The Computational Diet: A Review of Computational Methods Across Diet, Microbiome, and Health

Abstract

Food and human health are inextricably linked. As such, revolutionary impacts on health have been derived from advances in the production and distribution of food relating to food safety and fortification with micronutrients. During the past two decades, it has become apparent that the human microbiome has the potential to modulate health, including in ways that may be related to diet and the composition of specific foods. Despite the excitement and potential surrounding this area, the complexity of the gut microbiome, the chemical composition of food, and their interplay in situ remains a daunting task to fully understand. However, recent advances in high-throughput sequencing, metabolomics profiling, compositional analysis of food, and the emergence of electronic health records provide new sources of data that can contribute to addressing this challenge. Computational science will play an essential role in this effort as it will provide the foundation to integrate these data layers and derive insights capable of revealing and understanding the complex interactions between diet, gut microbiome, and health. Here, we review the current knowledge on diet-health-gut microbiota, relevant data sources, bioinformatics tools, machine learning capabilities, as well as the intellectual property and legislative regulatory landscape. We provide guidance on employing machine learning and data analytics, identify gaps in current methods, and describe new scenarios to be unlocked in the next few years in the context of current knowledge.

Keywords: artificial intelligence; data analytics; gut microbiome; machine learning; microbiota; nutrition.

FIGURE 1

The vision for the next nutrition revolution involves microbiome-aware dietary planning and manufacturing. First, DGMH data is collected, homogenized, and stored, with any new user data integrated as part of a cohesive compendium. Then, DGMH data are analyzed (data analytics) to identify the functional characteristics and target microbiota, personalized to the individual and the desired phenotype. This includes data processing followed by supervised and unsupervised learning using a user profile compendium. Bioinformatic tools are used during data processing to extract meaningful information from raw high-throughput data such as metagenomic sequence reads. Then, the recommendation system provides dietary recommendations to help achieve target microbiota. This includes the integration of user profiles in a compendium along with nutrition DB proceeded by data processing then content-based and collaborative filtering. Finally, diet engineering is performed to create dietary products for the user. This includes the design of prebiotics, probiotics, synbiotics, manufactured food, and detailed dietary planning. In practice, taste and flavor of dietary products is very important to help users commit to any given diet, therefore sensory analysis should inform all dietary engineering efforts.

FIGURE 2

Factors affecting the gut microbiota. A summary of human gut microbiome taxonomy at the family level and the corresponding modulating factors.

FIGURE 3

Illustration of data processing, data analytics, and recommendation systems. Data processing generates diverse types of information with different levels of resolution and dimensionality. Such information needs to be transformed and integrated across all users for building a compendium. Next, data analytics methods are used to discover the characteristics of target microbiota prescribed for individuals to achieve their health objectives. Finally, recommendation system methods use the compendium to find the dietary recommendations for helping individuals achieve the target microbiota.

FIGURE 4

Examples of microbiome-aware diet recommendation pipelines for scenarios (A–D).