Researchers at MIT and McMaster University have identified a new antibiotic, named abaucin, using artificial intelligence. The drug is effective against Acinetobacter baumannii, a hospital-borne, drug-resistant bacteria. Abaucin’s narrow-spectrum efficacy and unique mechanism of disrupting lipoprotein trafficking within bacterial cells is significant. Patients infected with Acinetobacter baumannii face pneumonia, meningitis, and other serious infections. Soldiers wounded in Iraq and Afghanistan also suffer from its effects. The microbe can survive on hospital equipment and take up antibiotic resistance genes from its environment. Nearly every antibiotic-resistant infection is now linked to Acinetobacter baumannii. The researchers’ findings suggest that artificial intelligence can significantly accelerate and expand the search for novel antibiotics.
Over the past few decades, pathogenic bacteria have become increasingly resistant to existing antibiotics, but few new antibiotics have been developed. Researchers have used machine learning, a type of artificial intelligence, to identify new antibiotics whose chemical structures are different from any existing drugs. To identify chemical compounds that could inhibit the growth of A. baumannii, researchers exposed A. baumannii grown in a lab dish to 7,500 different chemical compounds. They then fed the structure of each molecule into a machine learning algorithm and told the model whether each structure could inhibit bacterial growth.
The researchers used their model to analyze a set of 6,680 compounds it had not seen before, which came from the Drug Repurposing Hub at the Broad Institute. This analysis 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. In tests, the researchers found 9 antibiotics, including abaucin, the most potent.
The drug, 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 including Pseudomonas aeruginosa, Staphylococcus aureus, and carbapenem-resistant Enterobacteriaceae. This “narrow spectrum” killing ability is desirable because it minimizes the risk of bacteria spreading resistance against the drug. Another advantage is that the drug would likely spare the beneficial bacteria that live in the human gut and help to suppress opportunistic infections.
In studies in mice, abaucin treated wound infections caused by A. baumannii. The researchers also showed, in lab tests, that it works against a variety of drug-resistant A. baumannii strains. Further experiments revealed that the drug kills cells by interfering with lipoprotein trafficking, a process that cells use to transport proteins from the interior of the cell to the cell envelope. Specifically, the drug appears to inhibit LolE, a protein involved in this process. All Gram-negative bacteria express this enzyme, so the researchers were surprised to find that abaucin is so selective in targeting A. baumannii. The researchers hypothesize that slight differences in how A. baumannii performs this task might account for the drug’s selectivity.
Stokes’ lab is now working with other researchers at McMaster 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 modeling approach to identify potential antibiotics for other types of drug-resistant infections, including those caused by Staphylococcus aureus and Pseudomonas aeruginosa. The research was funded by various organizations, including the David Braley Center for Antibiotic Discovery, the Weston Family Foundation, the Audacious Project, and the Canadian Institutes of Health Research.
