Antimicrobials, including antibiotics, antivirals, antifungals and antiparasitic, are medicines used to prevent and treat infections in humans, animals and plants. Resistance to these antimicrobials by microbes, referred to as Antimicrobial resistance (AMR) is a threat to global health. The World Health Organization (WHO) has declared that AMR is one of the top 10 global public health threats facing humanity.
Misuse and overuse of antimicrobials, as well as poor infection prevention and control, are the main drivers in the development of drug-resistant pathogens worldwide. Without effective antimicrobials, the success of modern medicine in treating infections, including during major surgery and cancer chemotherapy, would be at increased risk.
A growing list of infections, including pneumonia, tuberculosis, blood poisoning, gonorrhea, and foodborne diseases, are becoming harder, and sometimes impossible, to treat as antibiotics become less effective. Investment in research and development of new antibiotics, vaccines, diagnostics and other tools, has been slow in recent years due to patent restrictions, cumbersome approval measures and lengthy, expensive clinical trials before potential drugs can be marketed.
Artificial Intelligence (AI), which has in recent months received a bad rap from some in the scientific and technology community, besides being demonized by many in the media, is now being recognized as a potential protagonist in the fight against AMR. Researchers at
Massachusetts Institute of Technology in the United States, and at McMaster University in Canada, recently used AI algorithms to identify a new antibiotic that can kill a type of bacteria that is responsible for many drug-resistant infections.
If developed for use in patients, the drug could help to combat Acinetobacter baumannii, a species of bacteria that is often found in hospitals and can lead to pneumonia, meningitis, and other serious infections. The microbe is also a leading cause of infections among soldiers wounded in wars and conflict zones. The bacteria has been found to survive in hospital settings for long periods and can build antibiotic resistance genes from its environment.
The researchers identified the new drug from a library of nearly 7,000 potential drug compounds using a machine-learning model that they trained to evaluate whether a chemical compound will inhibit the growth of A. baumannii. The study further supports the premise that AI can significantly accelerate and expand our search for novel antibiotics that can help combat problematic pathogens Over the past several decades, many pathogenic bacteria have become increasingly resistant to existing antibiotics, while very few new antibiotics have been developed. Researchers behind the current finding set out to combat this growing problem by using machine learning, a type of artificial intelligence that can learn to recognize patterns in vast amounts of data. They hoped this approach could be used to identify new antibiotics whose chemical structures are different from any existing drugs.
In their initial demonstration, the researchers trained a machine-learning algorithm to identify chemical structures that could inhibit growth of the Escherichia coli (E.coli), a bacteria commonly found in the lower intestine of warm-blooded organisms.In a screen of more than 100 million compounds, that algorithm yielded a molecule that the researchers called halicin. This molecule could kill not only E. coli but several other bacterial species that are resistant to treatment.Once they proved that machine-learning approaches can work well for complex antibiotic discovery tasks, they turned their attention to Acinetobacter, what is considered to be public enemy No. 1 for multidrug-resistant bacterial infections.
To obtain training data for their computational model, the researchers first exposed A. baumannii grown in a lab dish to about 7,500 different chemical compounds to see which ones could inhibit growth of the microbe. Then they fed the structure of each molecule into the model. They also told the model whether each structure could inhibit bacterial growth or not. This allowed the algorithm to learn chemical features associated with growth inhibition.
Once the model was trained, the researchers used it to analyze a set of 6,680 compounds it had not seen before. This analysis, which took less than two hours, yielded a few hundred top hits. Of these, the researchers chose 240 to test experimentally in the lab, focusing on compounds with structures that were different from those of existing antibiotics or molecules from the training data.
Those tests yielded nine antibiotics, including one that was very potent. This compound, which was originally explored as a potential diabetes drug, turned out to be extremely effective at killing A. baumannii but had no effect on other species of bacteria. Researchers perceive ‘narrow spectrum’ killing ability as a desirable feature for antibiotics because it minimizes the risk of bacteria rapidly spreading resistance against the drug. Another advantage is that the drug would likely spare the beneficial bacteria that live in the human gut.
In their studies in mice, the researchers showed that the drug, which they named abaucin, could treat wound infections caused by A. baumannii. They also showed,in lab tests, that it works against a variety of drug-resistant A. baumannii strains isolated from human patients. The scientists are now working to optimize the medicinal properties of the compound, in hopes of developing it for eventual use in patients.
The researchers also plan to use their AI modeling approach to identify potential antibiotics for other types of drug-resistant infections, including those caused by Staphylococcus aureus, a bacteria responsible for many human diseases, and Pseudomonas aeruginosa, which causes infections in blood, lungs and other parts of the body following surgery.
