From sourdough starters at home to loaves in supermarkets – artificial intelligence (AI) could be key to standardising and upscaling unpredictable sourdough, according to new research.
In a recent paper published in Trends in Food Science & Technology, scientists from Cardiff University, Shanxi University and Jiangnan University analysed how combining AI, a biological analysis approach called multi-omics, and computational modelling could help design synthetic microbial communities (SynComs) for sourdough products that are predictable, safe, and scalable.
Dr Faizan Sadiq, Assistant Professor in Microbial Biofilms at Cardiff University's School of Dentistry and co-author, said: "For thousands of years, sourdough fermentation relies on complex communities of lactic acid bacteria and yeasts – the composition of which shifts with flour type, process conditions and geography. That natural diversity produces distinctive breads but can make industrial production inconsistent, lengthen fermentation times, and complicate food-safety control."
The international team reviewed existing research for their study and demonstrate how combining traditional knowledge about sourdough fermentation with advanced technology could improve consistency, scalability, flavour and sustainability. They suggest that AI, guided by multi-omics data (a menthod that combines data from multiple fields) and computer models of metabolism, may help identify the most important microbes in the fermentation process and predict how they may work together in different environments. This could guide the design of SynComs suited to different flours and production settings.
Sourdough has surged in popularity, but its natural variability makes consistent, large-scale production challenging. By integrating AI with multi-omics, we can model microbial interactions more deeply and design stable synthetic communities that bring the reliability industry needs without losing the character people love.
Dr Sadiq added: "The same design principles for synthetic communities are directly applicable to clinical microbiology – for example, building model bacterial communities to study infections and to evaluate antimicrobial tolerance and resistance."
Professor Zhang from Shaxi University added: "We reviewed existing evidence showing how AI and multi-omics could help optimise sourdough and other complex fermentations. This approach provides a framework for designing stable synthetic microbial communities, or SynComs, to deliver consistent performance".
"Although challenges remain in scaling SynComs for industrial use, AI-enabled multi-omics offers a promising route to optimise sourdough fermentation and drive innovation in fermented food production," added Dr Sadiq.
The paper, Enhancing Sourdough Fermentation with AI and Multi-Omics: From Natural Diversity to Synthetic Microbial Community , was published in Trends in Food Science & Technology.
The study builds on Dr Sadiq and Professor Zhang's previous, extensive work into sourdough microbiota, applying multi-omics approaches to investigate safety, aroma, and quality.
