An Artificial-Intelligence-Discovered Functional Ingredient, NRT_N0G5IJ, Derived from Pisum sativum, Decreases HbA1c in a Prediabetic Population

Abstract

The prevalence of prediabetes is rapidly increasing, and this can lead to an increased risk for individuals to develop type 2 diabetes and associated diseases. Therefore, it is necessary to develop nutritional strategies to maintain healthy glucose levels and prevent glucose metabolism dysregulation in the general population. Functional ingredients offer great potential for the prevention of various health conditions, including blood glucose regulation, in a cost-effective manner. Using an artificial intelligence (AI) approach, a functional ingredient, NRT_N0G5IJ, was predicted and produced from Pisum sativum (pea) protein by hydrolysis and then validated. Treatment of human skeletal muscle cells with NRT_N0G5IJ significantly increased glucose uptake, indicating efficacy of this ingredient in vitro. When db/db diabetic mice were treated with NRT_N0G5IJ, we observed a significant reduction in glycated haemoglobin (HbA1c) levels and a concomitant benefit on fasting glucose. A pilot double-blinded, placebo controlled human trial in a population of healthy individuals with elevated HbA1c (5.6% to 6.4%) showed that HbA1c percentage was significantly reduced when NRT_N0G5IJ was supplemented in the diet over a 12-week period. Here, we provide evidence of an AI approach to discovery and demonstrate that a functional ingredient identified using this technology could be used as a supplement to maintain healthy glucose regulation.

How Healthy Are Non-Traditional Dietary Proteins? The Effect of Diverse Protein Foods on Biomarkers of Human Health

“…Chauhan et al (2021) investigated the consumption of AI-designed pea protein hydrolysate (15 g) for 12 weeks on the HBA1c of healthy prediabetic adults (HBA1c: 5.7 to 6.4%). The consumption of pea protein hydrolysate resulted in a significant (but small) reduction (0.12%) in the average HBA1c of the participants, whereas a placebo (containing microcrystalline cellulose, avicel ® ) or rice protein hydrolysate did not have a significant effect [ 107 ].…”

“…Although the health effects of soy proteins have been extensively investigated, only 22 human trials were identified for other legume proteins, such as pea and lupin. Pea protein was shown to reduce HbA1C in prediabetic adults [ 107 ], while a study comparing fava bean and pea protein in combination showed improved satiety compared to a high protein meat diet [ 118 ]. However, further studies using fibre-matched interventions saw no effect, suggesting the effect was likely due to non-protein components, such as fibre.…”

A comprehensive review on the glucoregulatory properties of food-derived bioactive peptides

“…Increase GLUT2 gene expression and protein content (LLP, VA, LL), decrease intracellular ROS and TNF-α (VLP, LL) Insulin resistant HepG2 cells Zhu et al (2020 ) Pea protein Alcalase and neutrase ALP, VLP, LLP, SP Reducing blood glucose levels, improving glucose tolerance, promoting insulin release and glycogen synthesis, and protecting liver and kidney structures High fat fed and streptozotocin (STZ)-induced diabetic mice Wei et al (2019 ) Pea protein Food-grade serine protease NRT_N0G5IJ (peptides between 7 and 16 amino acids, with net charge of + 1. Most peptides contained 40% hydrophobic residues) Increase glucose uptake, reduction in glycated haemoglobin (HbA1c) levels reducing fasting glucose Human skeletal muscle cells, db/db diabetic mice , and clinical (double-blinded, placebo controlled human trial) Chauhan et al (2021 ) Foxtail millet protein Raw and cooked protein isolates Not determined Hypoglycemic effects through rewiring glucose homeostasis, mitigating diabetes-induced gut dysbiosis. The cooked foxtail millet protein isolate affected the GLP-1R/PI3K/AKT pathway and reversed the weight loss trend and alleviated lipid disorders in diabetic mice STZ-induced diabetic mice Fu et al (2021 ) Wheat gluten Commercial protein hydrolysate (HyPep 4601) Not determined Suppression of food intake in healthy rats, elevating plasma PYY levels, stimulation of CCK and GLP-1 in enteroendocrine cells Enteroendocrine cell lines (STC-1 cells and GLUTag cells), and Wistar rats Chen, Hira, Nakajima, and Hara (2018 ) Walnut Neutrase and alcalase LVRL, LRYL, VLLALVLLR Improve glucose consumption, glucose uptake, and GLUT4 translocation, elevation of p-IRS-1 and p-Akt.…”

Artificial Intelligence in Functional Food Ingredient Discovery and Characterisation: A Focus on Bioactive Plant and Food Peptides

“…K.;Sharma et al, 2017;Kathy;Kennedy et al, 2020b;K. ;Kennedy et al, 2020a;Chauhan et al, 2021;Corrochano et al, 2021;Cal et al, 2020). With a focus on peptides, we argue here for complementing, if not replacing, the traditional sequence of FFI characterisation (Figure 1) with an AI-powered alternative ("benefit definition → bioactive prediction → food source identification → bioactive release → bioactive validation"; Figure 2) by placing artificial intelligence upfront in the entire process.…”

“…To untangle these networks and characterise key bioactives and functions within, an integrated peptidomics-AI platform has recently been proven to be successful by our laboratories (Corrochano et al, 2021;Casey et al, 2021;Kathy Kennedy et al, 2020b;K. Kennedy et al, 2020a;Chauhan et al, 2021). As previously discussed, mass spectrometrybased peptidomics of food protein hydrolysates is a key input to the AI platform: the process begins with LC-MS/MS-based peptidomics that identifies and quantifies peptides in their native state, as released by mild hydrolysis from parent proteins in the natural food source, which is not limited to a single type of food or plant source.…”