CoChat

De novo design of peptide binders to conformationally diverse targets with contrastive language modeling

Bhat, Suhaas, Palepu, Kalyan, Hong, Lauren, Mao, Joey, Ye, Tianzheng, Iyer, Rema, Zhao, Lin, Chen, Tianlai, Vincoff, Sophia, Watson, Rio, Wang, Tian Z., Srijay, Divya, Kavirayuni, Venkata Srikar, Kholina, Kseniia, Goel, Shrey, Vure, Pranay, Deshpande, Aniruddha J., Soderling, Scott H., DeLisa, Matthew P., Chatterjee, Pranam · 2025 · Science Advances
Cited by 82

The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.

Abstract

Designing binders to target undruggable proteins presents a formidable challenge in drug discovery. In this work, we provide an algorithmic framework to design short, target-binding linear peptides, requiring only the amino acid sequence of the target protein. To do this, we propose a process to generate naturalistic peptide candidates through Gaussian perturbation of the peptidic latent space of the ESM-2 protein language model and subsequently screen these novel sequences for target-selective interaction activity via a contrastive language-image pretraining (CLIP)–based contrastive learning architecture. By integrating these generative and discriminative steps, we create a Peptide Prioritization via CLIP (PepPrCLIP) pipeline and validate highly ranked, target-specific peptides experimentally, both as inhibitory peptides and as fusions to E3 ubiquitin ligase domains. PepPrCLIP-derived constructs demonstrate functionally potent binding and degradation of conformationally diverse, disease-driving targets in vitro. In total, PepPrCLIP empowers the modulation of previously inaccessible proteins without reliance on stable and ordered tertiary structures.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1126/sciadv.adr8638

Cites

22 of 22 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Research works printed but not linked: 38

