EUVIMEDEUVIMED entdecken
Open Access

Scalable protein design using optimization in a relaxed sequence space

Christopher Frank iD, Ali Khoshouei iD, Lara Fuβ iD, Dominik Schiwietz iD, Dominik Putz, Lara Weber iD, Zhixuan Zhao iD, Motoyuki Hattori iD, Shihao Feng iD, Yosta de Stigter iD, Sergey Ovchinnikov iD, Hendrik Dietz iD

Science · 25.10.2024 · 386 (6720) · 439-445

DOI: 10.1126/science.adq1741 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science, erschienen am 25.10.2024. Verfasst von Christopher Frank und 11 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory for Biomolecular Nanotechnology, Department of Biosciences, School of Natural Sciences Technical University of Munich, 85748 Garching, Ger…. Hauptthemen laut MEDLINE: Machine Learning, Protein Engineering, Proteins. Die Arbeit wurde bisher 99-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning (ML)–based design approaches have advanced the field of de novo protein design, with diffusion-based generative methods increasingly dominating protein design pipelines. Here, we report a “hallucination”-based protein design approach that functions in relaxed sequence space, enabling the efficient design of high-quality protein backbones over multiple scales and with broad scope of application without the need for any form of retraining. We experimentally produced and characterized more than 100 proteins. Three high-resolution crystal structures and two cryo–electron microscopy density maps of designed single-chain proteins comprising up to 1000 amino acids validate the accuracy of the method. Our pipeline can also be used to design synthetic protein-protein interactions, as validated experimentally by a set of protein heterodimers. Relaxed sequence optimization offers attractive performance with respect to designability, scope of applicability for different design problems, and scalability across protein sizes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningProtein EngineeringProteinsAmino Acid SequenceCryoelectron MicroscopyCrystallography, X-RayModels, MolecularProtein ConformationProtein Multimerization

Substanzen

Proteins

Autor:innen und Institutionen

  • Laboratory for Biomolecular Nanotechnology, Department of Biosciences, School of Natural Sciences Technical University of Munich, 85748 Garching, Germany.
  • Munich Institute of Biomedical Engineering, Technical University of Munich, 85748 Garching, Germany.
  • State Key Laboratory of Genetic Engineering, Shanghai Key Laboratory of Bioactive Small Molecules, Collaborative Innovation Center of Genetics and Development, Department of Department of Physiology and Neurobiology, Sc…
  • Changping Laboratory, Beijing 102200, China.
  • Faculty of Applied Sciences, Harvard University, Cambridge, MA, USA.
  • Department of Biology, Massachusetts Institute of Technology, Cambridge, MA, USA.

ORCID-Profile: Christopher Frank, Ali Khoshouei, Lara Fuβ, Dominik Schiwietz, Lara Weber, Zhixuan Zhao, Motoyuki Hattori, Shihao Feng, Yosta de Stigter, Sergey Ovchinnikov, Hendrik Dietz

Förderung

  • NIH HHS

Zitieren

APA

Frank, C., Khoshouei, A., Fuβ, L., Schiwietz, D., Putz, D., Weber, L., Zhao, Z., Hattori, M., Feng, S., de Stigter, Y., Ovchinnikov, S., & Dietz, H. (2024). Scalable protein design using optimization in a relaxed sequence space. Science, 386(6720), 439-445. https://doi.org/10.1126/science.adq1741

Vancouver

Frank C, Khoshouei A, Fuβ L, Schiwietz D, Putz D, Weber L, et al. Scalable protein design using optimization in a relaxed sequence space. Science. 2024;386(6720):439-445. doi:10.1126/science.adq1741

BibTeX
@article{Frank2024,
  author = {Frank, Christopher and Khoshouei, Ali and Fuβ, Lara and Schiwietz, Dominik and Putz, Dominik and Weber, Lara and Zhao, Zhixuan and Hattori, Motoyuki and Feng, Shihao and de Stigter, Yosta and Ovchinnikov, Sergey and Dietz, Hendrik},
  title = {Scalable protein design using optimization in a relaxed sequence space},
  journal = {Science},
  year = {2024},
  volume = {386},
  number = {6720},
  pages = {439--445},
  doi = {10.1126/science.adq1741}
}
Kostenlos starten →