Novel antibiotic for IBD validated with AI prediction

Novel antibiotic for IBD validated with AI prediction

HAMILTON, CANADA: In a landmark scientific breakthrough, researchers at McMaster University and the Massachusetts Institute of Technology (MIT) have discovered a new antibiotic for inflammatory bowel disease (IBD)—and, for the first time, successfully used artificial intelligence (AI) to predict how it works before scientists validated it in the lab.

The study, published in Nature Microbiology, introduces enterololin, a narrow-spectrum antibiotic that spares the gut microbiome while targeting harmful bacteria linked to Crohn’s disease and other IBD conditions. This dual achievement marks a global first in AI-guided drug discovery.

Why enterololin is different

Unlike most broad-spectrum antibiotics that wipe out both good and bad bacteria, enterololin selectively attacks a family of bacteria called Enterobacteriaceae, which includes E. coli. By sparing the healthy microbiome, the drug reduces opportunities for drug-resistant bacteria to colonize the gut.

“This new drug is a really promising treatment candidate for the millions of patients living with IBD,” said Jon Stokes, assistant professor at McMaster and lead investigator. “Developing something that might meaningfully alleviate symptoms could help people experience a much higher quality of life.”

AI prediction speeds up discovery

Traditionally, identifying a drug’s mechanism of action (MOA)—how it works against disease—takes years and millions of dollars. But in this study, AI completed the prediction in 100 seconds, later confirmed by laboratory testing.

Using DiffDock, an AI platform developed at MIT, researchers identified that enterololin targets a protein complex called LolCDE, essential for bacterial survival.

“AI can provide mechanistic explanations, which are critical for moving a molecule through the development pipeline,” said Regina Barzilay, MIT professor and AI model developer.

Validation experiments conducted by McMaster graduate student Denise Catacutan proved the AI’s prediction correct, shaving nearly two years off the typical research timeline.

From lab to patients

The discovery has already advanced toward clinical development. Stoked Bio, a spin-out company led by Jeff Skinner, has licensed enterololin from McMaster and is optimizing it for human use. The company is also testing variants against other dangerous pathogens, including Klebsiella.

If successful, human trials could begin within three years.

“Working on something translational like this is surreal,” Catacutan said. “The fact that something we discovered in the lab may someday help patients is truly amazing.”

The bigger picture: AI in drug discovery

This breakthrough highlights how AI can accelerate drug development, not only by identifying potential compounds but also by predicting their biological impact. While researchers stress that AI predictions must still be validated, this approach drastically reduces costs and timelines.

“AI is my wrench—it’s a tool for fixing the leak before it becomes a flood,” Stokes said. “My focus is on getting new drugs to the patients who need them, and AI is helping us get there faster.”

---

Stay informed and protect your health!

CLICK HERE TO JOIN Medical News Pakistan on WhatsApp for expert tips, health updates, and the latest medical research straight to your phone.