Abstract
Drug-resistant bacterial infections pose a serious threat to global health, driving the development of antibacterial strategies beyond classic antibiotics. Host defense peptide mimetic polymeric antibiotics have emerged as promising candidates to combat drug resistance, however, navigating the vast chemical space of polymers remains a significant challenge due to complex structure–activity relationships, while data-driven approaches are further constrained by polymer complexity and scarce labeled data. To address this, we develop PolyCLOVER, a framework that integrates multi-stage self-supervised learning, active learning, and high-throughput experimentation to iteratively discover polymeric antibiotics with potent antibacterial activity and low toxicity. Applied to a combi…
Abstract
Drug-resistant bacterial infections pose a serious threat to global health, driving the development of antibacterial strategies beyond classic antibiotics. Host defense peptide mimetic polymeric antibiotics have emerged as promising candidates to combat drug resistance, however, navigating the vast chemical space of polymers remains a significant challenge due to complex structure–activity relationships, while data-driven approaches are further constrained by polymer complexity and scarce labeled data. To address this, we develop PolyCLOVER, a framework that integrates multi-stage self-supervised learning, active learning, and high-throughput experimentation to iteratively discover polymeric antibiotics with potent antibacterial activity and low toxicity. Applied to a combinatorial library of ~100,000 poly(β-amino ester)s, the framework uncovers three lead compounds that self-assemble into stable nanoparticles (SANPs) with minimum inhibitory concentrations of 4 μg/mL and 8 μg/mL against multidrug-resistant S. aureus and A. baumannii, respectively. These SANPs also serve as adjuvant antibiotic carriers, restoring bacterial sensitivity to penicillin G. In vivo studies demonstrate their therapeutic efficacy both as monotherapies and in combination therapies with antibiotics. PolyCLOVER may become a powerful framework for discovery of new polymeric biomaterials without reliance on external datasets.
Data availability
The data that support the findings of this study are available within the main text and the Supplementary Information. The pretrained checkpoints and processed datasets are available at https://doi.org/10.6084/m9.figshare.2887696165. Source data are provided with this paper.
References
Naghavi, M. et al. Global burden of bacterial antimicrobial resistance 1990-2021: a systematic analysis with forecasts to 2050. Lancet 404, 1199–1226 (2024).
Ho, C. S. et al. Antimicrobial resistance: a concise update. Lancet Microbe 6, 100947 (2024). 1.
Martins, A. et al. Antibiotic candidates for Gram-positive bacterial infections induce multidrug resistance. Sci. Transl. Med. 17, eadl2103 (2025).
Brown, E. D. & Wright, G. D. Antibacterial drug discovery in the resistance era. Nature 529, 336–343 (2016).
Hutchings, M. I., Truman, A. W. & Wilkinson, B. Antibiotics: past, present and future. Curr. Opin. Microbiol. 51, 72–80 (2019).
Shi, Z. et al. A comprehensive overview of the antibiotics approved in the last two decades: retrospects and prospects. Molecules 28, 1762 (2023).
Bognár, B., Spohn, R. & Lázár, V. Drug combinations targeting antibiotic resistance. npj Antimicrob. Resist. 2, 29 (2024).
Tyers, M. & Wright, G. D. Drug combinations: a strategy to extend the life of antibiotics in the 21st century. Nat. Rev. Microbiol. 17, 141–155 (2019).
Joseph, J., Boby, S., Mooyottu, S. & Muyyarikkandy, M. S. Antibiotic potentiators as a promising strategy for combating antibiotic resistance. npj Antimicrob. Resist. 3, 53 (2025).
Song, M. et al. A broad-spectrum antibiotic adjuvant reverses multidrug-resistant Gram-negative pathogens. Nat. Microbiol. 5, 1040–1050 (2020).
Lewis, K. The Science of Antibiotic Discovery. Cell 181, 29–45 (2020).
MacNair, C. R., Rutherford, S. T. & Tan, M. W. Alternative therapeutic strategies to treat antibiotic-resistant pathogens. Nat. Rev. Microbiol. 22, 262–275 (2024).
Magana, M. et al. The value of antimicrobial peptides in the age of resistance. Lancet Infect. Dis. 20, E216–E230 (2020).
