Skip to content
DraconiticResearch
Search Sources API
190,869 studies31 sourcesUpdated 6 min ago
Peer-reviewedCC BYPLoS Computational Biology

Fung-AI: An AI/ML-driven pipeline for antifungal peptide discovery

  • Daniel Berman1
  • Elizabeth A. Lewis1
  • Tom D. Curtis1
  • Olivia N. Tiburzi1
  • Daniel F. Q. Smith2
  • Arturo Casadevall2
  • Laura J. Dunphy1
  1. 1Johns Hopkins Applied Physics Laboratory, Laurel, Maryland, United States of America
  2. 2W. Harry Feinstone Department of Molecular Microbiology and Immunology, Bloomberg School of Public Health, The Johns Hopkins University, Baltimore, Maryland, United States of America
Open at sourcePDFDOICite

Abstract

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 (LC50 > 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.

Related

  1. XAMPGen: An Interpretable SI Pipeline For Novel Antimicrobial Peptide Discovery
    K. Mondal, S. Padi, N. Kaur +6
    bioRxivPreprintCC BYFull textBioinformatics & computational biologybioRxiv
  2. MSIPep: A pipeline for immunogenic peptide identification and prioritization integrating immunopeptidomics and transcriptomics data
    Peng Liu, Siwen Zhang, Manman Lu +6
    BMC GenomicsPeer-reviewedCC BY-NC-ND 4.0Genetics & genomicsCrossref
  3. Integrated Approach for the Discovery of Antifungal and Antibiofilm Agents From Cerrado Plants
    Lorena C. Albernaz, Amanda M. Almeida, Laís S. Morais +5
    Chemistry and BiodiversityPeer-reviewedCC BY 4.0Full textMicrobiologyMedicinal chemistry & drug discoveryHAL
  4. The Plant-Derived Peptide Hyde C1 Exhibits Membrane-Associated Antifungal Activity and Protects Against Systemic Candida albicans Infection.
    Atefeh Nikzad Alamshiri, Sima Sadat Seyedjavadi, Fatemeh Peyravii Ghadikolaii +1
    Infection and drug resistancePeer-reviewedCC BY-NCFull textMicrobiologyEurope PMCPMC
  5. iAMP-deep: an alignment-free AI framework for insect antimicrobial peptide discovery
    Prakash Kolanchi, Murugan Marimuthu, Srinivasan Thulasy +1
    BMC GenomicsPeer-reviewedCC BY 4.0Genetics & genomicsCrossref

Cite

BibTeXRIS
BibTeX
@article{berman2026fungai,
  title = {{Fung-AI: An AI/ML-driven pipeline for antifungal peptide discovery}},
  author = {Daniel Berman and Elizabeth A. Lewis and Tom D. Curtis and Olivia N. Tiburzi and Daniel F. Q. Smith and Arturo Casadevall and Laura J. Dunphy},
  journal = {PLoS Computational Biology},
  year = {2026},
  month = jun,
  doi = {10.1371/journal.pcbi.1014105},
  url = {https://doi.org/10.1371/journal.pcbi.1014105},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Fung-AI: An AI/ML-driven pipeline for antifungal peptide discovery
AU  - Daniel Berman
AU  - Elizabeth A. Lewis
AU  - Tom D. Curtis
AU  - Olivia N. Tiburzi
AU  - Daniel F. Q. Smith
AU  - Arturo Casadevall
AU  - Laura J. Dunphy
PY  - 2026
DA  - 2026/06/15
JO  - PLoS Computational Biology
DO  - 10.1371/journal.pcbi.1014105
UR  - https://doi.org/10.1371/journal.pcbi.1014105
AB  - 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 (LC50 > 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.
SN  - 1553-734X
SN  - 1553-7358
ER  -