The Integration of Multi-omics With Artificial Intelligence in Hepatology: A Comprehensive Review of Personalized Medicine, Biomarker Identification, and Drug Discovery
{"title":"The Integration of Multi-omics With Artificial Intelligence in Hepatology: A Comprehensive Review of Personalized Medicine, Biomarker Identification, and Drug Discovery","authors":"Devina Ramesh , Praveen Manickavel , Soumita Ghosh , Mamatha Bhat","doi":"10.1016/j.jceh.2025.102611","DOIUrl":null,"url":null,"abstract":"<div><div>The evolution of high-throughput technologies has expanded the role of multi-omics in hepatology, moving away from traditional hypothesis-driven research toward integrative, data-driven models. However, high cost and resource intensity have limited widespread adoption. The multi-omics datasets for liver diseases are still relatively small. Progress has been made in integrating a few omics types, particularly in combining genomics with transcriptomics, proteomics, or metabolomics for liver disease research. However, fully integrated multi-omics studies remain limited, with most research focusing on two or three omics layers rather than comprehensive multi-modal integration. Emerging approaches such as federated learning can be leveraged to securely integrate multi-omics data, advance AI-driven biomarker discovery, and enhance precision medicine strategies across institutions.</div></div>","PeriodicalId":15479,"journal":{"name":"Journal of Clinical and Experimental Hepatology","volume":"15 6","pages":"Article 102611"},"PeriodicalIF":3.2000,"publicationDate":"2025-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Clinical and Experimental Hepatology","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0973688325001112","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
The evolution of high-throughput technologies has expanded the role of multi-omics in hepatology, moving away from traditional hypothesis-driven research toward integrative, data-driven models. However, high cost and resource intensity have limited widespread adoption. The multi-omics datasets for liver diseases are still relatively small. Progress has been made in integrating a few omics types, particularly in combining genomics with transcriptomics, proteomics, or metabolomics for liver disease research. However, fully integrated multi-omics studies remain limited, with most research focusing on two or three omics layers rather than comprehensive multi-modal integration. Emerging approaches such as federated learning can be leveraged to securely integrate multi-omics data, advance AI-driven biomarker discovery, and enhance precision medicine strategies across institutions.