Fung-AI: An AI/ML-driven pipeline for antifungal peptide discovery
PLOS Computational Biology · 2026
DOI: 10.1371/journal.pcbi.1014105 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, 2026. Verfasst von Daniel S Berman und 6 weiteren Autor:innen. Beteiligte Einrichtung: Johns Hopkins Applied Physics Laboratory, Laurel, Maryland, United States of America. Hauptthemen laut MEDLINE: Antifungal Agents, Drug Discovery, Peptides, Artificial Intelligence. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Johns Hopkins University Applied Physics Laboratory, NIAID.
Abstract (Originalsprache)
Emerging fungal pathogens represent a concerning threat to both global health and food security. In this study, we aimed to address our rising vulnerability to fungal pathogens through the development of the Fung-AI pipeline: an AI/ML-driven approach for antifungal discovery. A generative adversarial network (GAN) was trained to generate novel candidate antifungal peptide sequences. Next, in silico antifungal and hemolytic classifiers were built to further prioritize AI-generated peptides for experimental validation. From a pool of ~10,000 candidates, thirteen peptides were selected for testing over two-stages of experimentation. Five peptides were found to display mild antifungal activity against the wheat pathogen, Fusarium graminearum , with minimal inhibitory concentrations (MICs) ranging from 250 µg/mL to 500 µg/mL. Four of the five peptides also showed activity against the human pathogen, Candida albicans (MIC: 500 µg/mL). Two of our AI-generated antifungal peptides additionally demonstrated low cytotoxicity in HepG2 human liver carcinoma cells (LC 50 > 704.2 µg/mL) indicating that they may be useful as scaffolds for future optimization for therapeutic applications. None of our peptides were found to considerably inhibit the emerging pathogen C. auris , suggesting the need for pathogen-specific down-selection of candidate peptides. Overall, we present a proof-of-principle, generative-AI-based approach for the rapid design of de novo antifungal peptides.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Johns Hopkins Applied Physics Laboratory, Laurel, Maryland, United States of America.
- W. Harry Feinstone Department of Molecular Microbiology and Immunology, Bloomberg School of Public Health, The Johns Hopkins University, Baltimore, Maryland, United States of America.
ORCID-Profile: Daniel S Berman, Libby M Lewis, Laura J Dunphy
Förderung
- The Johns Hopkins University Applied Physics Laboratory
- NIAID
Zitieren
APA
Berman, D. S., Lewis, L. M., Curtis, T. D., Tiburzi, O. N., Smith, D. F. Q., Casadevall, A., & Dunphy, L. J. (2026). Fung-AI: An AI/ML-driven pipeline for antifungal peptide discovery. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1014105
Vancouver
Berman DS, Lewis LM, Curtis TD, Tiburzi ON, Smith DFQ, Casadevall A, et al. Fung-AI: An AI/ML-driven pipeline for antifungal peptide discovery. PLOS Computational Biology. 2026. doi:10.1371/journal.pcbi.1014105
BibTeX
@article{Berman2026,
author = {Berman, Daniel S and Lewis, Libby M and Curtis, Tom D and Tiburzi, Olivia N and Smith, Daniel F Q and Casadevall, Arturo and Dunphy, Laura J},
title = {Fung-AI: An AI/ML-driven pipeline for antifungal peptide discovery},
journal = {PLOS Computational Biology},
year = {2026},
doi = {10.1371/journal.pcbi.1014105}
}
EUVIMED