Related Experiment Video
Updated: Jul 12, 2026
Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions
Published on: December 1, 2020
Pred5AOP: an efficient screening of food-derived antioxidant peptides based on deep learning, molecular docking, and
Yan Zhang1, Yi He1, Shihong Li1
1Key Laboratory for Molecular Enzymology and Engineering of Ministry of Education, Edmond Fischer Cell Signaling Laboratory, College of Life Sciences, Jilin University, 2699 Qianjin Street, Changchun 130012, China.
Abstract:
Antioxidant peptides derived from dietary proteins positively impact human health due to their high activity and safety. In this study, a database of 76,343 peptides was constructed via in silico hydrolysis of 29 dietary proteins. A novel antioxidant peptide screening method, Pred5AOP, based on the MLP algorithm, identified six representative peptides: DHD, DDHR, TPNT, HYHE, NDHY, and NGDA. Experimental validation confirmed their significant antioxidant activity, including free radical scavenging and cell protection, with HYHE, DDHR, and NDHY showing exceptional effects. Molecular docking and quantum chemical analyses demonstrated strong binding affinities between these peptides and the Keap1 protein, while molecular dynamics simulations highlighted their binding mechanisms and structural stability. This study provides a new strategy for identifying antioxidant peptides from food proteins, supporting their potential use in functional foods and therapeutic applications.
