A multi-conformational virtual screening approach based on machine learning targeting PI3Kγ

Mol Divers. 2021 Aug;25(3):1271-1282. doi: 10.1007/s11030-021-10243-1. Epub 2021 Jun 23.

Abstract

Nowadays, more and more attention has been attracted to develop selective PI3Kγ inhibitors, but the unique structural features of PI3Kγ protein make it a very big challenge. In the present study, a virtual screening strategy based on machine learning with multiple PI3Kγ protein structures was developed to screen novel PI3Kγ inhibitors. First, six mainstream docking programs were chosen to evaluate their scoring power and screening power; CDOCKER and Glide show satisfactory reliability and accuracy against the PI3Kγ system. Next, virtual screening integrating multiple PI3Kγ protein structures was demonstrated to significantly improve the screening enrichment rate comparing to that with an individual protein structure. Last, a multi-conformational Naïve Bayesian Classification model with the optimal docking programs was constructed, and it performed a true capability in the screening of PI3Kγ inhibitors. Taken together, the current study could provide some guidance for the docking-based virtual screening to discover novel PI3Kγ inhibitors.

Keywords: Isoform-selective; Machine learning; Molecular docking; Naïve Bayesian Classification; PI3Kγ inhibitor; Virtual screening.

MeSH terms

  • Binding Sites
  • Class Ib Phosphatidylinositol 3-Kinase / chemistry*
  • Databases, Pharmaceutical
  • Drug Discovery
  • Ligands
  • Machine Learning*
  • Models, Molecular*
  • Molecular Conformation*
  • Molecular Docking Simulation
  • Molecular Dynamics Simulation
  • Molecular Structure
  • Phosphoinositide-3 Kinase Inhibitors / chemistry*
  • Phosphoinositide-3 Kinase Inhibitors / pharmacology
  • Protein Binding
  • ROC Curve
  • Structure-Activity Relationship

Substances

  • Ligands
  • Phosphoinositide-3 Kinase Inhibitors
  • Class Ib Phosphatidylinositol 3-Kinase
  • PIK3CG protein, human