Tracing nature's template: Using statistical machine learning to evolve biocatalysts (2012–2015)

Abstract:
Proteins like the P450 enzymes are highly versatile biological catalysts with untapped potential to improve the efficiency of chemical industries, lessen their environmental impact, reduce drug development costs, and help to remediate environmental contamination. We will use statistical machine learning to reveal how to redesign proteins for industrial use based on the examples Nature has refined over millions of years. By making and characterizing experimentally a large library of mutant proteins we can use sophisticated statistical methods to detect previously hidden relationships between protein sequence and structural stability, then mine this data using machine learning to predict how to best design commercially useful proteins.
Grant type:
ARC Discovery Projects
Researchers:
  • Associate Professor
    School of Chemistry and Molecular Biosciences
    Faculty of Science
    Affiliate Research Fellow
    Institute for Molecular Bioscience
  • Professor
    School of Chemistry and Molecular Biosciences
    Faculty of Science
    Affiliated Professor
    Centre for Crop Science
    Queensland Alliance for Agriculture and Food Innovation
Funded by:
Australian Research Council