Recent Advances in Artificial Intelligence-Driven Discovery and Industrial Applications of Bacteriocins from Lactic Acid Bacteria

• Lactic acid bacteria bacteriocins act as natural food preservatives. • Artificial intelligence enables efficient identification and application of these bacteriocins. • AI integration accelerates the discovery and industrial optimization of lactic acid bacteria bacteriocins Food spoilage poses a significant challenge to the global food industry, as traditional chemical preservatives carry health risks. In contrast, bacteriocins produced by lactic acid bacteria (LAB) represent a natural, efficient, and non-toxic antimicrobial substance, offering potential as alternatives to chemical preservatives. The traditional methods for discovering bacteriocins rely on pure culture screening and low-throughput sequencing, which encounter bottlenecks such as insufficient coverage of uncultured strains, low screening efficiency, and significant errors in activity prediction. Additionally, natural bacteriocins generally face issues of low yield and poor stability, which limit their industrial application. In recent years, artificial intelligence (AI) technologies, including machine learning (ML) and deep learning (DL), have significantly enhanced the efficiency and accuracy of discovering LAB bacteriocins through precise predictions, intelligent screening, and rational design of microbiome data. This article presents various algorithm models (such as SVM, CNN, Transformer, etc.) and tool applications (such as BAGEL4, BPAGS), systematically reviewing the latest advancements of AI in strain identification and screening, bacteriocin selection, and molecular design of bacteriocins. We discuss the critical role of AI in optimizing fermentation media production, simulating purification processes, and modifying high-yield strains, thereby facilitating the transition of bacteriocins from laboratory research to industrial applications. Moreover, this review highlights current challenges, including data scarcity and model interpretability. Looking ahead, the integration of multi-omics data and generative AI technologies holds promise for the intelligent design and efficient development of bacteriocins, thereby facilitating their widespread application in food preservation.