Development of homology model, docking protocol and Machine-Learning based scoring functions for identification of Equus caballus’s butyrylcholinesterase inhibitors

Abstract

Machine learning (ML), an emerging field in drug design, has the potential to predict in silico toxicity, shape-based analysis of inhibitors, scoring function (SF) etc. In the present study, a homology model, docking protocol, and a dedicated SF have been developed to identify the inhibitors of horse butyrylcholinesterase (BChE) enzyme. Horse BChE enzyme has homology with human BChE and is a substitute for the screening of in vitro inhibitors. The developed homology model was validated and the active site residues were identified from Cavityplus to generate grid box for docking. The validation of docking involved comparison of interactions of ligands co-crystallised with human BChE and the docked poses of the corresponding ligands with horse BChE. A high degree of similarity in the interaction profiles of generated poses validated the docking protocol. Scoring of ligands was further validated by docking with known BChE inhibitors. The binding energies obtained from SF was correlated with IC₅₀ values of inhibitors through classification and regression-based methods, which indicated poor predictivity of native SF. Therefore, protein-ligand binding energy, interaction profile, and ligand descriptors were used to develop and validate the classification and regression-based models. The validated extra tree binary classifier, random forest and extra tree regression-based models were compiled as a protein-ligand SF and were made available to the users through web application and python library. ML models exhibited improved area under the curve for ROC and good correlation between the predicted and observed IC₅₀ values, than the Autodock SF.

Communicated by Ramaswamy H. Sarma

Keywords:

• Artificial intelligence
• machine learning
• butyrylcholinesterase
• autodock
• protein ligand scoring function

Acknowledgements

AG, RS, SS, D, and DK would like to acknowledge the financial research support from Ministry of Education (MoE), New Delhi, India in the form of teaching assistantships to them. The support and the resources provided by ‘PARAM Shivay Facility’ under the National Supercomputing Mission, Government of India at the Indian Institute of Technology (BHU), Varanasi are gratefully acknowledged. We would also like to acknowledge the computational support received from Centre for Computing and Information Services (CCIS), Indian Institute of Technology (BHU), Varanasi. The authors extend their gratitude to Professor David A. Case, Department of Chemistry & Chemical Biology, Rutgers University, New Jersey, USA for granting a license of Amber 18 and Dr. Stefano Forli, Department of Integrative Structural and Computational Biology, Scripps Research, California Campus for providing python script, vstools_v0.16. Molecular graphics and analyses performed with UCSF Chimera, developed by the Resource for Biocomputing, Visualization, and Informatics at the University of California, San Francisco, with support from NIH P41-GM103311 is also acknowledged.

Disclosure statement

The authors declare that they have no conflicts of interest.