An Artificial Intelligence Characterised Functional Ingredient, Derived from Rice, Inhibits TNF-α and Significantly Improves Physical Strength in an Inflammaging Population

Abstract

Food-derived bioactive peptides offer great potential for the treatment and maintenance of various health conditions, including chronic inflammation. Using in vitro testing in human macrophages, a rice derived functional ingredient natural peptide network (NPN) significantly reduced Tumour Necrosis Factor (TNF)-α secretion in response to lipopolysaccharides (LPS). Using artificial intelligence (AI) to characterize rice NPNs lead to the identification of seven potentially active peptides, the presence of which was confirmed by liquid chromatography tandem mass spectrometry (LC-MS/MS). Characterization of this network revealed the constituent peptides displayed anti-inflammatory properties as predicted in vitro. The rice NPN was then tested in an elderly “inflammaging” population with a view to subjectively assess symptoms of digestive discomfort through a questionnaire. While the primary subjective endpoint was not achieved, analysis of objectively measured physiological and physical secondary readouts showed clear significant benefits on the ability to carry out physical challenges such as a chair stand test that correlated with a decrease in blood circulating TNF-α. Importantly, the changes observed were without additional exercise or specific dietary alterations. Further health benefits were reported such as significant improvement in glucose control, a decrease in serum LDL concentration, and an increase in HDL concentration; however, this was compliance dependent. Here we provide in vitro and human efficacy data for a safe immunomodulatory functional ingredient characterized by AI.

Discovery through Machine Learning and Preclinical Validation of Novel Anti-Diabetic Peptides

“…Using a machine learning approach similar to Kennedy et al, 2020 [ 33 ], one hundred peptide candidates were predicted as potentially possessing anti-diabetic functionality via blood glucose regulatory activity. This set of peptides was further refined using a collection of tools to filter out the sequences with undesirable physiochemical properties.…”

“…A similar predictive model to that used by Kennedy et al, 2020 [ 33 ] was utilised here; briefly, the model was developed using an ensemble of neural networks. To build the training set for the model, we used structured data from public databases (bioactivity annotations, biological pathways and structural annotations) and unstructured data extracted from peer-reviewed scientific papers and patents ( Figure 1 ).…”

“…Across the multiple iterations, in vitro activity was measured in 74% of cases, where peptides tested in glucose regulation assays would show what was internally classified as “medium to high activity”. A similar active learning paradigm was used in Kennedy et al, 2020 [ 33 ]. In that case, a lower ratio of in vitro activity was measured across the multiple lab tests, with only 40% of peptides tested in extra cellular matrix development assays displaying “medium to high activity”.…”

“…When considering peptides, deciphering scale and complexity becomes a major hurdle; for example, proteins can be broken down into peptides at a rate of 36 million per minute [ 21 ]. However, Artificial Intelligence (AI) and deep learning techniques are perfectly primed to extract previously indecipherable knowledge from disparate biological data streams; as such, machine learning is increasingly seen as a discovery tool in life science, with bioactive peptides being successfully predicted in the areas of inflammation and skin aging [ 31 , 32 , 33 , 34 ]. Here, similar machine learning methods were employed to identify a short linear novel peptide therapeutics for use in T2DM.…”

Characterising the efficacy and bioavailability of bioactive peptides identified for attenuating muscle atrophy within a Vicia faba-derived functional ingredient

“…Interestingly, machine learning methods have been also proposed for not just discovery of novel molecules but also the prediction of properties that are of crucial interest in discovery pipelines, such us cell penetrability ( Manavalan et al., 2018b ) or toxicity ( Gupta et al., 2013 ). Despite these advances, functional ingredient discovery using AI has only recently been described successfully, where a machine learning approach was shown to be capable of predicting a characterised bioactive functional ingredient sourced from the Oryza sativa proteome which effectively modulated circulating cytokines and improved physical performance in human ( Rein et al., 2019 ; Kennedy et al., 2020a ). Additionally, a similar approach identified two peptides within the Pisum sativum proteome with significant anti-aging properties ( Kennedy et al., 2020b , 2020c ).…”