MIT researchers Regina Barzilay and James Collins are the 2026 recipients of the Pritzker Prize for AI in Science Research Excellence. The prize recognizes their joint work in AI-enabled antibiotic discovery, combining deep learning, bioengineering and experimental validation to identify new candidates against drug-resistant pathogens.
Barzilay is MIT's School of Engineering Distinguished Professor of AI and Health, and Collins is the Termeer Professor of Medical Engineering and Science. The two are faculty co-leads of the Abdul Latif Jameel Clinic for Machine Learning in Health (Jameel Clinic). Established in 2024 by the University of Chicago in partnership with Caltech, the prize carries $50,000 per award. It was the first time in the prize's history that a team was honored.
From halicin to abaucin
Their best-known breakthrough came in 2020, in a paper in Cell with Jonathan Stokes as first author: halicin, described as the first AI-discovered antibiotic. Named for the HAL 9000 system in 2001: A Space Odyssey, the molecule had originally been studied as a possible diabetes drug. A deep learning model trained on 2,500 molecules flagged it, and tests showed it killed resistant bacteria such as Clostridium difficile, Acinetobacter baumannii and Mycobacterium tuberculosis. A process that would have taken years was completed in a few weeks.
In 2023, the team used machine learning again to identify abaucin, a narrow-spectrum antibiotic effective against A. baumannii. Its precision is the point: by targeting a single species, abaucin lowers the chance of harming beneficial gut bacteria and driving resistance.
A project against seven deadly pathogens
Their current Antibiotics-AI Project, in partnership with the nonprofit Phare Bio, aims to develop seven new classes of antibiotics targeting seven of the world's deadliest bacterial pathogens. The University of Chicago cites a projection that antimicrobial resistance could cause 10 million deaths a year by 2050.
"Historically, antibiotic discovery has depended on laborious, trial-and-error strategies," Collins said. "With generative AI, we're now seeing a shift from AI being used as a tool for discovery to AI being used as a design tool." Barzilay cautioned that the field is still early: "With AI, we can only automate parts of the pipeline, rather than totally transforming the discovery process."
One clarification: alongside the MIT team, the University of Chicago also honored Kristin Persson of the University of California, Berkeley, for pioneering data-driven materials design and founding the Materials Project. Barzilay and Collins were therefore not the year's only recipients — they were its first winning team.
Image credit: official prize graphic released by the University of Chicago Data Science Institute.
Sources: MIT News and University of Chicago Data Science Institute.
Transparency: this article was produced with the assistance of artificial intelligence, cross-checked against public sources on the internet. Consult the original sources to confirm the details.
Muse
