De novo design of luciferases using deep learning

Abstract De novo enzyme design has sought to introduce active sites and substrate-binding pockets that are predicted to catalyse a reaction of interest into geometrically compatible native scaffolds 1,2 , but has been limited by a lack of suitable protein structures and the complexity of native protein sequence–structure relationships. Here we describe a deep-learning-based ‘family-wide hallucination’ approach that generates large numbers of idealized protein structures containing diverse pocket shapes and designed sequences that encode them. We use these scaffolds to design artificial luciferases that selectively catalyse the oxidative chemiluminescence of the synthetic luciferin substrates diphenylterazine 3…

• NS
  National Science Foundation

  Awards: 1764328, OCI-1053575, 1053575, CHE-1764328
• HH
  Howard Hughes Medical Institute
• WR
  Washington Research Foundation
• UO
  University of Washington
• OP
  Open Philanthropy Project
• NN
  National Natural Science Foundation of China

  Award: 22103060
• NN
  Novo Nordisk
• NN
  Novo Nordisk Fonden
• NI
  National Institutes of Health

  Awards: OCI-1053575, U01 AI151698, AI151698
• NI
  National Institute of Allergy and Infectious Diseases

  Awards: U01 AI151698-01, U01 AI151698, AI151698
• NI
  National Institute of Biomedical Imaging and Bioengineering
• DO
  Division of Chemistry

  Awards: 1764328, CHE-1764328, 1053575