Mookherjee, N., Anderson, M. A., Haagsman, H. P. & Davidson, D. J. Antimicrobial host defence peptides: functions and clinical potential. Nat. Rev. Drug Discov. 19, 311–332 (2020).
Fernandes, S. & Cavalieri, F. Antimicrobial peptides boosted by ultrasound. Nat. Biomed. Eng. 9, 1177–1179 (2025). 1.
Hancock, R. E. & Sahl, H. G. Antimicrobial and host-defense peptides as new anti-infective therapeutic strategies. Nat. Biotechnol. 24, 1551–1557 (2006).
Yuan, Y. et al. Stable peptide-assembled nanozyme mimicking dual antifungal actions. Nat. Commun. 15, 5636 (2024).
Gelman, M. A., Weisblum, B., Lynn, D. M. & Gellman, S. H. Biocidal activity of polystyrenes that are cationic by virtue of protonation. Org. Lett. 6, 557–560 (2004).
Lam, S. J. et al. Combating multidrug-resistant Gram-negative bacteria with structurally nanoengineered antimicrobial peptide polymers. Nat. Microbiol. 1, 16162 (2016).
Nederberg, F. et al. Biodegradable nanostructures with selective lysis of microbial membranes. Nat. Chem. 3, 409–414 (2011).
Wu, Y. et al. Host defense peptide mimicking antimicrobial amino acid polymers and beyond: Design, synthesis and biomedical applications. Prog. Polym. Sci. 141, 101679 (2023).
Xie, J. et al. Addressing MRSA infection and antibacterial resistance with peptoid polymers. Nat. Commun. 12, 5898 (2021).
Qian, Y. et al. Secondary amine pendant β-peptide polymers displaying potent antibacterial activity and promising therapeutic potential in treating MRSA-induced wound infections and keratitis. J. Am. Chem. Soc. 144, 1690–1699 (2022).
Maset, R. G. et al. Combining SNAPs with antibiotics shows enhanced synergistic efficacy against S. aureus and P. aeruginosa biofilms. npj Biofilms Microbomes 9, 36 (2023).
Schaefer, S. et al. A synthetic peptide mimic kills Candida albicans and synergistically prevents infection. Nat. Commun. 15, 6818 (2024).
Wu, Y. M. et al. Host defense peptide mimicking antimicrobial amino acid polymers and beyond: design, synthesis and biomedical applications. Prog. Polym. Sci. 141, 47 (2023).
Shabani, S. et al. Synthetic peptide branched polymers for antibacterial and biomedical applications. Nat. Rev. Bioeng. 2, 343–361 (2024).
Shen, X. et al. AI-driven discovery and design of antimicrobial peptides. Sci. China Technol. Sci. 68, 2200205 (2025).
Wan, F., Torres, M. D. T., Guan, C. & de la Fuente-Nunez, C. Tutorial: guidelines for the use of machine learning methods to mine genomes and proteomes for antibiotic discovery. Nat. Protoc. 20, 2685–2697 (2025). 1.
Wan, F., Wong, F., Collins, J. J. & de la Fuente-Nunez, C. Machine learning for antimicrobial peptide identification and design. Nat. Rev. Bioeng. 2, 392–407 (2024).
Huang, J. et al. Identification of potent antimicrobial peptides via a machine-learning pipeline that mines the entire space of peptide sequences. Nat. Biomed. Eng. 7, 797–810 (2023).
Chen, J. W. et al. Global marine microbial diversity and its potential in bioprospecting. Nature 633, 371–379 (2024).
Santos, C. D. Jr. et al. Discovery of antimicrobial peptides in the global microbiome with machine learning. Cell 187, 35 (2024).
Torres, M. D. T. et al. Mining human microbiomes reveals an untapped source of peptide antibiotics. Cell 187, 31 (2024).
Maasch, J., Torres, M. D. T., Melo, M. C. R. & de la Fuente-Nunez, C. Molecular de-extinction of ancient antimicrobial peptides enabled by machine learning. Cell Host Microbe 31, 22 (2023).
Torres, M. D. T. et al. Mining for encrypted peptide antibiotics in the human proteome. Nat. Biomed. Eng. 6, 67–75 (2022).
