Blood test measures total burden of aging cells

When cells become senescent, they stop dividing but do not die. Instead, they begin secreting a mix of signaling molecules known as the SASP, short for senescence-associated secretory phenotype. These molecules can damage neighboring cells, fuel chronic inflammation and raise the risk of age-related diseases. The problem: there are hundreds of SASP components. Until now, no single biomarker could capture the total burden of those substances in one measurement.

A score built on deep learning

Researchers have now developed the SASP Score, a biomarker based on a deep learning algorithm. The model analyzes protein patterns in the blood and combines them into a single number reflecting the combined effect of circulating SASP molecules. The researchers describe the approach on Lifespan.io, which refers to the underlying scientific publication.

The idea that one number can summarize the complex SASP mixture is methodologically notable. Existing biomarkers measure individual SASP proteins such as IL-6 or GDF15, but provide no overall picture. The SASP Score attempts to overcome that limitation by learning to recognize the pattern as a whole.

What it proves and what it does not

The tool is promising, but caveats apply. Whether the score predicts how quickly someone ages, or how well a treatment works, still needs to be shown in larger studies. An algorithm trained on specific datasets may perform less well outside those datasets. The researchers suggest the SASP Score could be used to measure the effect of senolytics, drugs that clear senescent cells. That remains a hypothesis for now.

From a longevity perspective, the potential is clear: if the cumulative damage from aging cells can be captured with a single blood test, it becomes far easier to intervene at the right moment and to measure whether an intervention is working. Whether this can be done reliably still needs to be confirmed by independent research.

Read the original article