Designing Dietary Recommendations Using System Level Interactomics Analysis and Network-Based Inference

Revealing Comprehensive Food Functionalities and Mechanisms of Action through Machine Learning

Foods possess a range of unexplored functionalities; however, fully identifying these functions through empirical means presents significant challenges. In this study, we have proposed an in silico approach to comprehensively predict the functionalities of foods, encompassing even processed foods. This prediction is accomplished through the utilization of machine learning on biomedical big data. Our focus revolves around disease-related protein pathways, wherein we statistically evaluate how the constituent compounds collaboratively regulate these pathways. The proposed method has been employed across 876 foods and 83 diseases, leading to an extensive revelation of both food functionalities and their underlying operational mechanisms. Additionally, this approach identifies food combinations that potentially affect molecular pathways based on interrelationships between food functions within disease-related pathways. Our proposed method holds potential for advancing preventive healthcare.

Eat4Genes: a bioinformatic rational gene targeting app and prototype model for improving human health

Introduction and aims

Dietary Rational Gene Targeting (DRGT) is a therapeutic dietary strategy that uses healthy dietary agents to modulate the expression of disease-causing genes back toward the normal. Here we use the DRGT approach to (1) identify human studies assessing gene expression after ingestion of healthy dietary agents with an emphasis on whole foods, and (2) use this data to construct an online dietary guide app prototype toward eventually aiding patients, healthcare providers, community and researchers in treating and preventing numerous health conditions.

Methods

We used the keywords "human", "gene expression" and separately, 51 different dietary agents with reported health benefits to search GEO, PubMed, Google Scholar, Clinical trials, Cochrane library, and EMBL-EBI databases for related studies. Studies meeting qualifying criteria were assessed for gene modulations. The R-Shiny platform was utilized to construct an interactive app called "Eat4Genes".

Results

Fifty-one human ingestion studies (37 whole food related) and 96 key risk genes were identified. Human gene expression studies were found for 18 of 41 searched whole foods or extracts. App construction included the option to select either specific conditions/diseases or genes followed by food guide suggestions, key target genes, data sources and links, dietary suggestion rankings, bar chart or bubble chart visualization, optional full report, and nutrient categories. We also present user scenarios from physician and researcher perspectives.

Conclusion

In conclusion, an interactive dietary guide app prototype has been constructed as a first step towards eventually translating our DRGT strategy into an innovative, low-cost, healthy, and readily translatable public resource to improve health.

Predicting anticancer hyperfoods with graph convolutional networks

Background

Recent efforts in the field of nutritional science have allowed the discovery of disease-beating molecules within foods based on the commonality of bioactive food molecules to FDA-approved drugs. The pioneering work in this field used an unsupervised network propagation algorithm to learn the systemic-wide effect on the human interactome of 1962 FDA-approved drugs and a supervised algorithm to predict anticancer therapeutics using the learned representations. Then, a set of bioactive molecules within foods was fed into the model, which predicted molecules with cancer-beating potential.The employed methodology consisted of disjoint unsupervised feature generation and classification tasks, which can result in sub-optimal learned drug representations with respect to the classification task. Additionally, due to the disjoint nature of the tasks, the employed approach proved cumbersome to optimize, requiring testing of thousands of hyperparameter combinations and significant computational resources.To overcome the technical limitations highlighted above, we represent each drug as a graph (human interactome) with its targets as binary node features on the graph and formulate the problem as a graph classification task. To solve this task, inspired by the success of graph neural networks in graph classification problems, we use an end-to-end graph neural network model operating directly on the graphs, which learns drug representations to optimize model performance in the prediction of anticancer therapeutics.

Results

The proposed model outperforms the baseline approach in the anticancer therapeutic prediction task, achieving an F1 score of 67.99%±2.52% and an AUPR of 73.91%±3.49%. It is also shown that the model is able to capture knowledge of biological pathways to predict anticancer molecules based on the molecules’ effects on cancer-related pathways.

Conclusions

We introduce an end-to-end graph convolutional model to predict cancer-beating molecules within food. The introduced model outperforms the existing baseline approach, and shows interpretability, paving the way to the future of a personalized nutritional science approach allowing the development of nutrition strategies for cancer prevention and/or therapeutics.

