Machine learning discovery of novel antihypertensive peptides from highland barley protein inhibiting angiotensin I-converting enzyme (ACE).
Journal:
Food research international (Ottawa, Ont.)
PMID:
39967093
Abstract
Hypertension is a major global health concern, and there is a need for new antihypertensive agents derived from natural sources. This study aims to identify novel angiotensin I-converting enzyme (ACE) inhibitors from bioactive peptides derived from food sources, particularly highland barley proteins, addressing the gap in effective natural ACE inhibitors. This research employs a machine learning-based pipeline combined with peptidomics to screen for ACE-inhibitory peptides, Gradient Boosted Decision Trees (GBDT) with the best performance among four tested models was used to predict the ACE-inhibitory capacity of peptides derived from papain-hydrolyzed highland barley protein. The selected peptides were validated through computer simulations and in vitro experiments, with FPRPFL identified as the most potent ACE-inhibitor (IC = 1.18 μM). Enzyme inhibition kinetics and digestion stability simulations were used to investigate its inhibition mode and stability. The binding mode and mechanism of action of FPRPFL with ACE were further analyzed using circular dichroism, molecular docking and molecular dynamics simulations. Network pharmacology revealed its multi-target and multi-pathway antihypertensive properties. The integration of machine learning and in vitro experiments enables accurate bioactive peptides identification and comprehensive their functionality analysis, establishing a valuable pipeline for elucidating peptide mechanisms and laying a solid foundation for industrial-scale production of natural ACE-inhibitors.