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:

Peptide design through binding interface mimicry with PepMimic

Nature Biomedical Engineering (2025)Cite this article

Subjects

Abstract

Peptides offer advantages for targeted therapy, including oral bioavailability, cellular permeability and high specificity, setting them apart from conventional small molecules and biologics. Here we develop an artificial intelligence algorithm, PepMimic, to transform a known receptor or an existing antibody of a target into a short peptide binder by mimicking the binding interfaces between targets and known binders. We apply PepMimic to drug targets PD-L1, CD38, BCMA, HER2 and CD4. Surface plasmon resonance imaging results show that 8% of the peptides exhibit dissociation constant (KD) values at the 10−8 M level, and 26 peptides achieving KD values as low as 10−9 M, substantially higher than random library screening conducted under identical conditions. We apply PepMimic to target proteins lacking available binders by first using existing algorithms to design protein binders, followed by designing peptide through simulating these artificial interfaces. We extensively validate the top-ranked peptides using tail vein injections in breast, myeloma and lung tumour mouse models. Experimental results demonstrate effective membrane binding and highlight their strong potential for clinical diagnostic imaging and targeted therapeutic applications.

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: Schematic diagram of the PepMimic algorithm.
Fig. 2: Evaluations on target-specific peptide design on a non-redundant test set collected from literature.
Fig. 3: Evaluations on the latent interface encoder and analyses on the interface-mimicking capability of PepMimic.
Fig. 4: Results and analysis of molecular SPRi experiments, cellular assays, and in vivo validations for peptide mimicry.
Fig. 5: Generated structures and SPRi results of designed peptide mimicries on different target proteins.
Fig. 6: Results of peptide mimicry of AI-generated binding structures.

Similar content being viewed by others

Data availability

All the training data, the test set, the unsupervised dataset and detailed splits are available via Zenodo at https://doi.org/10.5281/zenodo.13373108 (ref. 70). The complexes used for mimicry are extracted from PDB (https: //www.rcsb.org/), the PDB IDs of which are listed in Supplementary Tables 1–5. The synthesized and tested peptide mimicry generations, as well as their experimental KD values, are presented in Supplementary Data 1.

Code availability

Codes for running our peptide mimicry algorithm are available via GitHub at https://github.com/kxz18/PepMimic (ref. 71).

References

  1. Muttenthaler, M., King, G. F., Adams, D. J. & Alewood, P. F. Trends in peptide-drug discovery. Nat. Rev. Drug Discov. 20, 309–325 (2021).

    Article  CAS  PubMed  Google Scholar 

  2. Wang, L. et al. Therapeutic peptides: current applications and future directions. Signal Transduct. Target. Ther. 7, 48 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Fosgerau, K. & Hoffmann, T. Peptide therapeutics: current status and future directions. Drug Discov. Today 20, 122–128 (2015).

    Article  CAS  PubMed  Google Scholar 

  4. Lee, A. C.-L., Harris, J. L., Khanna, K. K. & Hong, J.-H. A comprehensive review on current advances in peptide-drug development and design. Int. J. Mol. Sci. 20, 2383 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  5. Vanhee, P. et al. Computational design of peptide ligands. Trends Biotechnol. 29, 231–239 (2011).

    Article  CAS  PubMed  Google Scholar 

  6. Gainza, P. et al. Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning. Nat. Methods 17, 184–192 (2020).

    Article  CAS  PubMed  Google Scholar 

  7. Watson, J. L. et al. De novo design of protein structure and function with RFdiffusion. Nature 620, 1089–1100 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Karoyan, P. et al. Human ACE2 peptide-mimics block SARS-CoV-2 pulmonary-cell infection. Commun. Biol. 4, 197 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. S. E. Barrett, et al. Substrate interactions guide cyclase engineering and lasso peptide diversification. Nat. Chem. Biol. 21, 412–419 (2024).

  10. Miljanich, G. P. Ziconotide: neuronal calcium-channel blocker for treating severe chronic pain. Curr. Med. Chem. 11, 3029–3040 (2004).

    Article  CAS  PubMed  Google Scholar 

  11. Stone, G. W. et al. Bivalirudin for patients with acute coronary syndromes. N. Engl. J. Med. 355, 2203–2216 (2006).

    Article  CAS  PubMed  Google Scholar 

  12. Wilson, A. C., Meethal, S. V., Bowen, R. L. & Atwood, C. S. Leuprolide acetate: a drug of diverse clinical applications. Expert Opin. Investigational Drugs 16, 1851–1863 (2007).

    Article  CAS  Google Scholar 

  13. Burdick, D. et al. Assembly and aggregation properties of synthetic Alzheimer’s A4/β-amyloid peptide analogs. J. Biol. Chem. 267, 546–554 (1992).

