Repurposing FDA approved drugs as possible anti-SARS-CoV-2 medications using ligand-based computational approaches: sum of ranking difference-based model selection

The worldwide burden of coronavirus disease 2019 (COVID-19) is still unremittingly prevailing, with more than 440 million infections and over 5.9 million deaths documented so far since the SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) pandemic. The non-availability of treatment further aggravates the scenario, thereby demanding the exploration of pre-existing FDA-approved drugs for their effectiveness against COVID-19. The current research aims to identify potential anti-SARS-CoV-2 drugs using a computational approach and repurpose them if possible. In the present study, we have collected a set of 44 FDA-approved drugs of different classes from a previously published literature with their potential antiviral activity against COVID-19. We have employed both regression- and classification-based quantitative structure-activity relationship (QSAR) modeling to identify critical chemical features essential for anticoronaviral activity. Multiple models with the consensus algorithm were employed for the regression-based approach to improve the predictions. Additionally, we have employed a machine learning-based read-across approach using Read-Across-v3.1 available from https://sitcs.google.com/jadavpurunivcrsity.iu/dtc-lab-softwarc/hoiuc and linear discriminant analysis for the efficient prediction of potential drug candidate for COVID-19. Finally, the quantitative prediction ability of different modeling approaches was compared using the sum of ranking differences (SRD). Furthermore, we have predicted a true external set of 98 pharmaceuticals using the developed models for their probable anti-COVID activity and their prediction reliability was checked employing the Prediction Reliability Indicator tool available from https://dtclab.webs.com/software-tools. Though the present study does not target any protein of viral interaction, the modeling approaches developed can be helpful for identifying or screening potential anti-coronaviral drug candidates.

Automated summary

The study aims to identify potential anti-SARS-CoV-2 drugs from FDA-approved drugs using computational approaches. Regression- and classification-based QSAR modeling and machine learning-based read-across approach were employed to predict the antiviral activity and potential drug candidates for COVID-19. The developed modeling approaches can be helpful for identifying or screening potential anti-coronaviral drug candidates.