Deep learning-guided design of dynamic proteins.

Journal: Science (New York, N.Y.)
Published Date: May 22, 2025

Abstract

Deep learning has advanced the design of static protein structures, but the controlled conformational changes that are hallmarks of natural signaling proteins have remained inaccessible to de novo design. Here, we describe a general deep learning-guided approach for de novo design of dynamic changes between intradomain geometries of proteins, similar to switch mechanisms prevalent in nature, with atomic-level precision. We solve four structures that validate the designed conformations, demonstrate modulation of the conformational landscape by orthosteric ligands and allosteric mutations, and show that physics-based simulations are in agreement with deep-learning predictions and experimental data. Our approach demonstrates that new modes of motion can now be realized through de novo design and provides a framework for constructing biology-inspired, tunable, and controllable protein signaling behavior de novo.

Authors

  • Amy B Guo
    The UC Berkeley-UCSF Graduate Program in Bioengineering, University of California, San Francisco, San Francisco, CA, USA.
  • Deniz Akpinaroglu
    Department of Bioengineering, University of California, Merced, CA, United States of America.
  • Christina A Stephens
    Department of Pharmaceutical Chemistry, University of California, San Francisco, San Francisco, CA, USA.
  • Michael Grabe
    Department of Pharmaceutical Chemistry, University of California, San Francisco, San Francisco, CA, USA.
  • Colin A Smith
    Department of Chemistry, Wesleyan University, Middletown, CT, USA.
  • Mark J S Kelly
    Department of Pharmaceutical Chemistry, University of California, San Francisco, San Francisco, CA, USA.
  • Tanja Kortemme
    UC Berkeley-UCSF Graduate Program in Bioengineering, University of California, San Francisco, CA 94158.

Keywords

External Resources

Popular Topics
Recent Journals