The accuracy of SCUBA-D, a protein backbone structure diffusion model trained independently and orthogonally to existing protein structure prediction networks, is confirmed by the X-ray structures of 16 designed proteins and a protein complex, and by experimental validation of designed heme-binding proteins and Ras-binding proteins.
This is a preview of subscription content, access via your institution
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$32.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 print issues and online access
$259.00 per year
only $21.58 per issue
Buy this article
- Purchase on SpringerLink
- Instant access to the full article PDF.
USD 39.95
Prices may be subject to local taxes which are calculated during checkout
References
Kortemme, T. De novo protein design — from new structures to programmable functions. Cell 187, 526–544 (2024). This review article presents current advances in and the future potential of de novo protein structure and function design.
Watson, J. L. et al. De novo design of protein structure and function with RFdiffusion. Nature 620, 1089–1100 (2023). This paper reports the development of RFdiffusion, a fine-tuned generative model for de novo protein design.
Baek, M. et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science 373, 871–876 (2021). This paper reports the development of RoseTTAFold, a three-track neural network for protein structure and interaction prediction.
Ingraham, J. B. et al. Illuminating protein space with a programmable generative model. Nature 623, 1070–1078 (2023). This paper reports the development of Chroma, a freshly trained generative model for de novo protein design.
Huang, B. et al. A backbone-centred energy function of neural networks for protein design. Nature 602, 523–528 (2022). This paper reports the development of SCUBA, a backbone-centered energy function using neural networks for template-free protein design.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This is a summary of: Liu, Y. et al. De novo protein design with a denoising diffusion network independent of pretrained structure prediction models. Nat. Methods https://doi.org/10.1038/s41592-024-02437-w (2024).
Rights and permissions
About this article
Cite this article
SCUBA-D: a freshly trained diffusion model generates high-quality protein structures. Nat Methods 21, 1990–1991 (2024). https://doi.org/10.1038/s41592-024-02465-6
Published:
Version of record:
Issue date:
DOI: https://doi.org/10.1038/s41592-024-02465-6