    Article  CAS  PubMed  Google Scholar 

  14. Hruby, V. J. Designing peptide-receptor agonists and antagonists. Nat. Rev. Drug Discov. 1, 847–858 (2002).

    Article  CAS  PubMed  Google Scholar 

  15. Parisi, G. et al. Design of protein-binding peptides with controlled binding affinity: the case of SARS-CoV-2 receptor-binding domain and angiotensin-converting enzyme 2-derived peptides. Front. Mol. Biosci. 10, 1332359 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  16. Hill, T. A., Shepherd, N. E., Diness, F. & Fairlie, D. P. Constraining cyclic peptides to mimic protein-structure motifs. Angew. Chem. Int. Ed. 53, 13020–13041 (2014).

    Article  CAS  Google Scholar 

  17. Bryan, C. M. et al. Computational design of a synthetic PD-1 agonist. Proc. Natl Acad. Sci. USA 118, e2102164118 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Ingraham, J. B. et al. Illuminating protein space with a programmable generative model. Nature 623, 1070–1078 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. Lee, J. S., Kim, J. & Kim, P. M. Score-based generative modeling for de novo protein design. Nat. Comput. Sci. 3, 382–392 (2023).

    Article  CAS  PubMed  Google Scholar 

  20. Jin, W., Wohlwend, J., Barzilay, R. & Jaakkola, T. S. Iterative refinement graph neural network for antibody sequence–structure co-design. In International Conference on Learning Representations (2022); https://openreview.net/forum?id=LI2bhrE_2A

  21. Kong, X., Huang, W. & Liu, Y. Conditional antibody design as 3-D equivariant graph translation. In The Eleventh International Conference on Learning Representations (2023); https://openreview.net/forum?id=LFHFQbjxIiP

  22. Luo, S. et al. Antigen-specific antibody design and optimization with diffusion-based generative models for protein structures. Advances in Neural Information Processing Systems. 35, 9754–9767 (2022).

    Google Scholar 

  23. Abramson, J. et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630, 493–500 (2024).

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

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  25. 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 

  26. Krishna, R. et al. Generalized biomolecular modeling and design with RoseTTAFold All-Atom. Science 384, eadl2528 (2024).

    Article  CAS  PubMed  Google Scholar 

  27. Wang, F., Wang, Y., Feng, L., Zhang, C. & Lai, L. Target-specific de novo peptide-binder design with DiffPepBuilder. J. Chem. Inf. Model. 64, 9135–9149 (2024).

    Article  CAS  PubMed  Google Scholar 

  28. Li, J. et al. Full-atom peptide design based on multi-modal flow matching. In Proc. of the 41st International Conference on Machine Learning Vol. 235 (eds Salakhutdinov, R. et al.) 27615–27640 (PMLR, 2024).

  29. Haitao Lin, O. et al. PPFLOW: target-aware peptide design with torsional flow matching. In Proc. 41st International Conference on Machine Learning (eds Salakhutdinov, R. et al.) vol. 235, 30510–30528 (PMLR, 2024).

  30. Zhang, L., Rao, A. & Agrawala, M. Adding conditional control to text-to-image diffusion models. In Proc. IEEE/CVF International Conference on Computer Vision 3836–3847 (2023).

  31. Rafailov, R. et al. Direct preference optimization: your language model is secretly a reward model. Adv. Neural Inf. Process. Syst. 36, 53728–53741 (2023).

    Google Scholar 

  32. You, J., Liu, B., Ying, Z., Pande, V. & Leskovec, J. Graph convolutional policy network for goal-directed molecular-graph generation. Advances in Neural Information Processing Systems 31 (2018).

  33. Kong, X., Huang, W. & Liu, Y. End-to-end full-atom antibody design. In Proc. 40th International Conference on Machine Learning Vol. 202 (eds Krause, A. et al.) 17409–17429 (PMLR, 2023).

  34. Jin, W., Barzilay, R. & Jaakkola, T. Antibody–antigen docking and design via hierarchical structure refinement. In Proc. of the 39th International Conference on Machine Learning Vol. 162 (eds Chaudhuri, K. et al.) 10217–10227 (PMLR, 2022).

  35. Tsaban, T. et al. Harnessing protein-folding neural networks for peptide–protein docking. Nat. Commun. 13, 176 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  36. Steinegger, M. & Söding, J. MMseqs2 enables sensitive protein-sequence searching for the analysis of massive data sets. Nat. Biotechnol. 35, 1026–1028 (2017).

