Virtual Screening of Small Molecules Targeting BCL2 with Machine Learning, Molecular Docking, and MD Simulation

Biomolecules. 2024 May 1;14(5):544. doi: 10.3390/biom14050544.

Abstract

This study aimed to identify potential BCL-2 small molecule inhibitors using deep neural networks (DNN) and random forest (RF), algorithms as well as molecular docking and molecular dynamics (MD) simulations to screen a library of small molecules. The RF model classified 61% (2355/3867) of molecules as 'Active'. Further analysis through molecular docking with Vina identified CHEMBL3940231, CHEMBL3938023, and CHEMBL3947358 as top-scored small molecules with docking scores of -11, -10.9, and 10.8 kcal/mol, respectively. MD simulations validated these compounds' stability and binding affinity to the BCL2 protein.

Keywords: BCL2; cancer therapeutics; small molecules; virtual screening.

MeSH terms

  • Humans
  • Machine Learning*
  • Molecular Docking Simulation*
  • Molecular Dynamics Simulation*
  • Protein Binding
  • Proto-Oncogene Proteins c-bcl-2* / antagonists & inhibitors
  • Proto-Oncogene Proteins c-bcl-2* / chemistry
  • Proto-Oncogene Proteins c-bcl-2* / metabolism
  • Small Molecule Libraries* / chemistry
  • Small Molecule Libraries* / pharmacology

Substances

  • Proto-Oncogene Proteins c-bcl-2
  • Small Molecule Libraries
  • BCL2 protein, human

Grants and funding

This research received no external funding.