ARTIFICIAL INTELLIGENCE IN METABOLOMIC RESEARCH

Abstract

The term "metabolomics" refers to high-throughput methods for detecting various metabolites and small molecules in biological samples. Undirected metabolomics, also known as unbiased global metabolome analysis, can be used to discover key metabolites as variables or measurements of human health and illness. From this vantage point, it is investigated how artificial intelligence and machine learning enable significant advances in non-targeted metabolic processes as well as significant findings in the early detection and diagnosis of diseases (Jung-Ming G. Lin, et al. 2022). Metabolomics is important for finding cures for many diseases. In the development of innovations in the field of biotechnology, it is of great importance to collect, filter, analyze, and use biological information in smart data. For this reason, many biotechnology companies and various healthcare organizations around the world have created large biological databases. This biological data accelerates the development of products in many areas. Algorithms are being developed for biological data analysis. It is thought that many disease treatments will be found when the human genome is edited. Machine learning techniques are effective tools for metabolomic investigation; however, they can only be used in straightforward computing scenarios. When used functionally, data formatting frequently calls for the use of sub-computational resources that are not covered in this area.