Researchers at McMaster University and MIT have discovered a new antibiotic, enterololin, that targets inflammatory bowel diseases. By using AI to predict its effectiveness, they significantly accelerated the drug development process, offering hope to millions affected by Crohn’s disease.
In a groundbreaking development, researchers at McMaster University and the Massachusetts Institute of Technology have unveiled a novel antibiotic, enterololin, that targets inflammatory bowel diseases (IBD), including Crohn’s disease. Even more astonishing, they utilized a machine learning model to predict how the drug works, a pioneering achievement in the realm of artificial intelligence and medicine.
Published today in the journal Nature Microbiology, the study marks a significant leap forward in both IBD treatment and drug discovery methodology.
The new antibiotic promises to revolutionize therapeutic options for millions suffering from IBD-related conditions worldwide.
“This work shows that we’re still just scratching the surface as far as AI-guided drug discovery goes,” principal investigator Jon Stokes, an assistant professor in McMaster’s Department of Biochemistry and Biomedical Sciences, said in a news release. “The development of our new drug, which is designed to target IBD, has been fast-tracked thanks to the collaboration between humans and generative AI.”
Precision Treatment for IBD
Contrary to most broad-spectrum antibiotics that indiscriminately kill both harmful and beneficial bacteria, enterololin acts with surgical precision.
It targets Enterobacteriaceae, a family that includes E. coli, thus avoiding collateral damage to the beneficial microbiome.
This reduces the likelihood of drug-resistant bacteria colonizing the gut, a common complication with current treatments.
“This new drug is a really promising treatment candidate for the millions of patients living with IBD,” added Stokes. “We currently have no cure for these conditions, so developing something that might meaningfully alleviate symptoms could help people experience a much higher quality of life.”
AI’s Role in Fast-Tracking Drug Discovery
Traditionally, understanding a drug’s mechanism of action (MOA) can take years and millions of dollars. This study, however, leveraged an AI model developed by MIT to predict enterololin’s MOA in just 100 seconds.
The subsequent validation with laboratory experiments took only six months and $60,000, as opposed to the estimated two years and $2 million that conventional methods would require.
“AI has expedited the rate at which we can explore chemical space for new drug candidates, but, until now, it has done little to alleviate a major bottleneck in drug development, which is understanding what these new drug candidates actually do,” Stokes added.
“What we’re showing here is that AI can also provide mechanistic explanations, which are critical for moving a molecule through the development pipeline,” added Regina Barzilay, a professor in MIT’s School of Engineering who developed the AI model DiffDock, which made the prediction.
Future Prospects
The team’s next steps include optimizing enterololin for human use through Stokes’ spin-out company, Stoked Bio.
Early trials show promise against other drug-resistant bacteria, like Klebsiella, with human trials anticipated to start within three years.
Source: McMaster University