Integrated Machine Learning and Structure-Based Virtual Screening Identifies Natural Product Targeting 50S Ribosome Inhibitory Activity Against Cutibacterium acnes
Molecules · 16.11.2025 · 30 (22) · 4433
DOI: 10.3390/molecules30224433 ↗Kurz gefasst
Fachartikel in der Zeitschrift Molecules, online erschienen am 16.11.2025. Verfasst von Jixing Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macao 999078, China. Hauptthemen laut MEDLINE: Biological Products, Anti-Bacterial Agents, Machine Learning, Ribosomes. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Macao Polytechnic University Foundation.
Abstract (Originalsprache)
Acne vulgaris is a prevalent inflammatory disease of the pilosebaceous unit in which Cutibacterium acnes (C. acnes) contributes to lesion initiation and persistence, supporting antibacterial interventions as a component of clinical management. Given the essential role of the 50S large ribosomal subunit—particularly 23S rRNA sites in the peptidyl transferase center and nascent peptide exit tunnel—in C. acnes protein synthesis and viability, targeting the 50S offers an effective path to lead discovery for acne treatment. Here, we present an integrated computational–experimental workflow to identify anti-C. acnes candidates from a 186,659-compound natural product library. Curated 50S/23S ligands trained and validated two ML-QSAR regression models built on different molecular fingerprints (MACCS keys and PubChem 2D) to predict anti-C. acnes activity and rapidly triage the library. Compounds were further screened by ADMET filtering and structure-based docking to 23S rRNA pockets, followed by cluster and interaction analysis. Among six experimental hits, three compounds exhibited MICs against C. acnes of ≤8 μg/mL, with tripterin, a pentacyclic triterpenoid, being the most potent (0.5–2 μg/mL across two acne-relevant strains). Collectively, these results indicate that a 50S ribosomal-focused, multistage computational screening workflow, integrated with in vitro assays, efficiently prioritizes compounds with quantifiable anti-C. acnes activity across a broad range of natural products.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macao 999078, China.
- Faculty of Health Sciences and Sports, Macao Polytechnic University, Macao 999078, China.
- School of Chemical Biology and Biotechnology, Peking University Shenzhen Graduate School, Shenzhen 518055, China.
ORCID-Profile: Jixing Liu, Henry H Y Tong, Hang Zheng, Miriam Iun Fan Lei, Shu Li
Förderung
- Macao Polytechnic University Foundation
Zitieren
APA
Liu, J., Tong, H. H. Y., Zheng, H., Lei, M. I. F., & Li, S. (2025). Integrated Machine Learning and Structure-Based Virtual Screening Identifies Natural Product Targeting 50S Ribosome Inhibitory Activity Against Cutibacterium acnes. Molecules, 30(22), 4433. https://doi.org/10.3390/molecules30224433
Vancouver
Liu J, Tong HHY, Zheng H, Lei MIF, Li S. Integrated Machine Learning and Structure-Based Virtual Screening Identifies Natural Product Targeting 50S Ribosome Inhibitory Activity Against Cutibacterium acnes. Molecules. 2025;30(22):4433. doi:10.3390/molecules30224433
BibTeX
@article{Liu2025,
author = {Liu, Jixing and Tong, Henry H Y and Zheng, Hang and Lei, Miriam Iun Fan and Li, Shu},
title = {Integrated Machine Learning and Structure-Based Virtual Screening Identifies Natural Product Targeting 50S Ribosome Inhibitory Activity Against Cutibacterium acnes},
journal = {Molecules},
year = {2025},
volume = {30},
number = {22},
pages = {4433},
doi = {10.3390/molecules30224433}
}
EUVIMED