Abstract Metabolomics reveals molecular changes at the metabolic level during biological processes. Recent advancements, particularly through integration with other omics and artificial intelligence (AI), are advancing metabolic data analysis and multi‐omics interpretation. This review introduces a “metabolomics‐centric” paradigm as a conceptual framework for multi‐omics integration, positioning metabolic readouts as the functional anchor for interpreting genotype‐phenotype relationships. It also chronicles the evolution and medical applications of integration technologies. Our discussion first traces the field's evolution from bulk to single‐cell and spatial methodologies, next surveys integration strategies to uncover mechanistic insights, and finally examines how AI‐driven multimodal data integration and AI‐optimized metabolomics workflows tackle persistent biological and computational challenges. Looking forward, this review identifies the AI virtual cell as a pivotal future direction for metabolomics‐based multi‐omics integration, calling for increased attention to its development to simulate dynamic molecular phenotypic networks within a multi‐omics context.
Wang et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: