Finding new drugs is an expensive and time-consuming task. But a type of artificial intelligence called machine learning can greatly speed up the process and get the job done at a relatively low cost. Recently, scientists have used this technology to find three promising candidates for senolytic drugs – drugs that slow aging and prevent age-related diseases.

Cenolytics kill senescent cells. These cells are “alive” (metabolically active), but they can no longer reproduce (reproduce). That’s why they’re often called zombie cells.

These cells have damage to their DNA, like skin cells damaged by sunlight, so stopping their replication stops the damage from spreading.

Aging cells is not always a good thing. They secrete a cocktail of inflammatory proteins that can spread to neighboring cells. Throughout our lives, our cells are exposed to a series of attacks, from UV rays to exposure to chemicals, and these cells accumulate.

Increasing numbers of senescent cells have been associated with a number of diseases, including type 2 diabetes, COVID, pulmonary fibrosis, osteoarthritis and cancer. Studies in laboratory mice have shown that eliminating senescent cells using senolytics can alleviate these diseases. These drugs can kill zombie cells while keeping healthy cells alive.

About 80 senolytics are known, but only two have been tested in humans: the combination of dasatinib and quercetin. It would be great to find more senolytics that can be used for a variety of diseases, but it takes tens to 20 years and billions of dollars to get a drug to market. So the scientists decided to turn to artificial intelligence for the myth.

To run this study, they popped the AI ​​models with samples of known senolites and non-senolites. The models learned to distinguish them and could then be used to predict whether molecules they had never seen before would also be senolytic. Using artificial intelligence, the scientists identified 21 molecules with potential senolytic properties.

“Had we tested the original 4,340 molecules in the lab, it would have taken at least a few weeks of hard work and £50,000 to purchase the compounds, regardless of the cost of experimental equipment and setup.”said one of the scientists.

The scientists then tested these candidate drugs on two types of cells: healthy and aging. The results showed that three of the 21 compounds (periplocin, oleandrin and ginkgetin) were able to destroy senescent cells while preserving most normal cells. These new senolytics were then tested to learn more about how they work in the body. More detailed biological experiments oleander proven to be more effective than the known effective senolytic drug of its kind.

The potential implications of this interdisciplinary approach involving data scientists, chemists and biologists are enormous. Given enough high-quality data, AI models can accelerate the wonderful work chemists and biologists have been doing for years. This will help find faster treatment and cure for diseases that claim hundreds of thousands of lives each year.