One of the most exciting areas of research on slowing down — or even reversing — aging, is the field of senolytics. Senolytics are molecules that can suppress age-related processes at the cellular level, by targeting “senescent” cells, or so-called “zombie” cells that are a sign of aging. These cells stop multiplying but don’t die off when they should, and emit harmful chemicals that can trigger inflammation and, in turn, lead to a number of age-related diseases including cardiovascular disease, diabetes, Alzheimer’s and others.
Senolytics are intended to target these “zombie” cells and, in effect, program them to die off naturally. Scientists have identified some natural substances that apparently have senolytic capability (quercetin, fisetin, piperlongumine and the curcumin analog) and there is active research into the development of new compounds.
Now, as reported here, AI playing a role.
Researchers from biotech company Integrated Biosciences, working with scientists from MIT and Harvard, used AI to screen more than 800,000 compounds, leading to the identification of three new drug candidates. These candidates “when compared with senolytics currently under investigation, were found to have comparable efficacy and superior medicinal chemistry properties.”
From the article: “The researchers used deep neural networks to predict the senolytic activity of any molecule, using experimentally generated data. The AI model discovered three highly selective and potent senolytic compounds from a chemical space of over 800,000 molecules; all three compounds had chemical properties suggestive of high oral bioavailability and were found to have favorable toxicity profiles in hemolysis and genotoxicity tests… In experiments testing one of the compounds in 80-week-old mice, roughly corresponding to 80-year-old humans, it cleared senescent cells and reduced expression of senescence-associated genes in the kidneys.”
The money quote, from Felix Wong, co-founder of the company: “This research result is a significant milestone for both longevity research and the application of artificial intelligence to drug discovery. These data demonstrate that we can explore chemical space in silico and emerge with multiple candidate anti-aging compounds that are more likely to succeed in the clinic, compared to even the most promising examples of their kind being studied today.”
It’s exciting to see that scientists are beginning to leverage the astonishing capacity of AI to analyze massive amounts of data to arrive at potential solutions much more quickly and comprehensively than anything we could have imagined in the past. Obviously these solutions would need further testing before being able to be brought to the market, but anything that can accelerate the process — especially since it also improves the qualitative breadth and depth of the analysis — is definitely a game-changer. We’ll certainly be reporting on this often.