2023-05-14 13:49:30
Researchers at biotech company Integrated Biosciences opened new senolytic classes of small molecules using artificial intelligence. The AI selected three drug candidates from a huge number of other senoliptic drug options. In experiments on mice, one of these compounds has already been proven to destroy senescent cells and reduce the expression of genes associated with aging. The results may be promising in the creation of drugs that will slow down the aging process and prevent the development of dangerous diseases.
The paper, written in collaboration with researchers at MIT and Harvard, describes AI-assisted screening of more than 800,000 compounds to identify the top three drug candidates.
Senolytics are a class of small molecules that can remove senescent cells from the body, thus reducing inflammation and slowing down the aging process. Despite promising clinical results, most of the senolytic compounds identified to date are hampered by low bioavailability and adverse side effects.
Integrated Biosciences 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 nearly 1 million molecular variants. All three showed chemical properties indicative of high oral bioavailability. They have been found to have favorable toxicity profiles in hemolysis and genotoxicity tests.
Structural and biochemical analyzes show that all three compounds bind to Bcl-2, a protein that regulates apoptosis and is also a target for chemotherapy. Experiments testing one of the compounds in 80-week-old mice (corresponding to an 80-year-old human age) showed that it destroyed senescent cells and reduced the expression of aging-related genes in the kidneys.
The result of this study is an important milestone for both longevity research and the application of artificial intelligence to drug development.
1684245031
#finds #effective #antiaging #drug #candidates