An evaluation of Roluperidone as a promising repurposing candidate for Alzheimer’s Disease: A Computational Investigation

Abstract

Alzheimer’s disease (AD) is the most dominant and prevalent form of dementia. The therapeutic agents for AD are not sufficient. Drug repurposing ( i.e., also called drug repositioning or therapeutic switching of drugs) could contribute to adding novel therapeutic agents in AD discovery pipeline. Blood-brain barrier (BBB) is a crucial factor, for brain’s diseases related drug discovery. Since, CNS active compounds have BBB crossing property, in this study this category of compounds was re-evaluated as repurposing potential candidate for AD by integrated machine learning algorithm, cheminformatics analysis, molecular Docking and simulation-based approach. We builded three machine learning model such as Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGB) for the prediction of AD potential repurposing candidates. The SVM classification model performed better than others. The SVM classification model achieved an Area Under the Curve of the Receiver Operating Characteristics (ROC-AUC) of 0.81, along with higher precision, recall, and F1 scores. The support vector machine (SVM) was implemented to classify 500 CNS active compounds as AD drug potential and non-AD drug potential. Using the SVM model, 60 compounds were predicted as AD repurposing potential from 500 CNS active compounds. Structural similarity analysis of 60 compounds with Donepezil as a reference drug was performed using 5 different types of fingerprints such as ‘substructure’, ‘extended’, ‘circular’, ‘EState’, ‘MACCS’. 9 compounds from them obtained as structurally most similar to the reference drug. After the molecular docking performance of 9 compounds into the active site & peripheral anionic site of human acetylcholinesterase (hAChE), it was revealed that Roluperidone’ had binding affinity of −12 kcal/mol, and ‘Napitane’ had binding affinity of −11.9 kcal/mol whereas the reference drug Donepezil had a binding affinity of −11.8 Kcal/mol. Molecular dynamics simulation revealed that Roluperionde had better binding integrity to hAChE. This study laid out computational reinvestigation of 500 CNS active drugs for therapeutic switching to AD, and ‘Roluperidone’ is found as an AD repurposing potential candidate. However, in-vitro and in-vivo studies are further needed to fully elucidate the compound’s potential as AD repurposing drugs.