The intersection of Artificial Intelligence (AI) and food science has opened new frontiers in understanding the “dark matter” of food, the vast array of unidentified bioactive compounds that influence human health. This narrative review examines how AI, particularly machine learning and deep learning, is revolutionizing the discovery, characterization, and application of bioactive peptides and amino acids derived from food sources, both plant- and animal-based. These compounds exhibit diverse health benefits, including antioxidant, anti-inflammatory, antihypertensive, and antimicrobial properties, yet their complexity and the limitations of traditional methods have hindered comprehensive study. AI-driven approaches, such as predictive modeling, molecular dynamics simulations, and natural language processing, are accelerating the identification of bioactive peptides, optimizing extraction processes, and enabling personalized nutrition strategies. The integration of AI with omics technologies (e.g., nutrigenomics, proteomics) further enhances our understanding of how these peptides modulate physiological pathways. However, this is not without challenges and limitations, such as data quality, model interpretability, and persistent gaps in interdisciplinary collaboration. Additionally, the review highlights the lack of standardized databases and concerns about the use of AI, including the need for ethical approvals and protocols aligned with privacy laws, particularly in the context of personalized nutrition guidance. This review synthesizes current advancements, identifies research gaps, and underscores the transformative potential of AI in functional food development and precision nutrition. By addressing these challenges, AI can unlock the full therapeutic potential of food-derived bioactive compounds, providing innovative solutions to global health challenges such as non-communicable diseases. The findings advocate for robust interdisciplinary efforts to bridge computational and nutritional sciences, paving the way for scalable, evidence-based applications in health and wellness.

India, the world’s leading rice exporter, banned the export of non-Basmati white rice, accounting for 25% of its total exports (or 10% of the global rice trade). The ban aims to ensure availability to domestic Indian consumers and reduce domestic market prices, impacting global rice market accessibility, consumers, and producers across twelve regions. The study utilized the global simulation model (GSIM) to analyze the effects of trade restrictions on industries. The model uses national product differentiation to assess trade policy changes at global, regional, or national scales. It examined importer and exporter effects on trade values, tariff revenues, exporter surplus, and importer surplus. It found that India’s Voluntary Export Restraint (VER) ban on non-Basmati rice resulted in a higher local price and a negative global net welfare impact of USD 1.7 billion. The losses decreased to USD 1.4 billion when importing countries responded by reducing rice import tariffs by 25% and USD 1.1 billion when importing countries reduced tariffs by 75%. Sub-Saharan Africa, the Middle East, North Africa, and the Gulf Cooperation Council regions were most affected. The study also found minimal impact on consumer surplus in India due to inelastic rice demand.

Middle East Respiratory Syndrome (MERS-CoV) is a coronavirus-caused viral respiratory infection initially detected in Saudi Arabia in 2012. In UAE, high seroprevalence (97.1) of MERS-CoV in camels was reported in several Emirate of Abu Dhabi studies, including camels in zoos, public escorts, and slaughterhouses. The objectives of this research include simulation of MERS-CoV spread using a customized animal disease spread model (i.e., customized stochastic model for the UAE; analyzing the MERS-CoV spread and prevalence based on camels age groups and identifying the optimum control MERS-CoV strategy. This study found that controlling animal mobility is the best management technique for minimizing epidemic length and the number of affected farms. This study also found that disease dissemination differs amongst camels of three ages: camel kids under the age of one, young camels aged one to four, and adult camels aged four and up; because of their immunological state, kids, as well as adults, had greater infection rates. To save immunization costs, it is advised that certain age groups be targeted and that intense ad hoc unexpected vaccinations be avoided. According to the study, choosing the best technique must consider both efficacy and cost.

Highly Pathogenic Avian Influenza (HPAI) is a highly contagious, transboundary disease that can affect animals and humans, posing significant health risks to both. This study aimed to prepare for a potential outbreak by modelling the spread of HPAI using stochastic methods with the customized North American Animal Disease Spread Model (NAADSM) software ^© , which was tailored specifically for the UAE. Information from 46 commercial poultry farms, including parents, broilers, and layers, was used. This investigation simulated one baseline scenario without intervention and three disease control methods. The scenarios are baseline (without any disease-spread intervention; scenario 1), movement control strategy (scenario 2), intensive vaccination strategy (scenario 3), and depopulation of poultry farms (scenario 4). The model generated outputs on the number of farms and the number of birds infected, vaccinated, or depopulated, as well as the duration of the disease outbreak. The results indicated that the depopulation strategy, scenario 4, led to the lowest epidemic impact and the shortest outbreak duration (16 days), compared with scenarios 1, 2, and 3, which had outbreak durations of 26, 32, and 31 days, respectively. The results of this study help decision-makers determine the optimal control strategy to combat HPAI. Such a strategy minimizes the consequences of the disease spread and the associated implementation costs.