Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

De novo design of self-assembling peptides with antimicrobial activity guided by deep learning

Nature Materials volume 24, pages 1295–1306 (2025)Cite this article

Subjects

Abstract

Bioinspired materials based on self-assembling peptides are promising for tackling various challenges in biomedical engineering. While contemporary data-driven approaches have led to the discovery of self-assembling peptides with various structures and properties, predicting the functionalities of these materials is still challenging. Here we describe the deep learning-guided de novo design of antimicrobial materials based on self-assembling peptides targeting bacterial membranes to address the emerging problem of bacterial drug resistance. Our approach integrates non-natural amino acids for enhanced peptide self-assembly and effectively predicts the functional activity of the self-assembling peptide materials with minimal experimental annotation. The designed self-assembling peptide leader displays excellent in vivo therapeutic efficacy against intestinal bacterial infection in mice. Moreover, it exhibits an enhanced biofilm eradication capability and does not induce acquired drug resistance. Mechanistic studies reveal that the designed peptide can self-assemble on bacterial membranes to form nanofibrous structures for killing multidrug-resistant bacteria. This work thus provides a strategy to discover functional peptide materials by customized design.

Access through your institution
Buy or subscribe

This is a preview of subscription content, access via your institution

Access options

Access through your institution

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Overview of the discovery workflow of the new SAFP materials.
Fig. 2: The TransSAFP protocol for identifying potential SAFPs.
Fig. 3: Experimental validation and screening of SAFP candidates.
Fig. 4: Prediction and analysis of SAFP in entire octapeptide library.
Fig. 5: Therapeutic efficacy of p45 against intestinal infection.
Fig. 6: Antimicrobial mechanisms and biofilm eradication of p45.

Similar content being viewed by others

Data availability

The data that support the findings are available within the main text and the Supplementary Information and can be obtained from the corresponding authors upon request. The positive pretrained dataset was collected from the DBAASP database (https://dbaasp.org/search). The negative pretrained dataset was collected from the UniProt database (http://www.uniprot.org). Datasets and codes for the model are accessible via Science Data Bank at https://doi.org/10.57760/sciencedb.19186 (ref. 46). Source data are provided with this paper.

Code availability

The TransSAFP model can be accessed via GitHub at https://github.com/LiuHuayang27/TransSAFP (ref. 47), which is archived at the Science Data Bank at https://doi.org/10.57760/sciencedb.19186 (ref. 46).

References

  1. Ahnert, S. E. et al. Principles of assembly reveal a periodic table of protein complexes. Science 350, aa2245 (2015).

    Article  Google Scholar 

  2. Vermeire, P.-J. et al. Molecular interactions driving intermediate filament assembly. Cells 10, 2457 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Yang, G. et al. Precise and reversible protein-microtubule-like structure with helicity driven by dual supramolecular interactions. J. Am. Chem. Soc. 138, 1932–1937 (2016).

    Article  CAS  PubMed  Google Scholar 

  4. Imada, K. Bacterial flagellar axial structure and its construction. Biophys. Rev. 10, 559–570 (2018).

    Article  CAS  PubMed  Google Scholar 

  5. Jia, Y. & Li, J. Molecular assembly of rotary and linear motor proteins. Accounts Chem. Res. 52, 1623–1631 (2019).

    Article  CAS  Google Scholar 

  6. Chiesa, G., Kiriakov, S. & Khalil, A. S. Protein assembly systems in natural and synthetic biology. BMC Biol. 18, 35 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  7. Silva, G. A. et al. Selective differentiation of neural progenitor cells by high-epitope density nanofibers. Science 303, 1352–1355 (2004).

    Article  CAS  PubMed  Google Scholar 

  8. Yolamanova, M. et al. Peptide nanofibrils boost retroviral gene transfer and provide a rapid means for concentrating viruses. Nat. Nanotechnol. 8, 130–136 (2013).

    Article  CAS  PubMed  Google Scholar 

  9. Münch, J. et al. Semen-derived amyloid fibrils drastically enhance HIV infection. Cell 131, 1059–1071 (2007).

    Article  PubMed  Google Scholar 

  10. Kim, J. et al. In situ self-assembly for cancer therapy and imaging. Nat. Rev. Mater. 8, 710–725 (2023).

    Article  Google Scholar 

  11. Baek, M. et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science 373, 871–876 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Guo, J. et al. Cell spheroid creation by transcytotic intercellular gelation. Nat. Nanotechnol. 18, 1094–1104 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  14. He, P.-P. et al. Bispyrene-based self-assembled nanomaterials: in vivo self-assembly, transformation, and biomedical effects. Acc. Chem. Res. 52, 367–378 (2019).

    Article  CAS  PubMed  Google Scholar 

  15. Gao, J., Zhan, J. & Yang, Z. Enzyme-instructed self-assembly (EISA) and hydrogelation of peptides. Adv. Mater. 32, 1805798 (2020).

    Article  CAS  Google Scholar 

  16. Frederix, P. W. J. M. et al. Exploring the sequence space for (tri-)peptide self-assembly to design and discover. Nat. Chem. 7, 30–37 (2015).

