Computational multiomics methods are based on machine learning methods, and are primarily used for classifying patients into subtypes, discovering novel biomarkers, drug repurposing, and advancing precision medicine. Advances in high-throughput technologies have enabled comprehensive profiling of multiple molecular layers, resulting in the emergence of multiomics approaches for a more accurate understanding of disease mechanisms, therapeutic targets, and biological heterogeneity. This review examines current applications of multiomics in oncology, ageing, and immune-mediated diseases, highlighting the strengths and challenges of integrative models in understanding disease mechanisms, identifying biomarkers, and guiding precision therapies. Integration strategies, from early to late fusion and horizontal to vertical frameworks, are also examined alongside recent advances in computational platforms and preprocessing techniques.
Mathew et al. (Fri,) studied this question.