Supplementary Information

The online version contains supplementary material available at (10.1186/s40246-021-00333-4).

NutriGenomeDB: a nutrigenomics exploratory and analytical platform

Habitual consumption of certain foods has shown beneficial and protective effects against multiple chronic diseases. However, it is not clear by which molecular mechanisms they may exert their beneficial effects. Multiple -omic experiments available in public databases have generated gene expression data following the treatment of human cells with different food nutrients and bioactive compounds. Exploration of such data in an integrative manner offers excellent possibilities for gaining insights into the molecular effects of food compounds and bioactive molecules at the cellular level. Here we present NutriGenomeDB, a web-based application that hosts manually curated gene sets defined from gene expression signatures, after differential expression analysis of nutrigenomics experiments performed on human cells available in the Gene Expression Omnibus (GEO) repository. Through its web interface, users can explore gene expression data with interactive visualizations. In addition, external gene signatures can be connected with nutrigenomics gene sets using a gene pattern-matching algorithm. We further demonstrate how the application can capture the primary molecular mechanisms of a drug used to treat hypertension and thus connect its mode of action with hosted food compounds.

Molecular annotation of food - towards personalized diet and precision health

Background

Personalized diet requires matching human genotypic and phenotypic features to foods that increase the chance of achieving a desired physiological health outcome. New insights and technologies will help to decipher the intricacies of diet-health relationships and create opportunities for breakthroughs in dietary interventions for personal health management.

Scope and Approach

This article describes the scientific progress towards personalized diet and points out the need for integrating high-quality data on food. A framework for molecular annotation of food is presented, focusing on what aspects should be measured and how these measures relate to health. Strategies of applying trending technologies to improve personalized diet and health are discussed, highlighting challenges and opportunities for transforming data into insights and actions.

Key Findings and Conclusions

The goal of personalized diet is to enable individuals and caregivers to make informed dietary decisions for targeted health management. Achieving this goal requires a better understanding of how molecular properties of food influence individual eating behavior and health outcomes. Annotating food at a molecular level encompasses characterizing its chemical composition and modifications, physicochemical structure, and biological properties. Features of molecular properties in the food annotation framework are applicable to varied conditions and processes from raw materials to meals. Applications of trending technologies, such as omics techniques, wearable biosensors, and artificial intelligence, will support data collection, data analytics, and personalized dietary actions for targeted health management.

HyperFoods: Machine intelligent mapping of cancer-beating molecules in foods

Recent data indicate that up-to 30–40% of cancers can be prevented by dietary and lifestyle measures alone. Herein, we introduce a unique network-based machine learning platform to identify putative food-based cancer-beating molecules. These have been identified through their molecular biological network commonality with clinically approved anti-cancer therapies. A machine-learning algorithm of random walks on graphs (operating within the supercomputing DreamLab platform) was used to simulate drug actions on human interactome networks to obtain genome-wide activity profiles of 1962 approved drugs (199 of which were classified as “anti-cancer” with their primary indications). A supervised approach was employed to predict cancer-beating molecules using these ‘learned’ interactome activity profiles. The validated model performance predicted anti-cancer therapeutics with classification accuracy of 84–90%. A comprehensive database of 7962 bioactive molecules within foods was fed into the model, which predicted 110 cancer-beating molecules (defined by anti-cancer drug likeness threshold of >70%) with expected capacity comparable to clinically approved anti-cancer drugs from a variety of chemical classes including flavonoids, terpenoids, and polyphenols. This in turn was used to construct a ‘food map’ with anti-cancer potential of each ingredient defined by the number of cancer-beating molecules found therein. Our analysis underpins the design of next-generation cancer preventative and therapeutic nutrition strategies.

