The machine-learning workflow behind our senescence biomarkers — from data collection to prediction.
As cells age they can enter senescence — a durable state in which they permanently stop dividing yet remain metabolically active, secreting a cocktail of inflammatory signals that disturbs the surrounding tissue. These cells accumulate with age and drive a wide range of age-related pathologies, from fibrosis to neurodegeneration — but they have long been notoriously difficult to identify reliably and at scale.
We develop computational tools to change that. Using deep learning, we read the signatures of senescence and biological age directly from cell-nucleus morphology and routine imaging data, without the need for specialised staining. Trained across large image datasets, these models detect senescent cells, quantify how tissues age, and reveal how candidate interventions shift that trajectory over time.
Coupled with artificial intelligence for target identification and platforms such as mitodb.com for classifying disease mechanisms, these data-driven methods scale far beyond what manual analysis allows. Together they help move the field from simply cataloguing the hallmarks of aging toward measuring — and ultimately modulating — them in living systems, and toward therapies that clear or silence senescent cells.
See the full list of the lab's publications on Google Scholar.