Discovering de novo peptide substrates for enzymes using machine learning.

Journal: Nature communications
Published Date: Dec 7, 2018

Abstract

The discovery of peptide substrates for enzymes with exclusive, selective activities is a central goal in chemical biology. In this paper, we develop a hybrid computational and biochemical method to rapidly optimize peptides for specific, orthogonal biochemical functions. The method is an iterative machine learning process by which experimental data is deposited into a mathematical algorithm that selects potential peptide substrates to be tested experimentally. Once tested, the algorithm uses the experimental data to refine future selections. This process is repeated until a suitable set of de novo peptide substrates are discovered. We employed this technology to discover orthogonal peptide substrates for 4'-phosphopantetheinyl transferase, an enzyme class that covalently modifies proteins. In this manner, we have demonstrated that machine learning can be leveraged to guide peptide optimization for specific biochemical functions not immediately accessible by biological screening techniques, such as phage display and random mutagenesis.

Authors

  • Lorillee Tallorin
    Department of Chemistry and Biochemistry, University of California San Diego, 9500 Gilman Drive, La Jolla, CA, 92093-0358, USA.
  • JiaLei Wang
    School of Operations Research and Information Engineering, Cornell University, 232 Rhodes Hall, Ithaca, NY, 14853-3801, USA.
  • Woojoo E Kim
    Department of Chemistry and Biochemistry, University of California San Diego, 9500 Gilman Drive, La Jolla, CA, 92093-0358, USA.
  • Swagat Sahu
    Department of Chemistry and Biochemistry, University of California San Diego, 9500 Gilman Drive, La Jolla, CA, 92093-0358, USA.
  • Nicolas M Kosa
    Department of Chemistry and Biochemistry, University of California San Diego, 9500 Gilman Drive, La Jolla, CA, 92093-0358, USA.
  • Pu Yang
    School of Operations Research and Information Engineering, Cornell University, 232 Rhodes Hall, Ithaca, NY, 14853-3801, USA.
  • Matthew Thompson
    Department of Chemistry and Biochemistry, University of California San Diego, 9500 Gilman Drive, La Jolla, CA, 92093-0358, USA.
  • Michael K Gilson
    Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California, San Diego, 9500 Gilman Drive, La Jolla, CA 92093, USA, mgilson@ucsd.edu.
  • Peter I Frazier
    School of Operations Research and Information Engineering, Cornell University, 232 Rhodes Hall, Ithaca, NY, 14853-3801, USA. pf98@cornell.edu.
  • Michael D Burkart
    Department of Chemistry and Biochemistry, University of California San Diego, 9500 Gilman Drive, La Jolla, CA, 92093-0358, USA. mburkart@ucsd.edu.
  • Nathan C Gianneschi
    Department of Chemistry and Biochemistry, University of California San Diego, 9500 Gilman Drive, La Jolla, CA, 92093-0358, USA. nathan.gianneschi@northwestern.edu.

Keywords

External Resources

Popular Topics
Recent Journals