Computational Structural Validation of CYP2C9 Mutations and Evaluation of Machine Learning Algorithms in Predicting the Therapeutic Outcomes of Warfarin

Kannan Sridharan; Thirumal Kumar D; Suchetha Manikandan; Gaurav Prasanna; Lalitha Guruswamy; Rashed Al Banna; George Priya Doss C

doi:10.2174/1389200224666230705124329

Computational Structural Validation of CYP2C9 Mutations and Evaluation of Machine Learning Algorithms in Predicting the Therapeutic Outcomes of Warfarin

Curr Drug Metab. 2023;24(6):466-476. doi: 10.2174/1389200224666230705124329.

Authors

Kannan Sridharan¹, Thirumal Kumar D², Suchetha Manikandan³, Gaurav Prasanna³, Lalitha Guruswamy³, Rashed Al Banna⁴, George Priya Doss C⁵

Affiliations

¹ Department of Pharmacology & Therapeutics, College of Medicine and Medical Sciences, Arabian Gulf University, Manama, Kingdom of Bahrain.
² Faculty of Allied Health Sciences, Meenakshi Academy of Higher Education and Research, Chennai, Tamil Nadu, India.
³ Centre for Healthcare Advancement, Innovation and Research, Vellore Institute of Technology, Chennai, India.
⁴ Department of Cardiology, Salmaniya Medical Complex, Manama, Kingdom of Bahrain.
⁵ School of Bio Sciences and Technology, Vellore Institute of Technology, Vellore, India.

PMID: 37409551
DOI: 10.2174/1389200224666230705124329

Abstract

Aim: The study aimed to identify the key pharmacogenetic variable influencing the therapeutic outcomes of warfarin using machine learning algorithms and bioinformatics tools.

Background: Warfarin, a commonly used anticoagulant drug, is influenced by cytochrome P450 (CYP) enzymes, particularly CYP2C9. MLAs have been identified to have great potential in personalized therapy.

Objective: The purpose of the study was to evaluate MLAs in predicting the critical outcomes of warfarin therapy and validate the key predictor genotyping variable using bioinformatics tools.

Methods: An observational study was conducted on adults receiving warfarin. Allele discrimination method was used for estimating the single nucleotide polymorphisms (SNPs) in CYP2C9, VKORC1, and CYP4F2. MLAs were used for identifying the significant genetic and clinical variables in predicting the poor anticoagulation status (ACS) and stable warfarin dose. Advanced computational methods (SNPs' deleteriousness and impact on protein destabilization, molecular dockings, and 200 ns molecular dynamics simulations) were employed for examining the influence of CYP2C9 SNPs on structure and function.

Results: Machine learning algorithms revealed CYP2C9 to be the most important predictor for both outcomes compared to the classical methods. Computational validation confirmed the altered structural activity, stability, and impaired functions of protein products of CYP2C9 SNPs. Molecular docking and dynamics simulations revealed significant conformational changes with mutations R144C and I359L in CYP2C9.

Conclusion: We evaluated various MLAs in predicting the critical outcome measures associated with warfarin and observed CYP2C9 as the most critical predictor variable. The results of our study provide insight into the molecular basis of warfarin and the CYP2C9 gene. A prospective study validating the MLAs is urgently needed.

Keywords: CYP2C9; MLAs.; Support vector machine; machine learning algorithm; molecular dynamics simulation; warfarin.