We’ve updated our Privacy Policy to make it clearer how we use your personal data. We use cookies to provide you with a better experience. You can read our Cookie Policy here.
Stay up to date on the topics that matter to you
Efforts to industrialise sourdough bread production may benefit from artificial intelligence (AI) and multi-omics, according to a recent study.
The paper, published in Trends in Food Science & Technology, explores how AI-guided approaches could help design synthetic microbial communities (SynComs) that are more predictable and scalable than traditional sourdough starters.
Sourdough bread is produced through the fermentation of flour and water by naturally occurring communities of lactic acid bacteria and yeasts. These communities vary according to environmental factors, flour type and geographical location. While this variability contributes to the bread’s flavour and texture, it also introduces inconsistencies in production and quality.
In industrial settings, this variability can lengthen processing times and complicate safety controls. The new paper outlines how a more engineered approach – one that draws on AI and biological data – could streamline the production process by identifying optimal microbial combinations.
The new paper suggests that AI, when used alongside computational modelling and a biological analysis approach called multi-omics, can identify the most important microbes in the fermentation process and predict how they may work together in different environments.
Multi-omics is a scientific approach that combines different types of biological data, such as DNA (genomics), RNA (transcriptomics), proteins (proteomics) and metabolites (metabolomics), to get a comprehensive view of how living systems function.
This information could be used to predict how microbial communities behave, enabling the design of stable SynComs tailored to specific production environments.
A synthetic microbial community is a group of microorganisms assembled in the lab with specific strains chosen for their interactions. SynComs are designed to replicate or optimise natural processes in controlled environments.
Such predictive modelling may allow for the customisation of microbial communities based on flour type or other production variables, reducing the trial-and-error element in developing sourdough starters at an industrial scale.
“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,” said study author Faizan Sadiq, PhD, an assistant professor in microbial biofilms at Cardiff University.
Although the paper focuses on sourdough production, the authors suggest that similar approaches could apply in other fields.
“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,” said Sadiq.
“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.”
Reference: Yu Y, Wang J, Sadiq FA, et al. Enhancing sourdough fermentation with AI and multi-omics: From natural diversity to synthetic microbial community. Trends Food Sci Technol. 2025;165:105233. doi: 10.1016/j.tifs.2025.105233
This article has been republished from the following materials. Note: material may have been edited for length and content. For further information, please contact the cited source. Our press release publishing policy can be accessed here.
