Hybrid receptor structure/ligand-based docking and activity prediction in ICM: development and evaluation in D3R Grand Challenge 3

J Comput Aided Mol Des. 2019 Jan;33(1):35-46. doi: 10.1007/s10822-018-0139-5. Epub 2018 Aug 9.


In context of D3R Grand Challenge 3 we have investigated several ligand activity prediction protocols that combined elements of a physics-based energy function (ICM VLS score) and the knowledge-based Atomic Property Field 3D QSAR approach. Activity prediction models utilized poses produced by ICM-Dock with ligand bias and 4D receptor conformational ensembles (LigBEnD). Hybrid APF/P (APF/Physics) models were superior to pure physics- or knowledge-based models in our preliminary tests using rigorous three-fold clustered cross-validation and later proved successful in the blind prediction for D3R GC3 sets, consistently performing well across four different targets. The results demonstrate that knowledge-based and physics-based inputs into the machine-learning activity model can be non-redundant and synergistic.

Keywords: 3D QSAR; APF; Computer-aided drug design; D3R; D3R GC3; Docking; ICM.

MeSH terms

  • Binding Sites
  • Cathepsins / chemistry*
  • Computer-Aided Design
  • Crystallography, X-Ray
  • Databases, Protein
  • Drug Design
  • Ligands
  • Machine Learning
  • Molecular Docking Simulation / methods*
  • Protein Binding
  • Protein Conformation
  • Quantitative Structure-Activity Relationship
  • Thermodynamics


  • Ligands
  • Cathepsins
  • cathepsin S