Data mining/machine learning methods in foodomics

Foodomics aims to investigate the effects of food on health by collecting a large amount of data from which the relevant information is extracted using data mining methods. Nevertheless, it can be stated that their use is subordinate to software implemented on certain platforms since a lack of experience is often noted in researchers. The present paper is aimed to provide an overview on the latest research advances describing data analysis process in the untargeted approach using data mining methods when analytical techniques such as NMR, chromatography-MS and 2D chromatography are mainly employed. Moreover, it emphasizes the gaps that still need to be filled in the use of data mining methods. Finally, the terminology employed in this field is also explained and discussed.

Automated summary

Foodomics aims to investigate the effects of food on health by collecting and analyzing data using data mining methods, often implemented on specific platforms due to researchers' lack of experience. This paper provides an overview of the latest research advances in data analysis processes in untargeted approaches, mainly using analytical techniques such as NMR, chromatography-MS, and 2D chromatography, while emphasizing the gaps that still need to be filled in the use of data mining methods. Additionally, it explains and discusses the terminology used in this field.