Wu, T. et al. AI-guided few-shot inverse design of HDP-mimicking polymers against drug-resistant bacteria. Nat. Commun. 15, 6288 (2024).
Wu, Y. et al. Periodicity-aware deep learning for polymers. Nat. Comput. Sci. 5, 1214–1226 (2025).
Makabenta, J. M. V. et al. Nanomaterial-based therapeutics for antibiotic-resistant bacterial infections. Nat. Rev. Microbiol. 19, 23–36 (2021).
Pham, P., Oliver, S., Nguyen, D. T. & Boyer, C. Effect of cationic groups on the selectivity of ternary antimicrobial polymers. Macromol. Rapid Commun. 43, 2200377 (2022).
Phuong, P. T. et al. Effect of hydrophobic groups on antimicrobial and hemolytic activity: Developing a predictive tool for ternary antimicrobial polymers. Biomacromolecules 21, 5241–5255 (2020).
Turner, N. A. et al. Methicillin-resistant Staphylococcus aureus: an overview of basic and clinical research. Nat. Rev. Microbiol. 17, 203–218 (2019).
Wieder, O. et al. A compact review of molecular property prediction with graph neural networks. Drug Discov. Today.: Technol. 37, 1–12 (2020).
Reiser, P. et al. Graph neural networks for materials science and chemistry. Commun. Mater. 3, 93 (2022).
Li, H., Zhao, D. & Zeng, J. KPGT: knowledge-guided pre-training of graph transformer for molecular property prediction. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (ACM, 2022). 1.
Wang, Y., Wang, J., Cao, Z. & Barati Farimani, A. Molecular contrastive learning of representations via graph neural networks. Nat. Mach. Intell. 4, 279–287 (2022).
Hu, W. et al. Strategies for pre-training graph neural networks. In Proceedings of the 8th International Conference on Learning Representations (ICLR, 2020). 1.
Lin, Z. et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 1123–1130 (2023).
Qiang, B. et al. Bridging the gap between chemical reaction pretraining and conditional molecule generation with a unified model. Nat. Mach. Intell. 5, 1476–1485 (2023).
Wang, T. & Isola, P. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In Proceedings of the 37th International Conference on Machine Learning (ACM, 2020). 1.
Frederiksen, N., Hansen, P. R., Björkling, F. & Franzyk, H. Peptide/peptoid hybrid oligomers: The Influence of hydrophobicity and relative side-chain length on antibacterial activity and cell Selectivity. Molecules 24, 4429 (2019).
Zhang, W. et al. Host defense peptide mimicking cyclic peptoid polymers exerting strong activity against drug-resistant bacteria. Biomater. Sci. 10, 4515–4524 (2022).
O’Sullivan, M. E. et al. Aminoglycoside ribosome interactions reveal novel conformational states at ambient temperature. Nucleic Acids Res. 46, 9793–9804 (2018).
Zhou, M. et al. Poly(2-oxazoline)-based functional peptide mimics: eradicating MRSA infections and persisters while alleviating antimicrobial resistance. Angew. Chem. Int. Ed. 59, 6412–6419 (2020).
Rubinstein, E., Kollef, M. H. & Nathwani, D. Pneumonia caused by methicillin-resistant Staphylococcus aureus. Clin. Infect. Dis. 46, S378–S385 (2008).
Adedeji-Olulana, A. F. et al. Two codependent routes lead to high-level MRSA. Science 386, 573–580 (2024).
Williams, S. C. et al. Polyacrylamide-based antimicrobial copolymers to replace or rescue antibiotics. ACS Cent. Sci. 11, 486–496 (2025).
Fuda, C. et al. Activation for catalysis of penicillin-binding protein 2a from methicillin-resistant Staphylococcus a ureus by bacterial cell wall. J. Am. Chem. Soc. 127, 2056–2057 (2005).
Mishra, B., Lakshmaiah Narayana, J., Lushnikova, T., Wang, X. & Wang, G. Low cationicity is important for systemic in vivo efficacy of database-derived peptides against drug-resistant Gram-positive pathogens. Proc. Natl. Acad. Sci. 116, 13517–13522 (2019).
Dosta, P. et al. Investigation of the enhanced antitumour potency of STING agonist after conjugation to polymer nanoparticles. Nat. Nanotechnol. 18, 1351–1363 (2023).
