Use of artificial intelligence and machine learning for multiomics

In response to the increasing complexity of biomedical data, artificial intelligence (AI) and machine learning (ML) have become indispensable tools for integrating and analyzing multiomic datasets, enabling significant advances in precision medicine. This chapter explores the application of ML and AI techniques in multiomics, highlighting their transformative impact on biomedical research and healthcare. It introduces commonly used supervised and unsupervised ML methods for analyzing multiomic datasets, outlines data integration strategies, including early, middle, and late integration approaches, and addresses key challenges such as data heterogeneity, high dimensionality, missing data, and model interpretability. Special attention is given to the application of these approaches in atherosclerotic cardiovascular disease (ASCVD). While much of the current AI-driven multiomics research has centered on oncology, this chapter emphasizes the potential of these methods to advance the understanding and treatment of ASCVD. The chapter concludes by underscoring the promise of AI and ML in advancing personalized medicine and future innovations in disease diagnosis, prognosis, and therapy.