EUVIMEDEUVIMED entdecken
Open Access

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

Suhaas Bhat iD, Kalyan Palepu, Lauren Hong, Joey Mao iD, Tianzheng Ye iD, Rema Iyer, Lin Zhao iD, Tianlai Chen iD, Sophia Vincoff iD, Rio Watson, Tian Z Wang, Divya Srijay und 8 weitere

Science Advances · 24.01.2025 · 11 (4)

DOI: 10.1126/sciadv.adr8638 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 24.01.2025. Verfasst von Suhaas Bhat und 19 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Duke University, Durham, NC, USA. Hauptthemen laut MEDLINE: Peptides, Drug Design. Die Arbeit wurde bisher 82-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS, NIMH NIH HHS, NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PeptidesDrug DesignProtein BindingHumansAlgorithmsProtein ConformationModels, MolecularDrug DiscoveryAmino Acid Sequence

Substanzen

Peptides

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Duke University, Durham, NC, USA.
  • Department of Cell Biology, Duke University, Durham, NC, USA.
  • Robert F. Smith School of Chemical and Biomolecular Engineering, Cornell University, Ithaca, NY, USA.
  • Cancer Genome and Epigenetics Program, Sanford Burnham Prebys Institute, San Diego, CA, USA.
  • Meinig School of Biomedical Engineering, Cornell University, Ithaca, NY, USA.
  • Cornell Institute of Biotechnology, Cornell University, Ithaca, NY, USA.

ORCID-Profile: Suhaas Bhat, Joey Mao, Tianzheng Ye, Lin Zhao, Tianlai Chen, Sophia Vincoff, Aniruddha J Deshpande, Scott H Soderling, Matthew P DeLisa, Pranam Chatterjee

Förderung

  • NCI NIH HHS
  • NIMH NIH HHS
  • NIH HHS

Zitieren

APA

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. (2025). De novo design of peptide binders to conformationally diverse targets with contrastive language modeling. Science Advances, 11(4). https://doi.org/10.1126/sciadv.adr8638

Vancouver

Bhat S, Palepu K, Hong L, Mao J, Ye T, Iyer R, et al. De novo design of peptide binders to conformationally diverse targets with contrastive language modeling. Science Advances. 2025;11(4). doi:10.1126/sciadv.adr8638

BibTeX
@article{Bhat2025,
  author = {Bhat, Suhaas and Palepu, Kalyan and Hong, Lauren and Mao, Joey and Ye, Tianzheng and Iyer, Rema and Zhao, Lin and Chen, Tianlai and Vincoff, Sophia and Watson, Rio and Wang, Tian Z and Srijay, Divya and Kavirayuni, Venkata Srikar and Kholina, Kseniia and Goel, Shrey and Vure, Pranay and Deshpande, Aniruddha J and Soderling, Scott H and DeLisa, Matthew P and Chatterjee, Pranam},
  title = {De novo design of peptide binders to conformationally diverse targets with contrastive language modeling},
  journal = {Science Advances},
  year = {2025},
  volume = {11},
  number = {4},
  doi = {10.1126/sciadv.adr8638}
}
Kostenlos starten →