    Article  CAS  PubMed  Google Scholar 

  17. Xu, T. Y. et al. Accelerating the prediction and discovery of peptide hydrogels with human-in-the-loop. Nat. Commun. 14, 3880 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Batra, R. et al. Machine learning overcomes human bias in the discovery of self-assembling peptides. Nat. Chem. 14, 1427–1435 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. Pirtskhalava, M. et al. DBAASP v.2: an enhanced database of structure and antimicrobial/cytotoxic activity of natural and synthetic peptides. Nucleic Acids Res. 44, D1104–D1112 (2016).

    Article  CAS  PubMed  Google Scholar 

  20. Pirtskhalava, M. et al. DBAASP v3: database of antimicrobial/cytotoxic activity and structure of peptides as a resource for development of new therapeutics. Nucleic Acids Res. 49, D288–D297 (2021).

    Article  CAS  PubMed  Google Scholar 

  21. Vaswani A. et al. Attention is all you need. In Proc. 31st International Conference on Neural Information Processing Systems (eds Guyon, I. et al.) 6000–6010 (Curran Associates, 2017).

  22. McInnes, L., Healy, J. & Melville, J. UMAP: uniform manifold approximation and projection. J. Open Source Softw. 3, 861 (2018).

    Article  Google Scholar 

  23. Xu, Z. J. & Zhou, H. Deep frequency principle towards understanding why deeper learning is faster. In Proc. 35th AAAI Conference on Artificial Intelligence (eds. Leyton-Brown, K. et al.) 10541–10550 (AAAI Press, 2021).

  24. Barth, A. Infrared spectroscopy of proteins. Biochim. Biophys. Acta Bioenerg. 1767, 1073–1101 (2007).

    Article  CAS  Google Scholar 

  25. Pavia, D. L. et al. in Introduction to Spectroscopy, 5th edn, 70–71 (Cengage Learning, 2015).

  26. Barron, A. R. in Chemistry of the Main Group Elements Ch. 2.7 (Midas Green Innovations, 2014).

  27. el Battioui, K. et al. In situ captured antibacterial action of membrane-incising peptide lamellae. Nat. Commun. 15, 3424 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  28. Marty, R. et al. Hierarchically structured microfibers of ‘single stack’ perylene bisimide and quaterthiophene nanowires. ACS Nano 7, 8498–8508 (2013).

    Article  CAS  PubMed  Google Scholar 

  29. Kovacs, J. M., Mant, C. T. & Hodges, R. S. Determination of intrinsic hydrophilicity/hydrophobicity of amino acid side chains in peptides in the absence of nearest‐neighbor or conformational effects. Biopolymers 84, 283–297 (2006).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Pane, K. et al. Antimicrobial potency of cationic antimicrobial peptides can be predicted from their amino acid composition: application to the detection of ‘cryptic’ antimicrobial peptides. J. Theor. Biol. 419, 254–265 (2017).

    Article  CAS  PubMed  Google Scholar 

  31. Lopetuso, L. R. et al. Commensal Clostridia: leading players in the maintenance of gut homeostasis. Gut Pathog. 5, 23 (2013).

    Article  PubMed  PubMed Central  Google Scholar 

  32. Zafar, H. & Saier, M. H. Gut Bacteroides species in health and disease. Gut Microbes 13, 1848158 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  33. Shi, S. H. et al. Multidrug resistant Gram-negative bacilli as predominant bacteremic pathogens in liver transplant recipients. Transpl. Infect. Dis. 11, 405–412 (2009).

    Article  CAS  PubMed  Google Scholar 

  34. Torres, M. D. T. et al. Mining for encrypted peptide antibiotics in the human proteome. Nat. Biomed. Eng. 6, 67–75 (2022).

    Article  PubMed  Google Scholar 

  35. UniProt Consortium UniProt: the Universal Protein Knowledgebase in 2023. Nucleic Acids Res. 51, D523–D531 (2023).

    Article  Google Scholar 

  36. LeCun, Y. et al. Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998).

    Article  Google Scholar 

  37. Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735–1780 (1997).

    Article  CAS  PubMed  Google Scholar 

  38. Cho, K. et al. On the properties of neural machine translation: encoder–decoder approaches. In Proc. 8th Workshop on Syntax, Semantics and Structure in Statistical Translation (eds Wu, D. et al.) 103–111 (ACL, 2014).

  39. Schuster, M. & Paliwal, K. K. Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45, 2673–2681 (1997).

    Article  Google Scholar 

  40. Bahdanau, D., Cho, K. & Bengio, Y. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations (ICLR, 2015).

  41. Needleman, S. B. & Wunsch, C. D. A general method applicable to the search for similarities in the amino acid sequence of two proteins. J. Mol. Biol. 48, 443–453 (1970).

    Article  CAS  PubMed  Google Scholar 

  42. Abadi, M. et al. Tensorflow: large-scale machine learning on heterogeneous distributed systems. In Proc. USENIX Conference on Operating Systems Design and Implementation (eds Keeton, K. et al.) 265–283 (USENIX, 2016).