  1. 10.1038/s41392-022-00966-4 · DOI · Paper page
  2. 10.1016/j.copbio.2022.102807 · DOI
  3. 10.1186/1471-2199-4-10 · DOI
  4. 10.1074/jbc.M113.544825 · DOI · Paper page
  5. 10.1021/acssynbio.1c00357 · DOI · Paper page
  6. 10.1016/j.chembiol.2020.06.013 · DOI · Paper page
  7. 10.1186/s12934-018-0881-3 · DOI
  8. 10.3389/fimmu.2020.01986 · DOI · Paper page
  9. 10.1038/s41586-023-05993-x · DOI · Paper page
  10. C. Liu K. Wu H. Choi H. Han X. Zhang J. L. Watson S. Shijo A. K. Bera A. Kang E. Brackenbrough B. Coventry D. R. Hick A. N. Hoofnagle P. Zhu X. Li J. Decarreau S. R. Gerben W. Yang X. Wang M. Lamp A. Murray M. Bauer D. Baker Diffusing protein binders to intrinsically disordered proteins. bioRxiv 603789 [Preprint]. 16 July 2024. · DOI · Paper page
  11. 10.1126/science.ade2574 · doi:10.1126/science.ade2574 · Paper page
  12. A. Elnaggar H. Essam W. Salah-Eldin W. Moustafa M. Elkerdawy C. Rochereau B. Rost Ankh ☥: Optimized protein language model unlocks general-purpose modelling. bioRxiv 524265 [Preprint]. 18 January 2023. · DOI · Paper page
  13. 10.1038/s41587-022-01618-2 · DOI · Paper page
  14. A. Radford J. W. Kim C. Hallacy A. Ramesh G. Goh S. Agarwal G. Sastry A. Askell P. Mishkin J. Clark G. Krueger I. Sutskever Learning transferable visual models from natural language supervision. arXiv:2103.00020 (2021). · arXiv
  15. A. Ramesh P. Dhariwal A. Nichol C. Chu M. Chen Hierarchical text-conditional image generation with CLIP latents. arXiv:2204.06125 (2022). · arXiv
  16. 10.1093/nar/28.1.235 · DOI · Paper page
  17. 10.1038/s42003-022-03445-2 · DOI · Paper page
  18. 10.1186/s12859-020-03546-x · DOI · Paper page
  19. 10.3389/fbinf.2022.959160 · DOI · Paper page
  20. 10.1038/s42003-022-03604-5 · DOI · Paper page
  21. 10.1038/s42003-020-01470-7 · DOI · Paper page
  22. 10.1038/s42003-023-05464-z · DOI · Paper page
  23. K. Palepu M. Ponnapati S. Bhat E. Tysinger T. Stan G. Brixi S. R. T. Koseki P. Chatterjee Design of peptide-based protein degraders via contrastive deep learning. bioRxiv 493169 [Preprint]. 24 May 2022. · DOI · Paper page
  24. T. Chen S. Pertsemlidis R. Watson V. S. Kavirayuni A. Hsu P. Vure R. Pulugurta S. Vincoff L. Hong T. Wang V. Yudistyra E. Haarer L. Zhao P. Chatterjee PepMLM: Target sequence-conditioned generation of peptide binders via masked language modeling. arXiv:2310.03842 (2023). · arXiv
  25. 10.18632/oncotarget.15687 · DOI · Paper page
  26. 10.1126/science.275.5307.1784 · DOI · Paper page
  27. 10.1002/cncr.27555 · DOI · Paper page
  28. 10.32074/1591-951X-213 · DOI · Paper page
  29. 10.3389/fonc.2019.01078 · DOI
  30. 10.1016/j.ccell.2018.05.002 · DOI · Paper page
  31. S. Vincoff S. Goel K. Kholina R. Pulugurta P. Vure P. Chatterjee FusOn-pLM: A fusion oncoprotein-specific language model via focused probabilistic masking. bioRxiv 597245 [Preprint]. 4 June 2024. · DOI
  32. 10.1038/s41586-023-05909-9 · DOI · Paper page
  33. 10.1126/science.adf2465 · DOI · Paper page
  34. H. Touvron L. Martin K. Stone P. Albert A. Almahairi Y. Babaei N. Bashlykov S. Batra P. Bhargava S. Bhosale D. Bikel L. Blecher C. C. Ferrer M. Chen G. Cucurull D. Esiobu J. Fernandes J. Fu W. Fu B. Fuller C. Gao V. Goswami N. Goyal A. Hartshorn S. Hosseini R. Hou H. Inan M. Kardas V. Kerkez M. Khabsa I. Kloumann A. Korenev P. S. Koura M.-A. Lachaux T. Lavril J. Lee D. Liskovich Y. Lu Y. Mao X. Martinet T. Mihaylov P. Mishra I. Molybog Y. Nie A. Poulton J. Reizenstein R. Rungta K. Saladi A. Schelten R. Silva E. M. Smith R. Subramanian X. E. Tan B. Tang R. Taylor A. Williams J. X. Kuan P. Xu Z. Yan I. Zarov Y. Zhang A. Fan M. Kambadur S. Narang A. Rodriguez R. Stojnic S. Edunov T. Scialom Llamae 2: Open foundation and fine-tuned chat models. arXiv:2307.09288 (2023). · arXiv
  35. A. Gu T. Dao Mamba: Linear-time sequence modeling with selective state spaces. arXiv:2312.00752 (2023). · arXiv
  36. S. S. Sahoo M. Arriola Y. Schiff A. Gokaslan E. Marroquin J. T. Chiu A. Rush V. Kuleshov Simple and effective masked diffusion language models. arXiv:2406.07524 (2024). · arXiv
  37. Z. Peng B. Schussheim P. Chatterjee PTM-Mamba: A PTM-aware protein language model with bidirectional gated Mamba blocks. bioRxiv 581983 [Preprint]. 29 February 2024. · DOI
  38. 10.1038/s41592-022-01488-1 · doi:10.1038/s41592-022-01488-1 · Paper page

Cited by

See all 82

Metadata

Authors
Bhat, S., Palepu, K., Hong, L., Mao, J., Ye, T., Iyer, R., Zhao, L., Chen, T., Vincoff, S., Watson, R., Wang, T. Z., Srijay, D., Kavirayuni, V. S., Kholina, K., Goel, S., Vure, P., Deshpande, A. J., Soderling, S. H., DeLisa, M. P., & Chatterjee, P.
Venue
Science Advances
Published
2025-01-24
Volume
11
Issue
4
ISSN
2375-2548
Cited by
82
References
22
Language
en

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

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.