Yagin F.H.2024-08-042024-08-04202397830313650279783031365010https://doi.org/10.1007/978-3-031-36502-7_3https://hdl.handle.net/11616/92176Cells are a fundamental unit of life, and the ability to study the phenotypes and behavior of cells is crucial to understanding the functioning of complex biological systems. The prognostic and predictive accuracy of disease phenotypes can be enhanced by the use of integrative omics approaches due to their ability to examine biological processes holistically, which could lead to improved treatment and prevention in the long term. Therefore, multi-omics data integration strategies are needed to combine the complementary information brought by each omic layer. A major challenge in multi-omics research for disease diagnosis, monitoring, and treatment options is how to integrate high-dimensional data from omics. This chapter focused on machine learning methods for multi-omics data integration. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. All rights reserved.eninfo:eu-repo/semantics/closedAccessBiomarker discoveryDisease diagnosisDisease subtypingMachine learningMulti-Omics data integrationBook Chapter233810.1007/978-3-031-36502-7_32-s2.0-85194446694N/A