Development of machine learning models to predict inhibition of 3-dehydroquinate dehydratase

Chem Biol Drug Des. 2018 Aug;92(2):1468-1474. doi: 10.1111/cbdd.13312. Epub 2018 May 18.


In this study, we describe the development of new machine learning models to predict inhibition of the enzyme 3-dehydroquinate dehydratase (DHQD). This enzyme is the third step of the shikimate pathway and is responsible for the synthesis of chorismate, which is a natural precursor of aromatic amino acids. The enzymes of shikimate pathway are absent in humans, which make them protein targets for the design of antimicrobial drugs. We focus our study on the crystallographic structures of DHQD in complex with competitive inhibitors, for which experimental inhibition constant data is available. Application of supervised machine learning techniques was able to elaborate a robust DHQD-targeted model to predict binding affinity. Combination of high-resolution crystallographic structures and binding information indicates that the prevalence of intermolecular electrostatic interactions between DHQD and competitive inhibitors is of pivotal importance for the binding affinity against this enzyme. The present findings can be used to speed up virtual screening studies focused on the DHQD structure.

Keywords: 3-dehydroquinate dehydratase; crystallographic structures; drug design; machine learning; protein-ligand interactions; systems biology.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Area Under Curve
  • Binding Sites
  • Humans
  • Hydro-Lyases / antagonists & inhibitors
  • Hydro-Lyases / metabolism*
  • Machine Learning*
  • Molecular Docking Simulation
  • Protein Structure, Tertiary
  • ROC Curve
  • Shikimic Acid / chemistry
  • Shikimic Acid / metabolism
  • Static Electricity


  • Shikimic Acid
  • Hydro-Lyases
  • 3-dehydroquinate dehydratase