Abstract
Assessment of food quality is an important feature in novel food products development process. This is because quality has implications for safety, nutritional contents, traceability, and market value of foods. However, due to the biochemical complexities of food products, it has become important that advanced analytical tools relating to proteomics, genomics, and big data be used to completely characterize the molecular features of food substances and monitor potential variations in quality. Such in silico tools could be used to generate molecular templates for probing the biochemical and chemo-molecular features of food substances to validate food quality for high throughput screening. For example, deep learning has received significant attention due to its capacity for feature learning based on multi-layer artificial neural networks. The combination of deep learning, molecular analysis using advanced techniques such as chromatography, electrophoresis and spectroscopy, and genome characterization will constitute a novel approach for probing the quality dynamics of food substances. Discussed in this chapter are opportunities for integrated chemical analysis, bioinformatics, and computational approaches for effective monitoring of food quality. In addition, current advancements in food quality monitoring through a combination of proteomic and big data tools, as well as their future perspectives are addressed.