AUTHOR=Galal Aya , Talal Marwa , Moustafa Ahmed 

TITLE=Applications of machine learning in metabolomics: Disease modeling and classification

JOURNAL=Frontiers in Genetics

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.1017340

DOI=10.3389/fgene.2022.1017340

ISSN=1664-8021

ABSTRACT=Metabolomic studies have gained increased interest recently, enabling the research of biological phenotypes at the biochemical level. Because the metabolome can reveal what is happening in a cell or tissue according to the health or disease condition, metabolomic approaches are able to answer questions that other omics approaches may not be able to address directly. However, like high-throughput omics experiments, metabolomics studies often generate large amounts of complex data that are difficult to interpret. Machine Learning (ML), a subcategory of Artificial Intelligence (AI), can be employed to recognize patterns, analyze text, and identify objects across various domains and disciplines. ML algorithms range from logic-based to statistics and instance-based. With the inherent complexity of biological data, using ML to build informative predictive models is gaining widespread appeal. This review discusses how disease pathogenesis can be improved by deep and comprehensive metabolomic characterization. We cover the typical outline of a metabolic workflow. We also provide a review of the key ML methods and the application of ML in analyzing metabolomic data. Finally, we discuss how applying ML algorithms to metabolomic data can improve our understanding of disease pathogenesis and provide a tool for disease prediction.