AI-Driven Antimicrobial Peptide Discovery: Mining and Generation
Accounts of Chemical Research · 17.06.2025 · 58 (12) · 1831-1846
DOI: 10.1021/acs.accounts.0c00594 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Accounts of Chemical Research, online erschienen am 03.06.2025. Verfasst von Paulina Szymczak und 7 weiteren Autor:innen. Beteiligte Einrichtung: Institute of AI for Health, Helmholtz Zentrum Munich, Neuherberg 85764, Germany. Hauptthemen laut MEDLINE: Antimicrobial Peptides, Artificial Intelligence, Drug Discovery, Anti-Bacterial Agents. Die Arbeit wurde bisher 117-mal zitiert (Crossref) und nennt 118 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, Australian Research Council, Natural Science Foundation of Beijing Municipality.
Abstract (Originalsprache)
The escalating threat of antimicrobial resistance (AMR) poses a significant global health crisis, potentially surpassing cancer as a leading cause of death by 2050. Traditional antibiotic discovery methods have not kept pace with the rapidly evolving resistance mechanisms of pathogens, highlighting the urgent need for novel therapeutic strategies. In this context, antimicrobial peptides (AMPs) represent a promising class of therapeutics due to their selectivity toward bacteria and slower induction of resistance compared to classical, small molecule antibiotics. However, designing effective AMPs remains challenging because of the vast combinatorial sequence space and the need to balance efficacy with low toxicity. Addressing this issue is of paramount importance for chemists and researchers dedicated to developing next-generation antimicrobial agents.Artificial intelligence (AI) presents a powerful tool to revolutionize AMP discovery. By leveraging AI, we can navigate the immense sequence space more efficiently, identifying peptides with optimal therapeutic properties. This Account explores the emerging application of AI in AMP discovery, focusing on two primary strategies: AMP mining, and AMP generation, as well as the use of discriminative methods as a valuable toolbox.AMP mining involves scanning biological sequences to identify potential AMPs. Discriminative models are then used to predict the activity and toxicity of these peptides. This approach has successfully identified numerous promising candidates, which were subsequently validated experimentally, demonstrating the potential of AI in AMP design and discovery.AMP generation, on the other hand, creates novel peptide sequences by learning from existing data through generative modeling. This class of models optimizes for desired properties, such as increased activity and reduced toxicity, potentially producing synthetic peptides that surpass naturally occurring ones. Despite the risk of generating unrealistic sequences, generative models hold the promise of accelerating the discovery of highly effective and highly novel and diverse AMPs.In this Account, we describe the technical challenges and advancements in these AI-based approaches. We discuss the importance of integrating various data sources and the role of advanced algorithms in refining peptide predictions. Additionally, we highlight the future potential of AI to not only expedite the discovery process but also to uncover peptides with unprecedented properties, paving the way for next-generation antimicrobial therapies.In conclusion, the synergy between AI and AMP discovery opens new frontiers in the fight against AMR. By harnessing the power of AI, we can design novel peptides that are both highly effective and safe, offering hope for a future where AMR is no longer a looming threat. Our paper underscores the transformative potential of AI in drug discovery, advocating for its continued integration into biomedical research.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Institute of AI for Health, Helmholtz Zentrum Munich, Neuherberg 85764, Germany.
- Faculty of Mathematics, Informatics and Mechanics, University of Warsaw, Warsaw 02-097, Poland.
- Faculty of Electronics and Information Technology, Warsaw University of Technology, Warsaw 00-661, Poland.
- Institute of Microbiology, Chinese Academy of Sciences; Beijing 100101, China.
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai 200433, China.
- Centre for Microbiome Research, School of Biomedical Sciences, Queensland University of Technology, Translational Research Institute, Woolloongabba, Queensland 4102, Australia.
ORCID-Profile: Paulina Szymczak, Cesar de la Fuente-Nunez, Ewa Szczurek
Förderung
- NIGMS NIH HHS
- Australian Research Council
- Natural Science Foundation of Beijing Municipality
- Defense Threat Reduction Agency
- National Institute of General Medical Sciences
- H2020 European Research Council
Zitieren
APA
Szymczak, P., Zarzecki, W., Wang, J., Duan, Y., Wang, J., Coelho, L. P., de la Fuente-Nunez, C., & Szczurek, E. (2025). AI-Driven Antimicrobial Peptide Discovery: Mining and Generation. Accounts of Chemical Research, 58(12), 1831-1846. https://doi.org/10.1021/acs.accounts.0c00594
Vancouver
Szymczak P, Zarzecki W, Wang J, Duan Y, Wang J, Coelho LP, et al. AI-Driven Antimicrobial Peptide Discovery: Mining and Generation. Accounts of Chemical Research. 2025;58(12):1831-1846. doi:10.1021/acs.accounts.0c00594
BibTeX
@article{Szymczak2025,
author = {Szymczak, Paulina and Zarzecki, Wojciech and Wang, Jiejing and Duan, Yiqian and Wang, Jun and Coelho, Luis Pedro and de la Fuente-Nunez, Cesar and Szczurek, Ewa},
title = {AI-Driven Antimicrobial Peptide Discovery: Mining and Generation},
journal = {Accounts of Chemical Research},
year = {2025},
volume = {58},
number = {12},
pages = {1831--1846},
doi = {10.1021/acs.accounts.0c00594}
}
EUVIMED