Top-down design of protein architectures with reinforcement learning.

Journal: Science (New York, N.Y.)
PMID: 37079676

Abstract

As a result of evolutionary selection, the subunits of naturally occurring protein assemblies often fit together with substantial shape complementarity to generate architectures optimal for function in a manner not achievable by current design approaches. We describe a "top-down" reinforcement learning-based design approach that solves this problem using Monte Carlo tree search to sample protein conformers in the context of an overall architecture and specified functional constraints. Cryo-electron microscopy structures of the designed disk-shaped nanopores and ultracompact icosahedra are very close to the computational models. The icosohedra enable very-high-density display of immunogens and signaling molecules, which potentiates vaccine response and angiogenesis induction. Our approach enables the top-down design of complex protein nanomaterials with desired system properties and demonstrates the power of reinforcement learning in protein design.

Authors

  • Isaac D Lutz
    Department of Biochemistry, University of Washington, Seattle, WA, USA.
  • Shunzhi Wang
    Department of Biochemistry, University of Washington, Seattle, WA, USA.
  • Christoffer Norn
    Department of Biochemistry, University of Washington, Seattle, WA 98105.
  • Alexis Courbet
    Department of Biochemistry, University of Washington, Seattle, WA, USA.
  • Andrew J Borst
    Department of Biochemistry, University of Washington, Seattle, WA, USA.
  • Yan Ting Zhao
    Department of Biochemistry, University of Washington, Seattle, WA, USA.
  • Annie Dosey
    Department of Biochemistry, University of Washington, Seattle, WA, USA.
  • Longxing Cao
    Department of Biochemistry and Institute for Protein Design, University of Washington, Seattle, Washington, United States of America.
  • Jinwei Xu
  • Elizabeth M Leaf
    Department of Biochemistry, University of Washington, Seattle, WA, USA.
  • Catherine Treichel
    Department of Biochemistry, University of Washington, Seattle, WA, USA.
  • Patrisia Litvicov
    Department of Biochemistry, University of Washington, Seattle, WA, USA.
  • Zhe Li
  • Alexander D Goodson
    Department of Biochemistry, University of Washington, Seattle, WA, USA.
  • Paula Rivera-Sánchez
    BioInnovation Institute, DK2200 Copenhagen N, Denmark.
  • Ana-Maria Bratovianu
    BioInnovation Institute, DK2200 Copenhagen N, Denmark.
  • Minkyung Baek
    Department of Biochemistry and Institute for Protein Design, University of Washington, Washington, WA, USA.
  • Neil P King
    Department of Biochemistry, University of Washington, Seattle, WA, USA.
  • Hannele Ruohola-Baker
    Department of Biochemistry, University of Washington, Seattle, WA, USA.
  • David Baker
    Department of Biochemistry, University of Washington, Seattle, Washington.

Keywords

External Resources

Popular Topics
Recent Journals