Machine learning-based prediction of drug and ligand binding in BCL-2 variants through molecular dynamics

John R Hamre 3rd; Dmitri K Klimov; Matthew D McCoy; M Saleet Jafri

doi:10.1016/j.compbiomed.2021.105060

Machine learning-based prediction of drug and ligand binding in BCL-2 variants through molecular dynamics

Comput Biol Med. 2022 Jan:140:105060. doi: 10.1016/j.compbiomed.2021.105060. Epub 2021 Nov 27.

Authors

John R Hamre 3rd¹, Dmitri K Klimov², Matthew D McCoy³, M Saleet Jafri⁴

Affiliations

¹ School of Systems Biology, George Mason University, Manassas, VA, USA. Electronic address: johnhamre3@gmail.com.
² School of Systems Biology, George Mason University, Manassas, VA, USA. Electronic address: dklimov@gmu.edu.
³ Innovation Center for Biomedical Informatics, Department of Oncology, Georgetown University Medical Center, Georgetown University, Washington DC, USA. Electronic address: mdm299@georgetown.edu.
⁴ School of Systems Biology, George Mason University, Fairfax, VA and Center for Biomedical Technology and Engineering, University of Maryland School of Medicine, Baltimore, MD, USA. Electronic address: sjafri@gmu.edu.

PMID: 34920365
DOI: 10.1016/j.compbiomed.2021.105060

Abstract

Venetoclax is a BH3 (BCL-2 Homology 3) mimetic used to treat leukemia and lymphoma by inhibiting the anti-apoptotic BCL-2 protein thereby promoting apoptosis of cancerous cells. Acquired resistance to Venetoclax via specific variants in BCL-2 is a major problem for the successful treatment of cancer patients. Replica exchange molecular dynamics (REMD) simulations combined with machine learning were used to define the average structure of variants in aqueous solution to predict changes in drug and ligand binding in BCL-2 variants. The variant structures all show shifts in residue positions that occlude the binding groove, and these are the primary contributors to drug resistance. Correspondingly, we established a method that can predict the severity of a variant as measured by the inhibitory constant (K_i) of Venetoclax by measuring the structure deviations to the binding cleft. In addition, we also applied machine learning to the phi and psi angles of the amino acid backbone to the ensemble of conformations that demonstrated a generalizable method for drug resistant predictions of BCL-2 proteins that elucidates changes where detailed understanding of the structure-function relationship is less clear.

Keywords: Drug resistance; Genome; Machine learning; Molecular simulation; Prediction; Venetoclax.