Finding new drugs called “drug discovery” is an expensive and time consuming business. But a type of AI called machine learning can speed up the process tremendously and get the job done at a fraction of the price.
My colleagues and I recently used this technology to find three promising candidates for senolytic drugs that slow aging and prevent age-related diseases.
Senolytics work by killing senescent cells. These are “live” (metabolically active) cells, but which can no longer replicate, hence their nickname: zombie cells.
The inability to reply is not necessarily a bad thing. These cells have had their DNA damaged, for example, skin cells damaged by the sun’s rays, so stopping replication prevents the damage from spreading.
But senescent cells aren’t always a good thing. They secrete a cocktail of inflammatory proteins that can spread to nearby cells. Over the course of a lifetime, our cells experience a barrage of assaults, from UV rays to exposure to chemicals, and so these cells build up.
High numbers of senescent cells have been implicated in a number of diseases, including type 2 diabetes, COVID, pulmonary fibrosis, osteoarthritis and cancer.
Studies on laboratory mice have shown that the elimination of senescent cells, using senolytics, can improve 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: a combination of dasatinib and quercetin. It would be nice to find more senolytics that can be used in a variety of diseases, but it takes ten to 20 years and billions of dollars for a drug to hit the market.
Results in five minutes
My colleagues and I, including researchers from the University of Edinburgh and the Spanish National Research Council IBBTEC-CSIC in Santander, Spain, wanted to know if we could train machine learning models to identify new candidate senolytic drugs.
To do this, we fed the AI models with examples of known and non-senolithic sinolytics. The models learned to distinguish between the two and could be used to predict whether even molecules they had never seen before might be senolytics.
When solving a machine learning problem, we usually first test the data on a range of different models as some of them tend to perform better than others.
To determine the best performing model, early in the process, we separate a small section of the available training data and keep it hidden from the model until the training process is complete.
We then use this test data to quantify how many errors the model is making. Whoever makes the fewest mistakes wins.
We determined our best model and set it up to make predictions. We gave him 4,340 molecules and five minutes later he gave us a list of results.
The AI model identified 21 highest-scoring molecules that it judged to have a high probability of being senolytics. If we had tested the original 4,340 molecules in the laboratory, it would have taken at least a few weeks of intense work and 50,000 just to buy the compounds, not counting the cost of the experimental machinery and setup.
We then tested these drug candidates on two types of cells: healthy and senescent. The results showed that of the 21 compounds, three (periplocin, oleandrin and ginkgetin) were able to eliminate senescent cells while keeping most of the normal cells alive. These new senolytics then underwent further testing to learn more about how they work in the body.
More detailed biological experiments showed that, of the three drugs, oleandrin was more effective than the best-performing known senolytic drug of its kind.
The potential repercussions of this interdisciplinary approach involving data scientists, chemists and biologists are enormous. With enough high-quality data, AI models can accelerate the tremendous work chemists and biologists are doing to find treatments and cures for diseases, especially those with unmet needs.
Having validated them in senescent cells, we are now testing the three candidate senolytics in human lung tissue. We hope to report our next results in two years.
Vanessa Smer-Barreto, Research Fellow, Institute of Genetics and Molecular Medicine, University of Edinburgh
This article is republished from The Conversation under a Creative Commons license. Read the original article.
#Artificial #intelligence #powerful #antiaging #molecule
Image Source : www.sciencealert.com