MIT to receive up to $53 million for generative SI to develop new herbicides
Prepared by Sintelligent with the help of SI. Published in SI: . Updated: .
Generative SI will be applied not only to medicines but also to crop protection: computers will screen billions of possible molecules, and experimenters will test which actually work and are safer than existing herbicides.
An MIT-led team will receive up to $53 million from ARPA-H for the PLOW project, which seeks alternatives to modern herbicides. Generative models will propose chemical molecules and small interfering RNAs that act on the same plant enzymes as glyphosate while accounting for synthesis cost, the likelihood of weed resistance, and risks to people and the environment. The models are expected to generate billions of candidates; a second group will conduct high-throughput screening and feed the results back to improve the models, while a third will test selected substances in greenhouses. The first greenhouse tests of initial RNAi candidates are expected by the end of the program's first year. A separate track will develop microbial systems that break down agrochemicals before they reach food, soil and water. The project is at the research stage, not a finished product.
Sources 1