The Intersection of Knowledge Graphs, Large Language Models, and Mass Spectrometry Data: Progress and Applications

ABSTRACT The rapid development of knowledge graphs (KGs) and large language models (LLMs) in artificial intelligence (AI) has provided a new approach to intelligent analysis of mass spectrometry (MS) data. KGs can enhance the ability to identify metabolites, perform functional annotation, and integrate multi‐omics data through structured knowledge representation and semantic association. Meanwhile, the powerful context‐understanding capabilities of LLMs and advanced natural language processing (NLP) technologies can assist in the automated analysis and application of MS data. When combined, they overcome the limitations of traditional technologies, which is significant for researching high‐dimensional data analysis, detecting low‐abundance signals, and integrating knowledge across domains. This article reviews cross‐domain applications of KGs and LLMs in MS data analysis. We focus on the latest progress in metabolite annotation, automated report generation, and multi‐omics data integration. Furthermore, from the perspectives of quality, evolution, and reliability of KGs, we outline technical challenges currently faced, such as insufficient data standardization, lack of traceability and version control in KGs, limited model interpretability, and obstacles in cross‐modal fusion. Finally, we summarize research directions that can promote integration of KG and LLM in the future, such as how to enhance knowledge representation and how to achieve multimodal learning and dynamic knowledge updates. All of these can improve the accuracy and efficiency of data interpretation and open new research directions in metabolomics, proteomics, and broader life sciences. This article is categorized under: Algorithmic Development > Biological Data Mining Application Areas > Health Care Fundamental Concepts of Data and Knowledge > Knowledge Representation