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

This is the authors' abstract. We don't add key points for this paper.

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.