To Explore the Potential Inhibitors against Multitarget Proteins of COVID 19 using In Silico Study

TL;DR

This study combines molecular docking and machine learning to identify potential multitarget inhibitors for COVID-19, proposing five novel compounds with promising binding affinities and favorable properties for further development.

Contribution

It introduces a novel integrated approach using molecular docking and decision tree regression to discover potential COVID-19 inhibitors, including five new promising compounds.

Findings

Identified five novel inhibitors with binding energies from -19.7 to -12.6 kcal/mol.

Decision Tree Regression outperformed other models in predicting inhibitors.

Analyzed physiochemical and pharmacokinetic properties to assess drug-likeness.

Abstract

The global pandemic due to emergence of COVID 19 has created the unrivaled public health crisis. It has huge morbidity rate never comprehended in the recent decades. Researchers have made many efforts to find the optimal solution of this pandemic. Progressively, drug repurposing is an emergent and powerful strategy with saving cost, time, and labor. Lacking of identified repurposed drug candidates against COVID 19 demands more efforts to explore the potential inhibitors for effective cure. In this study, we used the combination of molecular docking and machine learning regression approaches to explore the potential inhibitors for the treatment of COVID 19. We calculated the binding affinities of these drugs to multitarget proteins using molecular docking process. We perform the QSAR modeling by employing various machine learning regression approaches to identify the potential inhibitors against COVID 19. Our findings with best scores of R2 and RMSE demonstrated that our proposed Decision Tree Regression (DTR) model is the most appropriate model to explore the potential inhibitors. We proposed five novel promising inhibitors with their respective Zinc IDs ZINC (3873365, 85432544, 8214470, 85536956, and 261494640) within the range of -19.7 kcal/mol to -12.6 kcal/mol. We further analyzed the physiochemical and pharmacokinetic properties of these most potent inhibitors to examine their behavior. The analysis of these properties is the key factor to promote an effective cure for public health. Our work constructs an efficient structure with which to probe the potential inhibitors against COVID-19, creating the combination of molecular docking with machine learning regression approaches.