Senescent cells are a hallmark of aging. They have also been implicated in a broad spectrum of age-related diseases and conditions including cancer, diabetes, cardiovascular disease, and Alzheimer’s disease. Senolytics are compounds that selectively induce apoptosis, or programmed cell death, in senescent cells. Despite their potential promise, most senolytic compounds identified to date have been hampered by poor bioavailability and adverse side effects.
Now, a new study describes how an AI-driven platform, built on work pioneered in the lab of Jim Collins, PhD, at MIT and the Wyss Institute, identified candidates with comparable efficacy and improved medicinal chemistry relative to a current, known senolytic compound (ABT-737.) The AI-guided method screened 2,352 compounds for senolytic activity—in a model of etoposide-induced senescence—and trained graph neural networks to predict the senolytic activities of more than 800,000 molecules to reveal the three drug candidates. In addition, treatment of aged mice reduced the number of senescent cells and lowered expression of senescence-associated genes. The results, the authors noted, “underscore the promise of leveraging deep learning to discover senotherapeutics.”
The findings are published in Nature Aging, in the article, “Discovering small-molecule senolytics with deep neural networks.”
“This research result is a significant milestone for both longevity research and the application of artificial intelligence to drug discovery,” said Felix Wong, PhD, co-founder of Integrated Biosciences. “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.”
Integrated Biosciences was founded in 2022 by Wong and Max Wilson, PhD, to target age-related cellular stress responses, other neglected hallmarks of aging, and advance anti-aging drug development, using synthetic biology and AI platforms. The seed-stage company is based in San Carlos, CA.
In their new study, researchers trained deep neural networks on experimentally generated data to predict the senolytic activity of any molecule. Using this AI model, they discovered three highly selective and potent senolytic compounds from a chemical space of over 800,000 molecules. All three displayed chemical properties suggestive of high oral bioavailability and were found to have favorable toxicity profiles in hemolysis and genotoxicity tests. Structural and biochemical analyses indicate that all three compounds bind Bcl-2, a protein that regulates apoptosis and is also a chemotherapy target. Experiments testing one of the compounds in 80-week-old mice, roughly corresponding to 80-year-old humans, found that it cleared senescent cells and reduced expression of senescence-associated genes in the kidneys.
“One of the most promising routes to treat age-related diseases is to identify therapeutic interventions that selectively remove these cells from the body similarly to how antibiotics kill bacteria without harming host cells. The compounds we discovered display high selectivity, as well as the favorable medicinal chemistry properties needed to yield a successful drug,” said Satotaka Omori, PhD, head of aging biology at Integrated Biosciences. “We believe that the compounds discovered using our platform will have improved prospects in clinical trials and will eventually help restore health to aging individuals.”