    Article  CAS  PubMed  Google Scholar 

  37. Alford, R. F. et al. The Rosetta all-atom energy function for macromolecular modeling and design. J. Chem. Theory Comput. 13, 3031–3048 (2017).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  38. Kabsch, W. & Sander, C. Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features. Biopolymers 22, 2577–2637 (1983).

    Article  CAS  PubMed  Google Scholar 

  39. van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008).

    Google Scholar 

  40. Steinley, D. Properties of the Hubert–Arabie adjusted Rand index. Psychol. Methods 9, 386 (2004).

    Article  PubMed  Google Scholar 

  41. Henikoff, S. & Henikoff, J. G. Amino-acid substitution matrices from protein blocks. Proc. Natl Acad. Sci. USA 89, 10915–10919 (1992).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  42. Lin, D. Y. et al. The PD-1/PD-L1 complex resembles the antigen-binding Fv domains of antibodies and T-cell receptors. Proc. Natl Acad. Sci. USA 105, 3011–3016 (2008).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  43. Gainza, P. et al. De novo design of protein interactions with learned surface fingerprints. Nature 617, 176–184 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  44. Kang-Pettinger, T. et al. Identification, binding, and structural characterization of single-domain anti-PD-L1 antibodies inhibitory of immune-regulatory proteins PD-1 and CD80. J. Biol. Chem. 299, 1 (2023).

    Article  Google Scholar 

  45. Lee, H. T. et al. Molecular mechanism of PD-1/PD-L1 blockade via anti-PD-L1 antibodies atezolizumab and durvalumab. Sci. Rep. 7, 5532 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  46. Cheng, X. et al. Structure and interactions of the human programmed cell death 1 receptor. J. Biol. Chem. 288, 11771–11785 (2013).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  47. Tan, S. et al. Distinct PD-L1 binding characteristics of therapeutic monoclonal antibody durvalumab. Protein Cell 9, 135–139 (2018).

    Article  CAS  PubMed  Google Scholar 

  48. Zak, K. M. et al. Structural biology of the immune-checkpoint receptor PD-1 and its ligands PD-L1/PD-L2. Structure 25, 1163–1174 (2017).

    Article  CAS  PubMed  Google Scholar 

  49. Chevalier, A. et al. Massively parallel de novo protein design for targeted therapeutics. Nature 550, 74–79 (2017).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  50. Davies, D. R. & Cohen, G. H. Interactions of protein antigens with antibodies. Proc. Natl Acad. Sci. USA 93, 7–12 (1996).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  51. Muyldermans, S. Nanobodies: natural single-domain antibodies. Annu. Rev. Biochem. 82, 775–797 (2013).

    Article  CAS  PubMed  Google Scholar 

  52. Schymkowitz, J. et al. The FoldX web server: an online force field. Nucleic Acids Res. 33, W382–W388 (2005).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  53. Evans, R. et al. Protein complex prediction with AlphaFold-Multimer. Preprint at bioRxiv https://doi.org/10.1101/2021.10.04.463034 (2021).

  54. Wei Yang, D. R. et al. Design of high-affinity binders to convex protein target sites. Preprint at bioRxiv https://doi.org/10.1101/2024.05.01.592114 (2024).

  55. Liu, X. et al. Targeting Trop-2 in solid tumors: a look into structures and novel epitopes. Front. Immunol. 14, 1332489 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  56. Ho, J. & Salimans, T. Classifier-free diffusion guidance. In NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2021).

  57. Kyte, J. & Doolittle, R. F. A simple method for displaying the hydropathic character of a protein. J. Mol. Biol. 157, 105–132 (1982).

    Article  CAS  PubMed  Google Scholar 

  58. Helen, M. & Berman, et al. Protein Data Bank. Nucleic Acids Res. 28, 235–242 (2000).

    Article  Google Scholar 

  59. Tomer Tsaban, J. K. et al. Harnessing protein folding neural networks for peptide–protein docking. Nat. Commun. 13, 176 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  60. Steinegger, M. & Söding, J. Mmseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat. Biotechnol. 35, 1026–1028 (2017).

    Article  CAS  PubMed  Google Scholar 

  61. Kunchur Guruprasad, B. V. B. R. & Madhusudan, W. P. Correlation between stability of a protein and its dipeptide composition: a novel approach for predicting in vivo stability of a protein from its primary sequence. Protein Eng. 4, 155–161 (1990).

    Article  Google Scholar 

  62. Chothia, C. & Janin, J. Principles of protein–protein recognition. Nature 256, 705–708 (1975).

    Article  CAS  PubMed  Google Scholar 

  63. Basu, S. & Wallner, B. Dockq: a quality measure for protein–protein docking models. PLoS ONE 11, e0161879 (2016).

    Article  PubMed  PubMed Central  Google Scholar 

  64. Mitternacht, S. Freesasa: an open source C library for solvent accessible surface area calculations. F1000Research 5, 189 (2016).

