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

Abstract

While there have been significant advances in drug discovery for diabetes mellitus over the past couple of decades, there is an opportunity and need for improved therapies. While type 2 diabetic patients better manage their illness, many of the therapeutics in this area are peptide hormones with lengthy sequences and a molecular structure that makes them challenging and expensive to produce. Using machine learning, we present novel anti-diabetic peptides which are less than 16 amino acids in length, distinct from human signalling peptides. We validate the capacity of these peptides to stimulate glucose uptake and Glucose transporter type 4 (GLUT4) translocation in vitro. In obese insulin-resistant mice, predicted peptides significantly lower plasma glucose, reduce glycated haemoglobin and even improve hepatic steatosis when compared to treatments currently in use in a clinical setting. These unoptimised, linear peptides represent promising candidates for blood glucose regulation which require further evaluation. Further, this indicates that perhaps we have overlooked the class of natural short linear peptides, which usually come with an excellent safety profile, as therapeutic modalities.

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

“…To discover a functional ingredient with glucose-modulating activity, a predictive model was developed using a collection of neural networks. The predictive model utilised here was described by Casey et al (2021), whereby a number of validated peptides were identified with blood glucose modulation activity [ 22 ]. Briefly, neural networks models based on stacks of recurrent and dense layers were trained in fold cross-validation using a dataset of glucose-regulating peptides that was built by combining data from literature with proprietary internal data established from mass spectrometry and in vitro investigations.…”

Mass spectrometry as a lens into molecular human nutrition and health

“…21,81 Such AI-discovered, natural bioactive peptides were recently taken concept to (pre-) clinically proven solutions. 82,83,84,85 Bioactive food peptides belong to the macronutrient class of 'protein'. Although some bioactive peptides exist in their free form in various organisms such as humans, animals, plants, or microorganisms, by far most known bioactive peptides with relevance to human nutrition are 'hidden' in their 'parent proteins'.…”

“…21,81 Such AI-discovered, natural bioactive peptides were recently taken from concept to (pre-) clinically proven solutions. 82,83,84,85…”

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

“…They contain large complex networks of interacting bioactive peptides with attributable health benefits (Hernández-Ledesma et al, 2014;Nasri 2017). 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).…”