Paving the Way to Precision Nutrition Through Metabolomics

Nutrition is an interdisciplinary science that studies the interactions of nutrients with the body in relation to maintenance of health and well-being. Nutrition is highly complex due to the underlying various internal and external factors that could model it. Thus, hacking this complexity requires more holistic and network-based strategies that could unveil these dynamic system interactions at both time and space scales. The ongoing omics era with its high-throughput molecular data generation is paving the way to embrace this complexity and is deeply reshaping the whole field of nutrition. Understanding the future paths of nutrition science is of importance from both translational and clinical perspectives. Basic nutrients which might include metabolites are important in nutrition science. Moreover, metabolites are key biological communication channels and represent an appealing functional readout at the interface of different major influential factors that define health and disease. Metabolomics is the technology that enables holistic and systematic analyses of metabolites in a biological system. Hence, given its intrinsic functionality, its tight connection to metabolism and its high clinical actionability potential, metabolomics is a very appealing technology for nutrition science. The ultimate goal is to deliver a tailored and clinically relevant nutritional recommendations and interventions to achieve precision nutrition. This work intends to present an update on the applications of metabolomics to personalize nutrition in translational and clinical settings. It also discusses the current conceptual shifts that are remodeling clinical nutrition practices in this Precision Medicine era. Finally, perspectives of clinical nutrition in the ever-growing, data-driven healthcare landscape are presented.

Free Accessible Databases as a Source of Information about Food Components and Other Compounds with Anticancer Activity⁻Brief Review

Diet is considered to be a significant factor in cancer prevention and therapy. Many food components reveal anticancer activity. The increasing number of experiments concerning the anticancer potential of chemical compounds, including food components, is a challenge for data searching. Specialized databases provide an opportunity to overcome this problem. Data concerning the anticancer activity of chemical compounds may be found in general databases of chemical compounds and databases of drugs, including specialized resources concerning anticancer compounds, databases of food components, and databases of individual groups of compounds, such as polyphenols or peptides. This brief review summarizes the state of knowledge of chemical databases containing information concerning natural anticancer compounds (e.g., from food). Additionally, the information about text- and structure-based search options and links between particular internet resources is provided in this paper. Examples of the application of databases in food and nutrition sciences are also presented with special attention to compounds that are interesting from the point of view of dietary cancer prevention. Simple examples of potential database search possibilities are also discussed.

Biological Activities, Health Benefits, and Therapeutic Properties of Avenanthramides: From Skin Protection to Prevention and Treatment of Cerebrovascular Diseases

Oat (Avena sativa) is a cereal known since antiquity as a useful grain with abundant nutritional and health benefits. It contains distinct molecular components with high antioxidant activity, such as tocopherols, tocotrienols, and flavanoids. In addition, it is a unique source of avenanthramides, phenolic amides containing anthranilic acid and hydroxycinnamic acid moieties, and endowed with major beneficial health properties because of their antioxidant, anti-inflammatory, and antiproliferative effects. In this review, we report on the biological activities of avenanthramides and their derivatives, including analogs produced in recombinant yeast, with a major focus on the therapeutic potential of these secondary metabolites in the treatment of aging-related human diseases. Moreover, we also present recent advances pointing to avenanthramides as interesting therapeutic candidates for the treatment of cerebral cavernous malformation (CCM) disease, a major cerebrovascular disorder affecting up to 0.5% of the human population. Finally, we highlight the potential of foodomics and redox proteomics approaches in outlining distinctive molecular pathways and redox protein modifications associated with avenanthramide bioactivities in promoting human health and contrasting the onset and progression of various pathologies. The paper is dedicated to the memory of Adelia Frison.

Foodomics for human health: current status and perspectives

INTRODUCTION

In the post-genomic era, the opportunity to combine and integrate cutting-edge analytical platforms and data processing systems allowed the birth of foodomics, 'a discipline that studies the Food and Nutrition domains through the application of advanced omics technologies to improve consumer's well-being, health, and confidence'. Since then, this discipline has rapidly evolved and researchers are now facing the daunting tasks to meet consumers' needs in terms of food traceability, sustainability, quality, safety and integrity. Most importantly, today it is imperative to provide solid evidence of the mechanisms through which food can promote human health and well-being. Areas covered: In this review, the complex relationships connecting food, nutrition and human health will be discussed, with emphasis on the relapses for the development of functional foods and nutraceuticals, personalized nutrition approaches, and the study of the interplay among gut microbiota, diet and health/diseases. Expert commentary: Evidence has been provided supporting the role of various omic platforms in studying the health-promoting effects of food and customized dietary interventions. However, although associated to major analytical challenges, only the proper integration of multi-omics studies and the implementation of bioinformatics tools and databases will help translate findings from clinical practice into effective personalized treatment strategies.