    Article  PubMed  PubMed Central  Google Scholar 

  65. Kingma, D. P. & Welling, M. Auto-encoding variational Bayes. Preprint at https://arxiv.org/abs/1312.6114 (2013).

  66. Golub, G. H. & Van Loan, C. F. Matrix Computations (JHU Press, 2013).

  67. Jonathan Ho, A. J. & Pieter Abbeel, D. Diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840–6851 (2020).

    Google Scholar 

  68. Kong, X., Huang, W. & Liu, Y. End-to-end full-atom antibody design. In Proc. 40th International Conference on Machine Learning (eds Krause, A. et al.) vol. 202, 17409–17429 (PMLR, 2023).

  69. John Jumper, R. E. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  70. Kong, X., Jia, Y., Huang, W. & Liu, Y. PepBench: dataset for protein-binding peptide design. Zenodo https://doi.org/10.5281/zenodo.13373108 (2024).

  71. Kong, X. kxz18/PepMimic: checkpoints. Zenodo https://doi.org/10.5281/zenodo.15699103 (2025).

Download references

Acknowledgements

This work is jointly supported by, National Key Plan for Scientific Research and Development of China (grant no. 2023YFC3043300, to J.M.), the Natural Science Foundation of Fujian Province (grant no. 2024J010027, to W.H.), the National Key R&D Program of China (grant no. 2022ZD0160502, to Y.L.) and the National Natural Science Foundation of China (grant no. 61925601, to Y.L.).

Author information

Authors and Affiliations

  1. Department of Computer Science and Technology, Tsinghua University, Beijing, China

    Xiangzhe Kong, Rui Jiao & Yang Liu

  2. Institute for AI Industry Research, Tsinghua University, Beijing, China

    Xiangzhe Kong, Rui Jiao, Wei-Ying Ma, Yang Liu & Jianzhu Ma

  3. Institute for Artificial Intelligence, Peking University, Beijing, China

    Haowei Lin

  4. School of Intelligence Science and Technology, Peking University, Beijing, China

    Haowei Lin

  5. Helixon US Inc., New York, NY, USA

    Ruihan Guo

  6. Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China

    Wenbing Huang

  7. Beijing Key Laboratory of Research on Large Models and Intelligent Governance, Beijing, China

    Wenbing Huang

  8. Department of Radiology and Nuclear Medicine, Xuanwu Hospital Capital Medical University, Beijing, China

    Zihua Wang

  9. Fujian Provincial Key Laboratory of Brain Aging and Neurodegenerative Diseases, School of Basic Medical Sciences, Fujian Medical University, Fuzhou, China

    Zihua Wang

  10. Department of Electronic Engineering, Tsinghua University, Beijing, China

    Jianzhu Ma

Authors
  1. Xiangzhe Kong
    View author publications

    Search author on:PubMed Google Scholar

  2. Rui Jiao
    View author publications

    Search author on:PubMed Google Scholar

  3. Haowei Lin
    View author publications

    Search author on:PubMed Google Scholar

  4. Ruihan Guo
    View author publications

    Search author on:PubMed Google Scholar

  5. Wenbing Huang
    View author publications

    Search author on:PubMed Google Scholar

  6. Wei-Ying Ma
    View author publications

    Search author on:PubMed Google Scholar

  7. Zihua Wang
    View author publications

    Search author on:PubMed Google Scholar

  8. Yang Liu
    View author publications

    Search author on:PubMed Google Scholar

  9. Jianzhu Ma
    View author publications

    Search author on:PubMed Google Scholar

Contributions

X.K. and J.M. conceived and designed the generative model with contributions from R.J. X.K. and R.J. processed the data for training and inference, as well as conducted the computational experiments, with help from R.G. to construct the AlphaFold filtering pipeline. Z.W. conducted the wet-lab experiments. X.K., Z.W. and J.M. analysed the results. X.K., R.J., Z.W. and J.M. wrote the manuscript, with contributions from H.L. The study was supervised by W.-Y.M., W.H., Y.L. and J.M.

Corresponding authors

Correspondence to Zihua Wang, Yang Liu or Jianzhu Ma.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Biomedical Engineering thanks Leyi Wei 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 Methods 1–4, Figs. 1–12, Tables 1–7 and Algorithms 1–9.

Reporting Summary

Supplementary Data

All peptides tested by SPRi.

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

Kong, X., Jiao, R., Lin, H. et al. Peptide design through binding interface mimicry with PepMimic. Nat. Biomed. Eng (2025). https://doi.org/10.1038/s41551-025-01507-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41551-025-01507-4

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