Scientists at UC Davis have used artificial intelligence to help plants better recognize and defend against bacterial threats, a promising development that could safeguard vital crops like tomatoes and potatoes.
Researchers from the University of California, Davis, have utilized artificial intelligence to enhance the immune systems of plants, allowing them to detect a broader spectrum of bacterial threats. This breakthrough may significantly bolster the defense mechanisms of staple crops such as tomatoes and potatoes against debilitating diseases.
The study, published in the journal Nature Plants, highlights the innovative use of AI to redesign plant immune receptors. These receptors are crucial components of the plant immune system, enabling plants to identify and counteract bacterial invaders.
One of these receptors, FLS2, is responsible for recognizing flagellin, a protein found in the tail structures that bacteria use for mobility. However, bacteria often mutate to escape detection, posing a continual challenge to plant defenses.
“Bacteria are in an arms race with their plant hosts, and they can change the underlying amino acids in flagellin to evade detection,” lead author Gitta Coaker, a professor in the Department of Plant Pathology at UC Davis, said in a news release.
To overcome this challenge, Coaker’s team employed AlphaFold, an advanced AI tool designed to predict the 3D structure of proteins. By harnessing natural variations and AI insights, they redesigned FLS2, effectively upgrading the plant’s immune response to recognize and respond to a wider array of bacterial invaders.
The researchers specifically targeted receptors known to detect more bacterial strains, even if these receptors were not originally found in key crop species. By comparing these broad-spectrum receptors to narrower ones, they pinpointed which amino acids needed alteration.
“We were able to resurrect a defeated receptor, one where the pathogen has won, and enable the plant to have a chance to resist infection in a much more targeted and precise way,” Coaker added.
The implications of this research extend to creating broad-spectrum disease resistance in crops via predictive design. One of the focal points is Ralstonia solanacearum, a formidable soil-borne pathogen responsible for bacterial wilt, which afflicts more than 200 plant species, including vital crops like tomatoes and potatoes.
Looking forward, the team aims to refine machine learning tools to predict which immune receptors are optimal for editing and to minimize the number of amino acids that require modification. This innovative approach could revolutionize the way plant immune systems are enhanced, potentially leading to significantly higher crop yields and better global food security.
In addition to Coaker, the study’s authors include Tianrun Li, Esteban Jarquin Bolaños, Danielle M. Stevens and Hanxu Sha of UC Davis, along with Daniil M. Prigozhin of the Lawrence Berkeley National Laboratory.
Source: University of California, Davis