EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

AI-guided discovery and optimization of antimicrobial peptides through species-aware language model

Daehun Bae, Minsang Kim, Jiwon Seo, Hojung Nam iD

Briefings in Bioinformatics · 02.07.2025 · 26 (4)

DOI: 10.1093/bib/bbaf343 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 18.07.2025. Verfasst von Daehun Bae und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Buk-gu, Gwangju 61005, Republic of Kor…. Hauptthemen laut MEDLINE: Antimicrobial Peptides, Anti-Bacterial Agents, Drug Discovery, Antimicrobial Cationic Peptides. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Gwangju Institute of Science and Technology, National Research Foundation of Korea, Korea Machine Learning Ledger Orchestration for Drug Discovery Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rise of antibiotic-resistant bacteria drives an urgent need for novel antimicrobial agents. Antimicrobial peptides (AMPs) show promise solutions due to their multiple mechanisms of action and reduced propensity for resistance development. This study introduces LLAMP (Large Language model for AMP activity prediction), a target species-aware AI model that leverages pre-trained language models to predict minimum inhibitory concentration values of AMPs. Using LLAMP, we screened approximately 5.5 million peptide sequences, identifying peptides 13 and 16 as the most selective and most potent candidates, respectively. Analysis of attention values allowed us to pinpoint critical amino acid residues (e.g., Trp, Lys, and Phe). Using the critical amino acids, the sequence of the most selective peptide 13 was engineered to increase amphipathicity through targeted modifications, yielding peptide 13–5 with an overall enhancement in antimicrobial activity but a reduction in selectively. Notably, peptides 13–5 and 16 demonstrated antimicrobial potency and selectivity comparable to the clinically investigated AMP pexiganan. Our work demonstrates the potential of AI to expedite the discovery of peptide-based antibiotics to combat antibiotic resistance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Antimicrobial PeptidesAnti-Bacterial AgentsDrug DiscoveryAntimicrobial Cationic PeptidesMicrobial Sensitivity TestsHumans

Stichwörter der Autor:innen

AI-based screeningantibioticsantimicrobial peptidesmulti-drug resistantprotein language model

Substanzen

Antimicrobial PeptidesAnti-Bacterial AgentsAntimicrobial Cationic Peptides

Autor:innen und Institutionen

  • Department of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Buk-gu, Gwangju 61005, Republic of Korea.
  • Department of Chemistry, Gwangju Institute of Science and Technology (GIST), Buk-gu, Gwangju 61005, Republic of Korea.
  • AI Graduate School, Gwangju Institute of Science and Technology (GIST), Buk-gu, Gwangju 61005, Republic of Korea.

ORCID-Profile: Hojung Nam

Förderung

  • Gwangju Institute of Science and Technology
  • National Research Foundation of Korea
  • Korea Machine Learning Ledger Orchestration for Drug Discovery Project
  • Ministry of Health & Welfare and Ministry of Science and ICT, Republic of Korea

Zitieren

APA

Bae, D., Kim, M., Seo, J., & Nam, H. (2025). AI-guided discovery and optimization of antimicrobial peptides through species-aware language model. Briefings in Bioinformatics, 26(4). https://doi.org/10.1093/bib/bbaf343

Vancouver

Bae D, Kim M, Seo J, Nam H. AI-guided discovery and optimization of antimicrobial peptides through species-aware language model. Briefings in Bioinformatics. 2025;26(4). doi:10.1093/bib/bbaf343

BibTeX
@article{Bae2025,
  author = {Bae, Daehun and Kim, Minsang and Seo, Jiwon and Nam, Hojung},
  title = {AI-guided discovery and optimization of antimicrobial peptides through species-aware language model},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  volume = {26},
  number = {4},
  doi = {10.1093/bib/bbaf343}
}
Kostenlos starten →