MIT Team Receives Up to $53 Million for AI Herbicide Research

Massachusetts Institute of Technology (MIT) will lead a research project receiving up to $53 million from the U.S. Advanced Research Projects Agency for Health, according to MIT News. The team will develop generative AI tools to identify herbicide alternatives designed to limit risks to people and the environment.

The models will generate chemical compounds and small interfering RNA candidates that target plant enzymes affected by existing herbicides. Researchers will also optimize candidates for synthesis cost, resistance risk, and potential harm, while seeking to reduce reliance on imported phosphorus used in glyphosate production.

The project will generate billions of candidates, test them through screening, and use the results to improve the models. Selected candidates will then enter greenhouse studies, with initial RNA interference tests expected by the end of the program's first year. The researchers will also develop engineered bacteria, fungi, and RNA systems that break down agricultural chemicals before they reach food, soil, or waterways.