Accurate de novo design of high-affinity protein binding macrocycles using deep learning
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
The development of macrocyclic binders to therapeutic proteins typically relies on large-scale screening methods that are resource-intensive and provide little control over binding mode. Despite considerable progress in physics-based methods for peptide design and deep-learning methods for protein design, there are currently no robust approaches for de novo design of protein-binding macrocycles. Here, we introduce RFpeptides, a denoising diffusion-based pipeline for designing macrocyclic peptide binders against protein targets of interest. We test 20 or fewer designed macrocycles against each of four diverse proteins and obtain medium to high-affinity binders against all selected targets. Designs against MCL1 and MDM2 demonstrate K D between 1-10 μM, and the best anti-GABARAP macrocycle binds with a K D of 6 nM and a sub-nanomolar IC 50 in vitro . For one of the targets, RbtA, we obtain a high-affinity binder with K D < 10 nM despite starting from the target sequence alone due to the lack of an experimentally determined target structure. X-ray structures determined for macrocycle-bound MCL1, GABARAP, and RbtA complexes match very closely with the computational design models, with three out of the four structures demonstrating Ca RMSD of less than 1.5 Å to the design models. In contrast to library screening approaches for which determining binding mode can be a major bottleneck, the binding modes of RFpeptides-generated macrocycles are known by design, which should greatly facilitate downstream optimization. RFpeptides thus provides a powerful framework for rapid and custom design of macrocyclic peptides for diagnostic and therapeutic applications.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Watson, J. L., Juergens, D., Bennett, N. R., Trippe, B. L., Yim, J., Eisenach, H. E., Ahern, W., Borst, A. J., Ragotte, R. J., Milles, L. F., et al. (2022) · doi:10.1101/2022.12.09.519842 · Cited by 2,369
Self-citation
Research works printed but not linked: 36
- 10.1021/jacs.8b13178 · DOI · Paper page
- 10.1038/s41573-020-00135-8 · DOI · Paper page
- 10.1016/j.ejmech.2015.01.014 · DOI · Paper page
- 10.1038/s41573-020-00114-z · DOI · Paper page
- 10.1016/j.cell.2022.07.019 · DOI · Paper page
- 10.1038/nature19791 · DOI · Paper page
- 10.1126/science.aap7577 · DOI · Paper page
- 10.1073/pnas.2012800118 · DOI · Paper page
- 10.1038/s41467-021-23609-8 · DOI · Paper page
- 10.1038/s41467-023-43718-w · DOI
- 10.1101/2023.02.25.529956 · DOI · Paper page
- Grambow, C. A. , Weir, H. , Cunningham, C. N. , Biancalani, T. & Chuang, K. V. CREMP: Conformer-Rotamer Ensembles of Macrocyclic Peptides for Machine Learning. arXiv [q-bio.BM] (2023). · DOI · Paper page
- Zhang, C. et al. HighFold: accurately predicting structures of cyclic peptides and complexes with head-to-tail and disulfide bridge constraints. Brief. Bioinform. 25, (2024). · DOI · Paper page
- 10.1038/s42003-023-05464-z · DOI · Paper page
- 10.1021/acscentsci.3c01488 · DOI
- Li, Q. , Vlachos, E. N. & Bryant, P. Design of linear and cyclic peptide binders of different lengths from protein sequence information. bioRxiv (2024). · DOI
- 10.1038/s41586-023-06415-8 · DOI · Paper page
- 10.1126/science.abj8754 · doi:10.1126/science.abj8754 · Paper page
- 10.1038/s41586-023-06953-1 · DOI · Paper page
- 10.1126/sci-ence.adl2528 · doi:10.1126/sci-ence.adl2528
- 10.1038/s42003-021-02564-6 · DOI · Paper page
- 10.1038/s41592-020-0848-2 · DOI · Paper page
- 10.1126/science.274.5289.948 · DOI · Paper page
- 10.1016/j.yexcr.2015.02.003 · DOI · Paper page
- 10.1021/jacs.2c04699 · DOI
- 2022, The AUTOTAC chemical biology platform for targeted protein degradation via the autophagy-lysosome system, Nat. Commun, 13, 904, 10.1038/s41467-022-28520-4 · DOI · Paper page
- 10.1080/15548627.2015.1111503 · DOI · Paper page
- 10.1016/j.jmb.2008.06.086 · DOI
- 10.1109/MCSE.2007.55 · DOI · Paper page
- 10.21105/joss.03021 · DOI · Paper page
- 10.1002/PRO.3943 · DOI · Paper page
- van der Maaten, L. Visualizing Data using t-SNE. https://www.jmlr.org/papers/volume9/vandermaaten08a/vandermaaten08a.pdf?fbcl (2008).
- 10.1093/nar/gki524 · DOI · Paper page
- Pedregosa, F. et al. Scikit-learn: Machine Learning in Python. arXiv [cs.LG] 2825–2830 (2012).
- 10.1101/2023.12.22.573103 · DOI
- 10.1093/bioinformatics/16.9.776 · DOI · Paper page
Metadata
- Authors
- Rettie, S. A., Juergens, D., Adebomi, V., Bueso, Y. F., Zhao, Q., Leveille, A. N., Liu, A., Bera, A. K., Wilms, J. A., Üffing, A., Kang, A., Brackenbrough, E., Lamb, M., Gerben, S. R., Murray, A., Levine, P. M., Schneider, M., Vasireddy, V., Ovchinnikov, S., Weiergräber, O. H., Willbold, D., Kritzer, J. A., Mougous, J. D., Baker, D., DiMaio, F., & Bhardwaj, G.
- Publisher
- openRxiv
- Published
- 2024-11-18
- Cited by
- 19
- References
- 1
- Type
- Preprint
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Accurate de novo design of high-affinity protein binding macrocycles using deep learning. https://app.cochat.ai/papers/10.1101/2024.11.18.622547
- The paper
- Rettie, S. A., Juergens, D., Adebomi, V., Bueso, Y. F., Zhao, Q., Leveille, A. N., Liu, A., Bera, A. K., Wilms, J. A., Üffing, A., Kang, A., Brackenbrough, E., Lamb, M., Gerben, S. R., Murray, A., Levine, P. M., Schneider, M., Vasireddy, V., Ovchinnikov, S., . . . Bhardwaj, G. (2024). Accurate de novo design of high-affinity protein binding macrocycles using deep learning. https://doi.org/10.1101/2024.11.18.622547
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.