EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Painting Peptides With Antimicrobial Potency Through Deep Reinforcement Learning

Ruihan Dong, Qiushi Cao, Chen Song iD

Advanced Science · 2025-11 · 12 (43)

DOI: 10.1002/advs.202506332 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 12.09.2025. Verfasst von Ruihan Dong und 2 weiteren Autor:innen. Beteiligte Einrichtung: Center for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, 100871, China. Hauptthemen laut MEDLINE: Antimicrobial Peptides, Deep Learning, Anti-Bacterial Agents, Anti-Infective Agents. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, Innovative Research Group Project of the National Natural Science Foundation of China, Frontier Innovation Fund of Peking University Chengdu Academy for Advanced Interdisciplinary Biotechnologies.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the post‐antibiotic era, antimicrobial peptides (AMPs) are considered ideal drug candidates because of their lower likelihood of inducing resistance. Computational models provide an efficient way to design novel AMPs. However, current optimization and generation approaches are tailored for specific application scenarios, which hinders the ease of use. To address this challenge, a novel AMP design model named AMPainter is proposed. Based on deep reinforcement learning, AMPainter integrates optimization and generation tasks in a unified framework. AMPainter is applied to three types of peptides, including known AMPs, signal peptides (SPs), and random sequences. AMPainter outperforms ten related models in enhancing the activity of known AMPs on the predicted antimicrobial potency and diversity. Several AMPs demonstrate a 128‐fold decrease in their actual minimal inhibitory concentrations (MICs). AMPainter evolves effective AMPs from membrane‐active SPs with an experimental success rate of 80%. In terms of generation, de novo designed AMP from an inactive random sequence achieves an average MIC of 2.88 µM against four bacteria. In vitro MICs of peptides along the virtual evolutionary path match the predicted scores. Therefore, AMPainter can significantly improve the antimicrobial potency of various peptides, expand the AMP sequence space, and discover novel antimicrobial agents.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Antimicrobial PeptidesDeep LearningAnti-Bacterial AgentsAnti-Infective AgentsMicrobial Sensitivity TestsDrug DesignBacteriaReinforcement Machine Learning

Stichwörter der Autor:innen

antimicrobial peptidedeep reinforcement learningdirected evolutionsequence design

Substanzen

Antimicrobial PeptidesAnti-Bacterial AgentsAnti-Infective Agents

Autor:innen und Institutionen

  • Center for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, 100871, China.
  • Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, 100871, China.
  • Peking University-Tsinghua University-National Institute of Biological Sciences Joint Graduate Program, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, 100871, China.

ORCID-Profile: Chen Song

Förderung

  • National Key R&D Program of China
  • Innovative Research Group Project of the National Natural Science Foundation of China
  • Frontier Innovation Fund of Peking University Chengdu Academy for Advanced Interdisciplinary Biotechnologies
  • National Key Research and Development Program of China

Zitieren

APA

Dong, R., Cao, Q., & Song, C. (2025). Painting Peptides With Antimicrobial Potency Through Deep Reinforcement Learning. Advanced Science, 12(43). https://doi.org/10.1002/advs.202506332

Vancouver

Dong R, Cao Q, Song C. Painting Peptides With Antimicrobial Potency Through Deep Reinforcement Learning. Advanced Science. 2025;12(43). doi:10.1002/advs.202506332

BibTeX
@article{Dong2025,
  author = {Dong, Ruihan and Cao, Qiushi and Song, Chen},
  title = {Painting Peptides With Antimicrobial Potency Through Deep Reinforcement Learning},
  journal = {Advanced Science},
  year = {2025},
  volume = {12},
  number = {43},
  doi = {10.1002/advs.202506332}
}
Kostenlos starten →