AI helps farmers to combat bacterial crop disease

China’s Agricultural Ministry is asking farmers to switch to late-autumn crops like sweet potatoes because of the crop damages already seen.
Source – USDA Photo by Lance Cheung. Public Domain

Scientists have used artificial intelligence to help them to upgrade plant immune systems. This genetic manipulation potentially alters how agricultural produce, like tomatoes and potatoes, can be rendered to defend against harmful bacteria. The researchers, through a series of experiments, demonstrated that while the reengineering of plant receptors can lead them to recognise bacterial threats, it also stands that such processes can additionally enhance plant resistance and hence prepare agricultural produce against such threats and thus create a future of more resilient crops.

Essential to the research is the concept of plants, like animals, having immune systems. Part of the defence toolkit of plants includes immune receptors, which give them the ability to detect bacteria and defend themselves against microbial threats.

One of those receptors, called FLS2, has been identified as helping plants to recognise flagellin — a protein in the tiny tails bacteria use to swim. Nonetheless, bacteria are adept, and they constantly evolve to avoid detection.

According to lead scientist, Gitta Coaker, professor in the Department of Plant Pathology: “Bacteria are in an arms race with their plant hosts, and they can change the underlying amino acids in flagellin to evade detection.”

Ralstonia solanacearum usually enters the plant by a wound. Image by Clemson University – USDA Cooperative Extension Slide Series, , Bugwood.org – This image is Image Number 1234208 at Forestry Images, a source for forest health, natural resources and silviculture images operated by The Bugwood Network at the University of Georgia and the USDA Forest Service.

One of the researchers’ targets is a major crop threat: Ralstonia solanacearum, the cause of bacterial wilt. Some strains of the soil-borne pathogen can infect more than 200 plant species, including staple crops like tomato and potato.

R. solanacearum is an aerobic non-spore-forming, Gram-negative, plant pathogenic bacterium. R. solanacearum is soil-borne and motile; it colonises the xylem, causing bacterial wilt in a wide range of potential host plants. The disease is known as Granville wilt when it occurs prominently in tobacco plants. Bacterial wilts of tomato, pepper, eggplant, and Irish potato are also caused by the bacterium R. solanacearum.

Coaker’s research group turned to using natural variation coupled with artificial intelligence — specifically AlphaFold, a tool developed to predict the 3D shape of proteins and reengineered FLS2, essentially upgrading its immune system to catch more intruders.

The scientists focused on receptors already known to recognise more bacteria, even if they weren’t found in useful crop species. By comparing them with more narrowly focused receptors, the researchers were able to identify which amino acids to change.

Coaker adds: “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.”

The research appears in the journal Nature Plants, titled “Unlocking expanded flagellin perception through rational receptor engineering.”

Continue Reading