The NMR added value to the green foodomics perspective: Advances by machine learning to the holistic view on food and nutrition

Food is a complex matter, literally. From production to functionalization, from nutritional quality engineering to predicting effects on health, the interest in finding an efficient physicochemical characterization of food has boomed in recent years. The sheer complexity of characterizing food and its interaction with the human organism has however made the use of data driven approaches in modeling a necessity. High-throughput techniques, such as nuclear magnetic resonance (NMR) spectroscopy, are well suited for omics data production and, coupled with machine learning, are paving a promising way of modeling food-human interaction. The foodomics approach sets the framework for omic data integration in food studies, in which NMR experiments play a key role. NMR data can be used to assess nutritional qualities of food, helping the design of functional and sustainable sources of nutrients; detect biomarkers of intake and study how they impact the metabolism of different individuals; study the kinetics of compounds in foods or their by-products to detect pathological conditions; and improve the efficiency of in silico models of the metabolic network.