ChromAgeNet AI identifies aging in blood stem cells

Researchers from the Bellvitge Biomedical Research Institute (IDIBELL), the Barcelona Supercomputing Center, and other collaborating institutions have developed ChromAgeNet, a deep learning framework designed to detect aging in hematopoietic stem cells (HSCs).

Published in the journal Aging Cell, the study demonstrates that the model can analyze three-dimensional microscopy images of the nucleus to identify changes in chromatin architecture. Unlike traditional methods that focus on molecular measurements like DNA methylation, ChromAgeNet extracts information from the physical organization of the DNA-protein complex. The AI achieved a 77% accuracy rate in distinguishing between young and aged cells by identifying patterns such as chromatin entropy, peripheral heterochromatin, and chromatin condensates.

This technology could serve as a screening tool for rejuvenation research, allowing scientists to evaluate how effectively potential interventions can reverse age-associated changes in the immune and blood-forming systems.