging · Jeong H et al.