  43. Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. In 3rd International Conference on Learning Representations (ICLR, 2015).

  44. Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).

    Google Scholar 

  45. Cock, P. J. et al. Biopython: freely available Python tools for computational molecular biology and bioinformatics. Bioinformatics 25, 1422–1423 (2009).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  46. Liu, H., Song, Z., Huang, J. & Wang, H. Data archive for: “De novo design of self-assembling peptides with antimicrobial activity guided by deep-learning”. Science Data Bank https://doi.org/10.57760/sciencedb.19186 (2024).

  47. Liu, H., Song, Z., Huang, J., & Wang, H. Source codes repository for the model TransSAFP. GitHub https://github.com/LiuHuayang27/TransSAFP (2024).

Download references

Acknowledgements

This project was supported by the National Natural Science Foundation of China (82022038 to H.W. and 32171247 to J.H.) and the Westlake Education Foundation. This research was also supported by Zhejiang Provincial Natural Science Foundation of China under grant no. XHD23C1001. We thank the Instrumentation and Service Center for Molecular Sciences, the Instrumentation and Service Center for Physical Sciences, the Biomedical Research Core Facilities and the Supercomputer Center at Westlake University for assistance with measurements.

Author information

Author notes

  1. These authors contributed equally: Huayang Liu, Zilin Song.

Authors and Affiliations

  1. Key Laboratory of Precise Synthesis of Functional Molecules of Zhejiang Province, Department of Chemistry, School of Science, Westlake University, Hangzhou, China

    Huayang Liu, Yu Zhang, Bihan Wu, Dinghao Chen, Ziao Zhou, Hongyue Zhang, Sangshuang Li & Huaimin Wang

  2. Institute of Natural Sciences, Westlake Institute for Advanced Study, Hangzhou, China

    Huayang Liu & Huaimin Wang

  3. Key Laboratory of Structural Biology of Zhejiang Province, School of Life Sciences, Westlake University, Hangzhou, China

    Zilin Song, Xinping Feng & Jing Huang

  4. Institute of Biology, Westlake Institute for Advanced Study, Hangzhou, China

    Zilin Song & Jing Huang

  5. Westlake AI Therapeutics Lab, Westlake Laboratory of Life Sciences and Biomedicine, Hangzhou, China

    Zilin Song, Xinping Feng & Jing Huang

Authors
  1. Huayang Liu
    View author publications

    Search author on:PubMed Google Scholar

  2. Zilin Song
    View author publications

    Search author on:PubMed Google Scholar

  3. Yu Zhang
    View author publications

    Search author on:PubMed Google Scholar

  4. Bihan Wu
    View author publications

    Search author on:PubMed Google Scholar

  5. Dinghao Chen
    View author publications

    Search author on:PubMed Google Scholar

  6. Ziao Zhou
    View author publications

    Search author on:PubMed Google Scholar

  7. Hongyue Zhang
    View author publications

    Search author on:PubMed Google Scholar

  8. Sangshuang Li
    View author publications

    Search author on:PubMed Google Scholar

  9. Xinping Feng
    View author publications

    Search author on:PubMed Google Scholar

  10. Jing Huang
    View author publications

    Search author on:PubMed Google Scholar

  11. Huaimin Wang
    View author publications

    Search author on:PubMed Google Scholar

Contributions

H.W. and J.H. conceptualized, supervised and founded the project. H.L., Z.S., J.H. and H.W. designed the experiments, analysed the data and wrote the paper. H.L. established the database, performed most of the experiments and participated in DL model design. Z.S. encoded the peptide sequences and designed, trained and analysed the DL model. Y.Z. and S.L. participated in the peptide synthesis, MIC experiments and in vivo therapeutic efficacy assay. B.W. and D.C. participated in the in vivo toxicity test. Z.Z. participated in the establishment of the wet-lab database. H.Z. participated in the characterization of peptides by AFM. X.F. performed the coarse-grained molecular dynamics simulations.

Corresponding authors

Correspondence to Jing Huang or Huaimin Wang.

Ethics declarations

Competing interests

H.W., J.H., H.L. and Z.S. have filed a patent converting this work (China Patent application no. 2024112931879). The other authors declare no competing interests.

Peer review

Peer review information

Nature Materials thanks Cesar de la Fuente, Sonia Henriques and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary Figs. 1–29, Tables 1–13, Methods and References.

Reporting Summary

Supplementary Data 1

Liquid chromatography with mass spectrometry spectra of synthesized peptides.

Source data

Source Data Fig. 2

Source data for each image in Fig. 2.

Source Data Fig. 3

Source data for each image in Fig. 3.

Source Data Fig. 4

Source data for each image in Fig. 4.

Source Data Fig. 5

Source data for each image in Fig. 5.

Source Data Fig. 6

Source data for each image in Fig. 6.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, H., Song, Z., Zhang, Y. et al. De novo design of self-assembling peptides with antimicrobial activity guided by deep learning. Nat. Mater. 24, 1295–1306 (2025). https://doi.org/10.1038/s41563-025-02164-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41563-025-02164-3

This article is cited by

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing