Neural network conditioned to produce thermophilic protein sequences can increase thermal stability.

Journal: Scientific reports
PMID:

Abstract

This work presents Neural Optimization for Melting-temperature Enabled by Leveraging Translation (NOMELT), a novel approach for designing and ranking high-temperature stable proteins using neural machine translation. The model, trained on over 4 million protein homologous pairs from organisms adapted to different temperatures, demonstrates promising capability in targeting thermal stability. A designed variant of the Drosophila melanogaster Engrailed Homeodomain shows a melting temperature increase of 15.5 K. Furthermore, NOMELT achieves zero-shot predictive capabilities in ranking experimental melting and half-activation temperatures across a number of protein families. It achieves this without requiring extensive homology data or massive training datasets as do existing zero-shot predictors by specifically learning thermophilicity, as opposed to all natural variation. These findings underscore the potential of leveraging organismal growth temperatures in context-dependent design of proteins for enhanced thermal stability.

Authors

  • Evan Komp
    Chemical Engineering, University of Washington, Seattle, WA, USA. komp.evan@gmail.com.
  • Christian Phillips
    Chemistry, University of Washington, Seattle, WA, USA.
  • Lauren M Lee
    Department of Biology, Santa Clara University, Santa Clara, CA, USA.
  • Shayna M Fallin
    Department of Biology, Santa Clara University, Santa Clara, CA, USA.
  • Humood N Alanzi
    Chemical Engineering, University of Washington, Seattle, WA, USA.
  • Marlo Zorman
    Department of Chemistry, The University of Vermont, Burlington, VT 05403.
  • Michelle E McCully
    Department of Biology, Santa Clara University, Santa Clara, CA, USA.
  • David A C Beck
    Department of Chemical Engineering, University of Washington, Seattle, Washington 98195, USA; email: dacb@uw.edu, jpfaendt@uw.edu.