Artificial intelligence helps create antibiotic – 05/26/2023 – Science
Scientists have used artificial intelligence (AI) to develop a new antibiotic capable of killing a deadly species of superbug.
Technology helped sift through a list of thousands of potential chemical compounds, narrowing them down to just a few that could be tested in the lab.
The result was a potent experimental antibiotic called abaucin, which will need to undergo further testing before it can be used.
The researchers, from Canada and the US, say AI has the power to dramatically accelerate new drug discovery.
To stop the superbugs
Antibiotics kill bacteria. But there has been a shortage of new drugs for decades — and the bacteria are becoming more difficult to treat as they develop resistance to the antibiotics we have available.
It is estimated that more than one million people die each year from infections resistant to antibiotic treatment.
The researchers focused on one of the most troublesome species of bacteria — Acinetobacter baumannii, which can infect wounds and cause pneumonia.
You may not have heard of it, but it’s one of three superbugs that the World Health Organization (WHO) has identified as a “critical” threat.
It is often able to bypass multiple antibiotics — and is a problem in hospitals and nursing homes, where it can survive on surfaces and medical equipment.
Jonathan Stokes, from McMaster University in Canada, describes the bacterium as “public enemy number one”, since it is “very common” to find cases where it is “resistant to almost all antibiotics”.
To find a new antibiotic, researchers first had to train artificial intelligence.
They took thousands of drugs where the exact chemical structure was known, and manually tested them on Acinetobacter baumannii to see which ones could slow down or kill it.
That information was fed to the artificial intelligence so that it could learn the chemical characteristics of drugs that could attack the troublesome bacteria.
Artificial intelligence then analyzed a list of 6,680 compounds whose effectiveness was unknown. The results — published in the scientific journal Nature Chemical Biology — showed that the technology took an hour and a half to produce a list of finalists.
The researchers tested 240 in the lab and found nine potential antibiotics. One of these was the incredibly potent abaucine.
Laboratory experiments showed that this antibiotic could treat infected wounds in mice — and was able to kill samples of A. baumannii from patients.
“This is where the work begins,” says Stokes.
The next step is to perfect the drug in the laboratory and then carry out clinical trials. He expects the first AI-generated antibiotics to be available for prescription by 2030.
Interestingly, this experimental antibiotic had no effect on other bacterial species, working only against A. baumannii.
Many antibiotics kill bacteria indiscriminately. The researchers believe that abaucin’s precision will make it harder for drug resistance to emerge — and may lead to fewer side effects.
In principle, artificial intelligence could analyze tens of millions of potential chemical compounds — something that would be impractical to do manually.
“Artificial intelligence increases the rate and, in a perfect world, decreases the cost at which we can discover these new classes of antibiotics that we desperately need,” says Stokes.
The researchers tested the principles of artificial intelligence to aid in the discovery of antibiotics with the E coli in 2020, but are using that knowledge now to focus on the big threats. They plan to study Staphylococcus aureus and the Pseudomonas aeruginosa Next.
“This discovery further supports the premise that artificial intelligence can significantly accelerate and expand our search for new antibiotics,” says James Collins, a professor at the Massachusetts Institute of Technology (MIT, its acronym in English), in the USA.
“I’m excited, this work shows that we can use artificial intelligence to help fight troublesome pathogens such as A. baumannii.”
Dame Sally Davies, former England health chief and government advocate against antimicrobial resistance, told BBC Radio 4’s The World Tonight:
“We are one step away from winning.”
In her opinion, the idea of using artificial intelligence was “a big game changer”.
“I’m really happy to see the work he (Stokes) is doing, it’s going to save lives.”
This text was originally published here.