Using an artificial intelligence algorithm, researchers at MIT and McMaster University have identified 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 fight Acinetobacter baumannii, a species of bacteria that is often found in hospitals and can cause pneumonia, meningitis, and other serious infections. The microbe is also a leading cause of infections in wounded soldiers in Iraq and Afghanistan.
“Acinetobacter it can survive on hospital doorknobs and equipment for long periods of time, and it can acquire antibiotic resistance genes from its environment. Now it is very common to find A. baumannii isolates that are resistant to almost all antibiotics,” says Jonathan Stokes, a former MIT postdoc who is now an assistant professor of biochemistry and biomedical sciences at McMaster University.
The researchers identified the new drug from a library of nearly 7,000 potential drug compounds using a machine learning model they trained to assess whether a chemical compound will inhibit the growth of A. baumannii.
“This finding further supports the premise that AI can significantly accelerate and expand our search for new antibiotics,” says James Collins, Termeer Professor of Engineering and Medical Sciences at the Institute of Medical Engineering and Sciences (IMES) and the Department of Biological Engineering from MIT. “I am excited that this work shows that we can use AI to help combat problematic pathogens such as A. baumannii.”
Collins and Stokes are the lead authors of the new study, which appears today in nature chemistry biology. The paper’s lead authors are McMaster University graduate students Gary Liu and Denise Catacutan, and recent McMaster graduate Khushi Rathod.
drug discovery
During the last decades, many pathogenic bacteria have become increasingly resistant to existing antibiotics, while very few new antibiotics have been developed.
Several years ago, Collins, Stokes, and MIT professor Regina Barzilay (who is also an author on the new study), set out to combat this growing problem by using machine learning, a type of artificial intelligence that can learn to recognize patterns in a large amounts of data. Collins and Barzilay, who co-direct MIT’s Abdul Latif Jameel Clinic for Machine Learning in Health, hoped that 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 the growth of E.coli. In a screen of more than 100 million compounds, that algorithm produced a molecule the researchers named halicin, after the fictional artificial intelligence system from “2001: A Space Odyssey.” This molecule, they showed, could kill not only E.coli but several other bacterial species that are resistant to treatment.
“After that paper, when we show that these machine learning approaches can work well for complex antibiotic discovery tasks, we turn our attention to what I perceive to be public enemy number 1 for multidrug-resistant bacterial infections, which is Acinetobactersays Stokes.
To obtain training data for their computational model, the researchers first exposed A. baumannii grown in a laboratory dish to about 7,500 different chemical compounds to see which ones might inhibit the growth of the microbe. They then entered the structure of each molecule into the model. They also told the model whether or not each structure could inhibit bacterial growth. 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 previously unseen compounds that came from the Broad Institute’s Center for Drug Reuse. This analysis, which took less than two hours, returned a few hundred top results. Of these, the researchers chose 240 for experimental testing in the lab, focusing on compounds with different structures than existing antibiotics or molecules from the training data.
Those tests turned up 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, including Pseudomonas aeruginosa, staphylococcus aureusand resistant to carbapenems enterobacteria.
This “narrow spectrum” killing ability is a desirable characteristic for antibiotics because it minimizes the risk of bacteria rapidly spreading resistance against the drug. Another advantage is that the drug would likely prevent beneficial bacteria that live in the human gut and help suppress opportunistic infections such as Clostridium difficile.
“Antibiotics often need to be given systemically, and the last thing you want to do is cause significant dysbiosis and expose these already sick patients to secondary infections,” says Stokes.
A novel mechanism
In studies in mice, the researchers showed that the drug, which they called abaucin, could treat wound infections caused by A. baumannii. They have also shown, in laboratory tests, that it works against a variety of resistant drugs. A. baumannii strains isolated from human patients.
Other experiments revealed that the drug kills cells by interfering with a process known as lipoprotein trafficking, which cells use to transport proteins from inside 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 attacking A. baumannii. They hypothesize that slight differences in how A. baumannii performs this task could explain the selectivity of the drug.
“We have not yet finished the acquisition of experimental data, but we believe that it is because A. baumannii it does lipoprotein trafficking a bit differently than other Gram-negative species. We think that’s why we have this narrow spectrum activity,” says Stokes.
Stokes’ lab is now working with other researchers at McMaster to optimize the compound’s medicinal properties, with the hope 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 the David Braley Center for Antibiotic Discovery, the Weston Family Foundation, the Audacious Project, the C3.ai Digital Transformation Institute, the Abdul Latif Jameel Clinic for Machine Learning in Health, the DTRA Discovery for Medical Countermeasures against New and Emerging Threats, the DARPA Accelerated Molecular Discovery program, the Canadian Institutes for Health Research, Genome Canada, the McMaster University School of Health Sciences, the Boris Family, a Marshall Fellowship, and the Environmental and Biological Investigation of the Department of Energy.