Lynn, D. M. & Langer, R. Degradable poly (β-amino esters): synthesis, characterization, and self-assembly with plasmid DNA. J. Am. Chem. Soc. 122, 10761–10768 (2000).
Ben-Akiva, E. et al. Biodegradable lipophilic polymeric mRNA nanoparticles for ligand-free targeting of splenic dendritic cells for cancer vaccination. Proc. Natl. Acad. Sci. 120, e2301606120 (2023).
Landrum, G. RDKit: Open-source cheminformatics. Retrieved from https://www.rdkit.org (2013). 1.
Moriwaki, H., Tian, Y.-S., Kawashita, N. & Takagi, T. Mordred: a molecular descriptor calculator. J. Cheminform. 10, 4 (2018).
Wu, Y. Pretrained checkpoints and source code. figshare https://doi.org/10.6084/m9.figshare.28876961 (2025).
Acknowledgements
This work was supported by the National Natural Science Foundation of China (52293381), Zhejiang Provincial Natural Science Foundation of China (LR25E030001), the “Pioneer” and “Leading Goose” R&D Program of Zhejiang (2025C04012), and the National Key Research and Development Program of China (2022YFB3807300). This work was also supported by Transvascular Implantation Devices Research Institute China (TIDRIC) under Grant No. KY012024007 and KY012024009.
Author information
Author notes
These authors contributed equally: Yuhui Wu, Cong Wang, Xintian Shen.
Authors and Affiliations
MOE Key Laboratory of Macromolecule Synthesis and Functionalization, Department of Polymer Science and Engineering, Zhejiang University, Hangzhou, PR China
Yuhui Wu, Cong Wang, Xintian Shen, Bocheng Xu, Zihao Zhu, Yifeng Chen, Wenbin Dai, Yue Huang, Lingyun Zou, Jian Ji & Peng Zhang 1.
International Research Center for X Polymers, International Campus, Zhejiang University, Haining, PR China
Yuhui Wu, Xintian Shen, Jian Ji & Peng Zhang 1.
Department of Infectious Diseases, Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, Hangzhou, PR China
Yan Chen & Haiping Wang 1.
State Key Laboratory of Transvascular Implantation Devices, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, PR China
Bocheng Xu, Jian Ji & Peng Zhang 1.
Transvascular Implantation Devices Research Institute China, Hangzhou, PR China
Bocheng Xu & Jian Ji
Authors
- Yuhui Wu
- Cong Wang
- Xintian Shen
- Yan Chen
- Haiping Wang
- Bocheng Xu
- Zihao Zhu
- Yifeng Chen
- Wenbin Dai
- Yue Huang
- Lingyun Zou
- Jian Ji
- Peng Zhang
Contributions
P.Z. and J.J. conceptualized and supervised the project. P.Z., Y.W., C.W., and X.S. designed the experiments, analyzed the data, and wrote the paper. Y.W. and P.Z. designed the overall framework. Y.W. was responsible for the design, training, and analysis of the deep learning model. C. W. carried out the chemical synthesis and in vitro assays. X.S. investigated the self-assembly behavior of SANPs and their synergistic therapeutic effects with antibiotics. Y.C. and H.W. evaluated the performance of SANPs against clinically isolated multidrug-resistant bacteria. B.X. participated in the mouse peritonitis model experiments. Z.Z. participated in the toxicity evaluation. Y.F.C. assisted with the experiments. W.D. and Y.H. contributed to the mouse pneumonia model experiments. L.Z. participated in experimental discussions. All authors reviewed and approved the final manuscript.
Corresponding authors
Correspondence to Jian Ji or Peng Zhang.
Ethics declarations
Competing interests
The authors declare no competing interests.
Peer review
Peer review information
Nature Communications thanks Eleftherios Mylonakis, Fangping Wan, and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. A peer review file is available.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Wu, Y., Wang, C., Shen, X. et al. Iterative discovery of potent polymeric antibiotics via multi-stage and multi-task learning against antimicrobial resistance. Nat Commun (2026). https://doi.org/10.1038/s41467-026-68682-z
Received: 18 June 2025
Accepted: 13 January 2026
Published: 21 January 2026
DOI: https://doi.org/10.1038/s41467-026-68682-z