Artificial intelligence has found drugs that can fight aging

Artificial intelligence has found drugs that can fight aging


Finding new drugs or drug discovery is expensive and time-consuming. But a type of artificial intelligence called machine learning can speed up this process and do it at a very low cost.

A group of researchers from the University of Edinburgh recently used machine learning to find senolytic drugs. Senolytics are drugs that slow down the aging process and prevent age-related diseases.

Senolytic drugs work by destroying senescent cells. Senescent cells are metabolically active but cannot reproduce and are therefore known as “zombie cells”.

The inability to reproduce is not necessarily a bad thing. The DNA of these cells has been damaged (for example, skin cells that have been damaged by sunlight), so stopping replication prevents the damage from spreading.

Aging cells are not always a good thing. They secrete a combination of inflammatory proteins that can reach nearby cells.

Throughout our lives, our cells are attacked by various things from ultraviolet rays to chemicals, and old cells accumulate in our bodies. The increase in the number of senescent cells is involved in a wide range of diseases, including type 2 diabetes, covid, lung fibrosis, osteoarthritis and cancer.

Studies conducted on laboratory mice have shown that removing senescent cells using senolytics can improve the mentioned diseases. These drugs can kill zombie cells, but they have nothing to do with healthy cells.

About 80 senolytics are known, but only two of them have been tested in humans: the combination of dasatinib and quercetin. Finding more senolytics that can be used to treat various diseases is great, but it takes ten to twenty years and billions of dollars to bring a drug to market.

Results in five minutes

Researchers from the University of Edinburgh and Spain’s IBBTEC-CSIC research center wanted to know if they could train machine learning models to identify new senolytics. They included examples of senolytic drugs and non-senolytic drugs into the model. The models learned to distinguish between the two types of drugs and could therefore be used to predict whether previously unseen molecules were senolytics.


Source link


No comments yet. Why don’t you start the discussion?

Leave a Reply

Your email address will not be published. Required fields are marked *