As dairy enterprises increasingly focus on microbial contamination, traditional detection technologies are gradually showing limitations in terms of detection capability, accurate source tracking, and rapid response, especially when dealing with microbial communities in complex processing environments. Fortunately, whole-genome sequencing (WGS) and metagenomic sequencing provide innovative alternative solutions. These technologies significantly improve the detection of harmful microbes by offering strain-level resolution, detecting low-abundance organisms, and uncovering previously undetectable microbes. This review discusses the application of WGS and metagenomic sequencing in microbial monitoring, contamination source tracking, and quality control across the entire milk powder production chain. In particular, it highlights the progress made in microbial typing and source tracking, as well as in the detection of antibiotic resistance genes (ARGs) and virulence factor genes (VFGs). This review also compares microbial control standards for milk powder and its processing environment across different countries and international organizations, providing a regulatory perspective. Furthermore, the integration of emerging technologies is also discussed, particularly machine learning (ML) and deep learning (DL). Artificial intelligence (AI) enables more efficient, predictive, and accurate microbial monitoring, improving contamination control and contributing to safer and higher-quality milk powder production processes. This review provides critical insights that contribute to improving microbial safety management and control strategies in milk powder production.
Liu et al. (Tue,) studied this question.