The use of Artificial Intelligence (AI) is already revolutionizing the search for new medicines, such as antibiotics that fight superbugs. This is what a team of scientists points out in a new study, published in the journal Nature Chemical Biology. The strategy allowed the identification of a new compound, abaucin, which should destroy one of the most dangerous bacteria for humans.
Very promising, the research that uses AI to identify possible antibiotics is led by researchers from McMaster University, in Canada, and the Massachusetts Institute of Technology (MIT), in the United States. Today, the drug has yet to be tested extensively in animals and, later, in humans.
Antibiotic against one of the most dangerous bacteria
In the development phase, scientists believe they have discovered an antibiotic against the bacteria Acinetobacter baumanniiconsidered one of the most dangerous superbugs in the world by a survey by the World Health Organization (WHO).
The risk of the bacterium is so great that it has been included in the list of “priority pathogens” by the WHO, which should guide pharmacists and scientists in their search for new drugs. The list is divided into three levels, according to the degree of danger: critical, high and medium scale.
In the understanding of the organization, the A. baumannii configures on the critical scale, alongside two other bacteria resistant to traditional medicines, the Pseudomonas aeruginosa and those of the Enterobacteriaceae family. All resist the potent Carbapenem class of antibiotics. In general, there is a lack of medicines to deal with the growing problem of antimicrobial resistance, which can have implications for global health.
Who is most at risk from the superbug?
The great risk involving the bacteria A. baumannii it’s because it survives on surfaces for long periods of time, which makes it a problem for hospitals, nursing homes, and patients using medical devices (such as a mechanical ventilator). In those infected, it can cause pneumonia, meningitis and even death.
AI revolutionizes drug testing
To discover new ways of controlling the superbug, the American and Canadian scientists worked on an AI algorithm, capable of designing unprecedented structures of antibacterial molecules and estimating which ones might be promising. It was in this process that they discovered the potential medicine abaucine. If they depended on traditional models, the process would take years and cost much more.
“AI approaches to drug discovery are here to stay and will continue to be refined,” said James J. Collins, professor of medical engineering and science at MIT, in a statement. “We know algorithmic models work, now it’s a matter of widely adopting these methods to discover new antibiotics more efficiently and cost-effectively,” he adds.
As for the antibiotic already found, the specialist explains that it proved to be effective in the first round of tests in vitro (in the lab). The next steps involve tests on animal models and, one day, on humans.
Source: OMS, Nature Chemical Biology e McMaster University
