As the use of the most advanced technology available advances, more scientific discoveries are made. And if we talk about the use of Artificial Intelligence (AI) applied to medicinethe news also brings more hope to patients.
As happened yesterday, when a new study scientific study in which researchers from McMaster University in Ontario, Canada and the Massachusetts Institute of Technology (MIT) have discovered a new antibiotic thanks to the use of AI, which can be used to kill a deadly hospital superbug.
The scientists employed the use of AI to discover the abaucin, a drug effective against Acinetobacter baumannii, a bacterium that can cause dangerous infections in the human body, that the World Health Organization (WHO) has classified as a “critical” threat among its “priority pathogens”, a group of families of bacteria that represent the “greatest threat” to human health.
According to the WHO, bacteria have built-in abilities to find new ways to resist treatment and may pass on genetic material which allows other bacteria to become resistant to drugs as well. And especially a bacterium baumannii it poses a threat to hospitals, nursing homes and patients requiring ventilators and blood catheters, as well as those with open wounds from surgeries.
The bacteria can live for extended periods on shared environmental services and equipment, and can often be spread through contaminated hands. In addition to blood infections, to baumannii can cause urinary tract and lung infections.
According to the Centers for Disease Control and Prevention, the bacteria can also “colonize” or live in a patient without causing infection or symptoms. Thursday’s study revealed that researchers used an AI algorithm to examine thousands of antibacterial molecules in an attempt to predict new structural classes. As a result of the AI detection, the researchers were able to identify a new antibacterial compound which they called abaucin.
“We had a lot of data that just told us which chemicals could kill a bunch of bacteria and which ones couldn’t. My job was to train this model, and all this model was going to do was essentially tell us if the new molecules would have antibacterial properties or not”, explained Gary Liu, a MacMaster University graduate student who worked on the research. “So basically, through that, we can just increase the efficiency of the drug discovery pipeline and… refine all the molecules that we really care about,” he added.
After the scientists trained the AI model, they used it to analyze 6,680 compounds and molecules that it hadn’t encountered before. They fed into the AI information from thousands of drugs for which the precise chemical structure was known and which they had manually tested on Acinetobacter baumannii, to identify which could slow down or kill the superbug. The AI thus learned the chemical characteristics of the drugs that could attack the bacteria.
The analysis took an hour and a half and ended up yielding several hundred other compounds, 240 of which were later tested in a laboratory, ultimately revealing 9 potentially successful antibiotics, including abaucin. Then the scientists tested the new molecule against to baumannii in a mouse model of wound infection and found that the molecule suppressed the infection.
“This work validates the benefits of machine learning in the search for new antibiotics. Using AI, we can rapidly explore vast regions of chemical space, significantly increasing the chances of discovering fundamentally new antibacterial molecules.” said Jonathan Stokes, an assistant professor in McMaster University’s department of biomedicine and biochemistry who helped lead the study.
“We know that broad-spectrum antibiotics are suboptimal and that pathogens have the ability to evolve and adapt to every trick we throw at them. AI methods give us the opportunity to vastly increase the rate at which we discover new antibiotics, and we can do it. at a reduced cost. This is an important avenue of exploration for new antibiotics,” she added.
The scientist warned that for the first antibiotics discovered with the help of AI may be prescribed, perhaps we will have to wait until 2030. Interestingly, this experimental antibiotic had no effect on other species of bacteria and only works on A. baumannii.
This does not usually happen. Typically, many antibiotics block and kill pathogens indiscriminately. Including beneficial bacteria that live in the gut or on the skin. Thus, the researchers believe that the precision of abaucin will make it difficult for drug resistance to emerge by having a very specific target. If there were more antibiotics that worked with this precision, the researchers say, “it could prevent bacteria from becoming resistant”. They would also cause fewer side effects.
It should be noted that resistance to antibiotics has become one of the main causes of death in the world. Along these lines, a study published in The Lancet highlights horrifying facts, such as that antimicrobial resistance was the direct cause of at least 1.27 million deaths worldwide in 2019.
In addition, the UN anticipates that if we do not solve this problem, the number of deaths caused by superbugs could increase to 10 million in 2050. That is why a large number of research teams are working to find a remedy against this threat. In this case, through new technologies such as AI applied to science.
Dr. Jonathan Stokes, a researcher at McMaster University in Canada and co-author of the study, described this superbug as the “public enemy number one”, since it is “really common” to find cases in which it is “resistant to almost all antibiotics”. And he claimed that AI has “the power to greatly accelerate the discovery of new drugs.”