A Structure-Informed Graph Neural Network for Short Antimicrobial Peptide Discovery and Validation
Journal of Medicinal Chemistry · 2026
DOI: 10.1021/acs.jmedchem.6c00972 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Medicinal Chemistry, 2026. Verfasst von Yuchen Hu und 6 weiteren Autor:innen. Beteiligte Einrichtung: National '111' Centre for Cellular Regulation and Molecular Pharmaceutics, Key Laboratory of Fermentation Engineering (Ministry of Education), Cooper…. Hauptthemen laut MEDLINE: Antimicrobial Peptides, Anti-Bacterial Agents, Drug Discovery. Die Arbeit nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Middle / Young aged Teachers' Research Ability Improvement Project of Guangxi Higher Education, Open Fund Project of the Hubei Provincial Key Laboratory of Industrial Microbiology.
Abstract (Originalsprache)
Short antimicrobial peptides (AMPs) are promising anti-infective agents due to their broad-spectrum antimicrobial activity, low likelihood of inducing resistance, and relative ease of synthesis and optimization. In this study, we developed GW-AMP, a residue-level graph neural network model that integrates sequence-derived descriptors with predicted structural information to facilitate the discovery of short AMPs. GW-AMP demonstrated robust and balanced classification performance in both cross-validation and an independent test set, outperforming several established AMP prediction models. Guided by model predictions, candidate peptides were selected and experimentally evaluated for antibacterial activity and hemolysis, confirming GW-AMP’s effectiveness in identifying short AMPs with favorable activity and biocompatibility. Circular dichroism analysis further indicated that secondary-structure features and amphipathic distribution are closely linked to peptide potency and selectivity. Among the validated candidates, peptide 3 exhibited potent antibacterial activity, low hemolysis, and favorable in vivo efficacy and safety, supporting its potential as a lead compound for anti-infective development.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- National '111' Centre for Cellular Regulation and Molecular Pharmaceutics, Key Laboratory of Fermentation Engineering (Ministry of Education), Cooperative Innovation Centre of Industrial Fermentation (Ministry of Educat…
- Nantong Egens Biotechnology Co., Ltd, Nantong226010, China.
- School of Pharmacy, Guangxi Medical University, Nanning530021, China.
ORCID-Profile: Yuchen Hu
Förderung
- National Natural Science Foundation of China
- Middle / Young aged Teachers' Research Ability Improvement Project of Guangxi Higher Education
- Open Fund Project of the Hubei Provincial Key Laboratory of Industrial Microbiology
- Hubei University of Technology Initiative for Leadership in Green Industrial Technology
Zitieren
APA
Hu, Y., Zhou, J., Gao, Y., Yu, L., Chen, B., Su, J., & Li, H. (2026). A Structure-Informed Graph Neural Network for Short Antimicrobial Peptide Discovery and Validation. Journal of Medicinal Chemistry. https://doi.org/10.1021/acs.jmedchem.6c00972
Vancouver
Hu Y, Zhou J, Gao Y, Yu L, Chen B, Su J, et al. A Structure-Informed Graph Neural Network for Short Antimicrobial Peptide Discovery and Validation. Journal of Medicinal Chemistry. 2026. doi:10.1021/acs.jmedchem.6c00972
BibTeX
@article{Hu2026,
author = {Hu, Yuchen and Zhou, Junchao and Gao, Yuhang and Yu, Leyan and Chen, Ban and Su, Jiangtao and Li, Hong},
title = {A Structure-Informed Graph Neural Network for Short Antimicrobial Peptide Discovery and Validation},
journal = {Journal of Medicinal Chemistry},
year = {2026},
doi = {10.1021/acs.jmedchem.6c00972}
}
EUVIMED