Statistical and Machine-Learning Analyses in Nutritional Genomics Studies

Abstract

Nutritional compounds may have an influence on different OMICs levels, including genomics, epigenomics, transcriptomics, proteomics, metabolomics, and metagenomics. The integration of OMICs data is challenging but may provide new knowledge to explain the mechanisms involved in the metabolism of nutrients and diseases. Traditional statistical analyses play an important role in description and data association; however, these statistical procedures are not sufficiently enough powered to interpret the large integrated multiple OMICs (multi-OMICS) datasets. Machine learning (ML) approaches can play a major role in the interpretation of multi-OMICS in nutrition research. Specifically, ML can be used for data mining, sample clustering, and classification to produce predictive models and algorithms for integration of multi-OMICs in response to dietary intake. The objective of this review was to investigate the strategies used for the analysis of multi-OMICs data in nutrition studies. Sixteen recent studies aimed to understand the association between dietary intake and multi-OMICs data are summarized. Multivariate analysis in multi-OMICs nutrition studies is used more commonly for analyses. Overall, as nutrition research incorporated multi-OMICs data, the use of novel approaches of analysis such as ML needs to complement the traditional statistical analyses to fully explain the impact of nutrition on health and disease.

The methodology of food design. Part 2. Digital nutritiology in personal food

“…Machine-aided processing of datarefers to a computer system capable of describing the solution to a given problem and creating an algorithm based on this solution. More details about machine-aided processing of datamethods are presented in the work of L. Khorramine-zhad, [46]. You also need to use programs like Python (Python), R, RStudio, Statistics, etc.…”

Implementation of Nutrigenetics and Nutrigenomics Research and Training Activities for Developing Precision Nutrition Strategies in Malaysia

“…Machine learning and artificial intelligence will be employed to integrate the data from nutrigenetics, nutrigenomics, epigenetics, metabolomics, and gut microbiome. Machine learning has the potential to integrate omics data through the extraction of patterns in large datasets and clustering to generate predictive models and algorithms [ 34 ]. One of the machine learning methods is supervised machine learning, which is aimed at generating models that can accurately predict the data [ 35 ].…”

“…One of the machine learning methods is supervised machine learning, which is aimed at generating models that can accurately predict the data [ 35 ]. Through data mining, patterns and key indicators are extracted which are then used to find correlations within the various data groups (nutrigenetics, nutrigenomics, nutri-epigenetics, metabolomics and gut microbiota) [ 34 ]. Machine learning also involves supervised multivariate analysis, an example of which is partial least squares regression (PLSR), which works by identifying variables in groups of data which are most associated with the outcome of interest, thereby reducing the number of predictor variables [ 36 , 37 ].…”

Genomics and Personalized Nutrition

“…The purpose of this Special Issue was to expand and add to the research which uses genomics technologies in the development of personalized nutrition recommendations. This Special Issue on “Genomics and Personalized Nutrition” features five original articles [ 5 , 6 , 7 , 8 , 9 ] and four reviews [ 10 , 11 , 12 , 13 ] which examine two facets of personalized nutrition: 1—genomics and food bioactive compounds; and 2—genetic variations and diet interactions.…”

“…Further, the use of multiple genomics in nutrition research requires sophisticated integration analysis methods. In the article by Khorraminezhad et al, 2020 [ 10 ], machine learning analyses are defined and nutrition studies that use machine learning techniques are examined in-depth. Overall, the review concludes that use of machine learning should complement traditional statistical analyses to fully explain the impact of nutrition on health and disease using genomics techniques [ 10 ].…”