Abstract:Globally, we are failing to meet numerous nutritional, health, and environmental targets linked to food. Defining food composition in its full chemical and quantitative diversity is central to data-driven decision making for supporting nutrition and sustainable diets. “Foodomics”—the application of omics-technology to characterize and quantify biomolecules to improve wellbeing—has the potential to comprehensively elucidate what is in food, how this composition varies across the food system, and how diet compos… Show more
“…Food composition data is poised to grow in size and quality [37] [38] [39], and such predictive modelling applications can assist consumers in making reliable dietary decisions. For example, to choose food ingredients and cooking methods by getting answers to queries like-“How do boiling/streaming affect the nutrient profile of Vegetable X compared to roasting or frying”.…”
The future of personalized health relies on knowledge of dietary composition. The current analytical methods are impractical to scale up, and the computational methods are inadequate. We propose machine learning models to predict the nutritional profiles of cooked foods given the raw food composition and cooking method, for a variety of plant and animal-based foods. Our models (trained on USDAs SR dataset) were on average 31% better than baselines, based on RMSE metric, and particularly good for leafy green vegetables and various cuts of beef. We also identified and remedied a bias in the data caused by representation of composition per 100grams. The scaling methods are based on a process-invariant nutrient, and the scaled data improves prediction performance. Finally, we advocate for an integrated approach of data analysis and modeling when generating future composition data to make the task more efficient, less costly and apply for development of reliable models.
“…Food composition data is poised to grow in size and quality [37] [38] [39], and such predictive modelling applications can assist consumers in making reliable dietary decisions. For example, to choose food ingredients and cooking methods by getting answers to queries like-“How do boiling/streaming affect the nutrient profile of Vegetable X compared to roasting or frying”.…”
The future of personalized health relies on knowledge of dietary composition. The current analytical methods are impractical to scale up, and the computational methods are inadequate. We propose machine learning models to predict the nutritional profiles of cooked foods given the raw food composition and cooking method, for a variety of plant and animal-based foods. Our models (trained on USDAs SR dataset) were on average 31% better than baselines, based on RMSE metric, and particularly good for leafy green vegetables and various cuts of beef. We also identified and remedied a bias in the data caused by representation of composition per 100grams. The scaling methods are based on a process-invariant nutrient, and the scaled data improves prediction performance. Finally, we advocate for an integrated approach of data analysis and modeling when generating future composition data to make the task more efficient, less costly and apply for development of reliable models.
“…Aligned with this is the emerging era of "big data" and developments in almost every field (from health to economics and technology) that dominates the modern age. We are now in a post-genomic era marked by new terms and definitions: "personalized nutrition, " "nutrigenomics, " "metabolomics, " and "foodomics" (132)(133)(134). These novel domains should be accounted for when public health, wellbeing, health span, lifespan, and knowledge are addressed.…”
Section: Clinical Perspective and Future Directions -Precision Nutrit...mentioning
Aging is a natural physiological process, but one that poses major challenges in an increasingly aging society prone to greater health risks such as diabetes, cardiovascular disease, cancer, frailty, increased susceptibility to infection, and reduced response to vaccine regimens. The loss of capacity for cell regeneration and the surrounding tissue microenvironment itself is conditioned by genetic, metabolic, and even environmental factors, such as nutrition. The senescence of the immune system (immunosenescence) represents a challenge, especially when associated with the presence of age-related chronic inflammation (inflammaging) and affecting the metabolic programming of immune cells (immunometabolism). These aspects are linked to poorer health outcomes and therefore present an opportunity for host-directed interventions aimed at both eliminating senescent cells and curbing the underlying inflammation. Senotherapeutics are a class of drugs and natural products that delay, prevent, or reverse the senescence process – senolytics; or inhibit senescence-associated secretory phenotype – senomorphics. Natural senotherapeutics from food sources – nutritional senotherapeutics – may constitute an interesting way to achieve better age-associated outcomes through personalized nutrition. In this sense, the authors present herein a framework of nutritional senotherapeutics as an intervention targeting immunosenescence and immunometabolism, identifying research gaps in this area, and gathering information on concluded and ongoing clinical trials on this subject. Also, we present future directions and ideation for future clinical possibilities in this field.
“… 6 Despite the short time that the “Foodomics” domain exists in the scientific community, a wealth of technologies has been developed aiming to study the quality, the origin, and the safety of human nutrition. 7 An intriguing challenge in food research is the validity of food labels, especially on products designated as Protected Designation of Origin or Protected Geographical Indication (PGI), according to the EU geographical indications system for food quality. These food quality labels can serve as a valuable tool to protect genetic resources, to support sustainable rural development, and to add value to food products through differentiation based on their organoleptic properties and traditional “know-how” practices.…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.