One-shot design of functional protein binders with BindCraft

Martin Pačesa(SIB Swiss Institute of Bioinformatics), Lennart Nickel(SIB Swiss Institute of Bioinformatics), Christian Schellhaas(SIB Swiss Institute of Bioinformatics), Joseph Schmidt(SIB Swiss Institute of Bioinformatics), Ekaterina Pyatova(SIB Swiss Institute of Bioinformatics), Lucas Kissling(University of Zurich), Patrick Barendse(Wageningen University & Research), Jagrity Choudhury(University at Buffalo, State University of New York), Srajan Kapoor(University at Buffalo, State University of New York), Ana Alcaraz‐Serna(University of Lausanne), Yehlin Cho(Massachusetts Institute of Technology), Kourosh H. Ghamary(Visterra (United States)), Laura Vinué(Visterra (United States)), Brahm J. Yachnin(Visterra (United States)), Andrew M. Wollacott(Visterra (United States)), Stephen Buckley(SIB Swiss Institute of Bioinformatics), Adrie H. Westphal(Wageningen University & Research), Simon Lindhoud(Wageningen University & Research), Sandrine Georgeon(SIB Swiss Institute of Bioinformatics), Casper A. Goverde(SIB Swiss Institute of Bioinformatics), Georgios N. Hatzopoulos(École Polytechnique Fédérale de Lausanne), Pierre Gönczy(École Polytechnique Fédérale de Lausanne), Yannick D. Müller(University of Lausanne), Gerald Schwank(University of Zurich), Daan C. Swarts(Wageningen University & Research), Alex J. Vecchio(University at Buffalo, State University of New York), Bernard L. Schneider(École Polytechnique Fédérale de Lausanne), Sergey Ovchinnikov(IIT@MIT), Bruno E. Correia(SIB Swiss Institute of Bioinformatics)
Nature
August 27, 2025
Cited by 136Open Access
Full Text

Abstract

Protein–protein interactions are at the core of all key biological processes. However, the complexity of the structural features that determine protein–protein interactions makes their design challenging. Here we present BindCraft, an open-source and automated pipeline for de novo protein binder design with experimental success rates of 10–100%. BindCraft leverages the weights of AlphaFold2 (ref. 1) to generate binders with nanomolar affinity without the need for high-throughput screening or experimental optimization, even in the absence of known binding sites. We successfully designed binders against a diverse set of challenging targets, including cell-surface receptors, common allergens, de novo designed proteins and multi-domain nucleases, such as CRISPR–Cas9. We showcase the functional and therapeutic potential of designed binders by reducing IgE binding to birch allergen in patient-derived samples, modulating Cas9 gene editing activity and reducing the cytotoxicity of a foodborne bacterial enterotoxin. Last, we use cell-surface-receptor-specific binders to redirect adeno-associated virus capsids for targeted gene delivery. This work represents a significant advancement towards a ‘one design-one binder’ approach in computational design, with immense potential in therapeutics, diagnostics and biotechnology. BindCraft, an open-source, automated pipeline for de novo protein binder design with experimental success rates of 10–100%, leverages AlphaFold2 weights to generate binders with nanomolar affinity without the need for high-throughput screening.


Related Papers

No related papers found

Powered by citation graph analysis