MIT researchers will lead a federally funded effort worth up to $53 million to develop a new generation of herbicides that are safer for humans and the environment, according to an announcement from the university. The project, awarded by the U.S. Advanced Research Projects Agency for Health (ARPA-H) under its STREAM program, aims to address growing herbicide resistance in weeds and concerns about the health effects of existing chemicals.

More than 1 billion pounds of herbicide are used annually in the United States, MIT News reported. While these chemicals help farmers prevent significant crop loss and support soil-protecting regenerative farming practices, some weeds have developed resistance to the most common herbicides. Exposure to herbicides has been linked to increased risks of cancer, metabolic and endocrine disorders, and other adverse health outcomes. Farm workers face the highest exposure from frequent use, but many Americans are also exposed to small amounts through food and drinking water.

The project, called Precision Learning for On-target Weed control (PLOW), will be led by Christopher Voigt, head of MIT’s Department of Biological Engineering. The research team includes scientists from the Broad Institute of MIT and Harvard, the University of North Carolina at Chapel Hill, the University of Tennessee at Knoxville, the University of Illinois at Urbana-Champaign, and the biotechnology company Robigo.

“With herbicides like glyphosate and atrazine, there’s a real crisis because of resistance mutations that are coming,” Voigt said in the announcement. “And if you combine the resistance mutations with issues around national security of the supply chain of the precursors to herbicides, we could find ourselves without these core agrochemicals that are absolutely essential for getting the high crop yields and economical prices that the United States now sees.”

Glyphosate, one of the most widely used herbicides, kills weeds by interfering with an enzyme called EPSP synthase, which plants need to produce certain amino acids. After years of use, some weeds have acquired genetic mutations that make them resistant to glyphosate and similar chemicals, threatening crop yields.

The MIT-led team plans to develop generative AI models that can predict molecules — either chemical compounds or small interfering RNA (siRNA) — that disrupt the same plant enzymes targeted by glyphosate and other herbicides. The AI development effort is headed by MIT's Warren K. Lewis Associate Professor of Chemical Engineering Connor Coley, MIT's School of Engineering Distinguished Professor for AI and Health Regina Barzilay, and Alexander Tropsha, who holds the K.H. Lee Distinguished Professorship at the UNC Eshelman School of Pharmacy. These models are projected to produce billions of candidate molecules, which will then be tested by a high-throughput screening team led by Angela Koehler, the Charles W. and Jennifer C. Johnson Professor of Biological Engineering at MIT, and Jaime Cheah, associate director of scientific outreach and collaborative screening at the Broad Institute’s Center for the Development of Therapeutics.

“Those libraries will be screened both to identify those molecules that hit their target, but also to then provide all of that screening data back to the computational approach in order to improve it,” Voigt said.

Promising candidates will move to greenhouse studies led by researchers at the University of Tennessee at Knoxville, the University of Illinois, UNC, and Robigo. The first greenhouse tests of initial RNAi candidates are expected to be completed by the end of the first year of the program, according to MIT News.

The project also includes developing living microbial systems — engineered bacteria, fungi, and srRNA — that can degrade agrochemicals before they reach food, soil, or waterways. This approach aims to provide a scalable strategy for reducing environmental and human exposure.

For university students studying agriculture, environmental science, bioengineering, or public health, this project represents a significant investment in applying AI and synthetic biology to real-world problems. The research could lead to new career opportunities in agricultural biotechnology, computational biology, and regulatory science. Students at the participating institutions may also find research or internship opportunities connected to the project.

The funding comes from ARPA-H under agreement number 140D042690030. The views and conclusions in the announcement are those of the authors and should not be interpreted as representing official U.S. government policies.