Diving Deep into the Data: A Review of Deep Learning Approaches and Potential Applications in Foodomics

Abstract

Deep learning is a trending field in bioinformatics; so far, mostly known for image processing and speech recognition, but it also shows promising possibilities for data processing in food analysis, especially, foodomics. Thus, more and more deep learning approaches are used. This review presents an introduction into deep learning in the context of metabolomics and proteomics, focusing on the prediction of shelf-life, food authenticity, and food quality. Apart from the direct food-related applications, this review summarizes deep learning for peptide sequencing and its context to food analysis. The review’s focus further lays on MS (mass spectrometry)-based approaches. As a result of the constant development and improvement of analytical devices, as well as more complex holistic research questions, especially with the diverse and complex matrix food, there is a need for more effective methods for data processing. Deep learning might offer meeting this need and gives prospect to deal with the vast amount and complexity of data.

Metabolomics: A suitable foodomics approach to the geographical origin traceability of Ethiopian Arabica specialty coffees

“…They are used to identify novel bioactive chemicals, determine the effects of agricultural methods, processing, and/or storage on the chemical composition of food, and ultimately conduct authenticity studies (Danezis, Tsagkaris, Camin, et al, 2016). Compared to other omics disciplines, the metabolome is most closely related to the phenotype and is more significantly influenced by exogenous influences, such as weather, soil composition, or storage conditions, than the proteomics (Class et al, 2021; Creydt & Fischer, 2018).…”

“…The metabolome, however, permits an even more apparent fingerprint of a system because numerous substances may be considered for evaluation, and the specific condition of a product at a specific time point can be predicted (Class et al, 2021). By assessing the total amounts of small‐molecule metabolites, metabolomics provides a picture of pertinent biological activities (amino acids, organic acids, starch, fatty acids, lipids, hormones, peptides, and vitamins).…”

NMR in Metabolomics: From Conventional Statistics to Machine Learning and Neural Network Approaches

“…Foodomics is a term referred to the metabolomic approaches applied to foodstuffs for investigating topics mainly related with nutrition. Nowadays, DL methods are being progressively applied in the food field with different purposes, such as fraud detection [115]. Furthermore, another important issue is to guarantee the geographical origin and production/processing procedures of food, the precise proportions of ingredients, including additives and the kind of used raw materials.…”

The Shelf Life of Milk—A Novel Concept for the Identification of Marker Peptides Using Multivariate Analysis

“…It is the responsibility of the manufacturer to set a best-before date, but it is not specified in which way such an evaluation must be carried out. The manufacturer may define the conditions under which the best-before date is fixed [ 12 ]. Mostly, it is determined on the basis of microbiological and sensory methods [ 13 ], but beyond that, an individual safety margin is included.…”