Classifier-driven generative adversarial networks for enhanced antimicrobial peptide design
Briefings in Bioinformatics · 31.08.2025 · 26 (5)
DOI: 10.1093/bib/bbaf500 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 25.10.2025. Verfasst von Michaela Areti Zervou und 3 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science Department, University of Crete, University Campus, Voutes, 715 00, Heraklion, Greece. Hauptthemen laut MEDLINE: Antimicrobial Peptides, Drug Design, Neural Networks, Computer. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: TITAN ERA Chair project, Horizon Europe Framework Program of the European Commission and the Hellenic Foundation for Research and Innovation.
Abstract (Originalsprache)
The development of antimicrobial peptides (AMPs) presents a promising approach to addressing antibiotic-resistant pathogens. Computational methods, such as Feedback Generative Adversarial Networks (FBGANs), have demonstrated strong performance in optimizing AMP design. FBGAN operates as a classifier-guided Generative Adversarial Network (GAN), refining training data by replacing them with the classifier’s most accurate predictions based on a predefined threshold. However, this method may introduce bias and constrain the diversity and quality of the generated peptides. To address these limitations, we propose a novel classifier-driven GAN (cdGAN) framework that seamlessly integrates classifier predictions into the generative model’s loss function. This enables an adaptive, end-to-end learning process that enhances AMP generation without requiring explicit data modifications. By embedding classifier guidance within the loss computation, cdGAN dynamically optimizes both peptide diversity and functionality. Comparative studies indicate that cdGAN outperforms conventional guided-GAN architectures, such as Conditional GANs and Auxiliary Classifier GANs, while achieving performance comparable to or exceeding established AMP design methods. Additionally, cdGAN’s flexible architecture allows for the simultaneous optimization of multiple peptide attributes. To demonstrate this capability, we introduce a multi-task classifier based on the Evolutionary Scale Modeling 2 (ESM2) model, enabling cdGAN to assess both antimicrobial activity and peptide structural properties in parallel. This enhancement improves the likelihood of generating viable therapeutic candidates with enhanced antimicrobial effectiveness and reduced toxicity.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Computer Science Department, University of Crete, University Campus, Voutes, 715 00, Heraklion, Greece.
- Institute of Computer Science, Foundation for Research and Technology-Hellas, Nikolaou Plastira 100, 700 13, Heraklion, Greece.
- Institute of Applied and Computational Mathematics, Foundation for Research and Technology-Hellas, Nikolaou Plastira 100, 700 13, Heraklion, Greece.
ORCID-Profile: Michaela Areti Zervou, Effrosyni Doutsi, Yannis Pantazis, Panagiotis Tsakalides
Förderung
- TITAN ERA Chair project
- Horizon Europe Framework Program of the European Commission and the Hellenic Foundation for Research and Innovation
Zitieren
APA
Zervou, M. A., Doutsi, E., Pantazis, Y., & Tsakalides, P. (2025). Classifier-driven generative adversarial networks for enhanced antimicrobial peptide design. Briefings in Bioinformatics, 26(5). https://doi.org/10.1093/bib/bbaf500
Vancouver
Zervou MA, Doutsi E, Pantazis Y, Tsakalides P. Classifier-driven generative adversarial networks for enhanced antimicrobial peptide design. Briefings in Bioinformatics. 2025;26(5). doi:10.1093/bib/bbaf500
BibTeX
@article{Zervou2025,
author = {Zervou, Michaela Areti and Doutsi, Effrosyni and Pantazis, Yannis and Tsakalides, Panagiotis},
title = {Classifier-driven generative adversarial networks for enhanced antimicrobial peptide design},
journal = {Briefings in Bioinformatics},
year = {2025},
volume = {26},
number = {5},
doi = {10.1093/bib/bbaf500}
}
EUVIMED