Prog Mol Biol Transl Sci. 2026 ;pii: S1877-1173(26)00012-8. [Epub ahead of print]221
43-70
Multi-omics research has transformed our ability to study biological systems by capturing information across multiple molecular layers, including genomics, transcriptomics, epigenomics, proteomics, metabolomics, and microbiomics. Each omics dimension provides a unique perspective on cellular and organismal function, yet single-omics approaches often fail to capture the full complexity of health and disease. Integrating diverse omics datasets offers a systems-level view that is essential for advancing precision medicine, addressing disease heterogeneity, and uncovering mechanisms of pathogenesis. The increasing availability of high-dimensional, heterogeneous data demands robust computational and AI-driven approaches. Methods ranging from traditional statistical techniques to advanced deep learning and network-based models enable the integration, analysis, and interpretation of multi-omics data. These approaches have already demonstrated significant impact in cancer, cardiovascular and metabolic disorders, neurodegenerative diseases, infectious diseases, and rare genetic conditions. Translational applications include biomarker discovery, patient stratification, therapy optimization, drug repurposing, and clinical decision support. Despite these advances, challenges remain in data standardization, scalability, interpretability, and ethical use of genomic information. Future directions emphasize explainable AI, regulatory frameworks, and integration with digital health records to bridge research insights with clinical practice. Overall, AI-powered multi-omics integration will shape the future of biomedical research and precision healthcare.
Keywords: Artificial intelligence; Disease modelling; Multiomics