From peas to potatoes, AI identifies nearly 800 promising plant proteins for food and cosmetics
Scientists from Leeds' School of Food Science and Nutrition have developed an advanced AI process that can rapidly identify plant proteins capable of acting as emulsifiers from tens of millions of initial candidates. To date, it has identified nearly 800. The discovery will cut years of costly trial-and-error research and bring the next generation of plant-based foods and cosmetics closer.
Scientists from the University of Leeds' School of Food Science and Nutrition have developed an artificial intelligence (AI) system capable of swiftly identifying plant proteins that could function as emulsifiers. This technology has already pinpointed nearly 800 promising candidates out of an initial pool of tens of millions of possibilities.
Emulsifiers play a crucial role in various industries, including food, cosmetics, pharmaceuticals, and industrial applications. They help bind oil and water together into stable mixtures, which is why there is a growing interest in finding sustainable, plant-based alternatives to synthetic or animal-derived emulsifiers. The research, led by Dr. Simha Sridharan from the university's Sarkar Lab and published in Communications Chemistry, employed a combination of AI and statistical physics to model and predict the emulsifying properties of plant proteins.
By understanding how proteins interact with oil and water mixtures, the AI system can rapidly screen potential candidates and identify those with properties similar to those of animal proteins. The team's findings could significantly reduce the time and cost associated with testing and identifying suitable plant-based emulsifiers, accelerating the shift towards sustainable, plant-based food systems.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
