A systematic review of RdRp of SARS-CoV-2 through artificial intelligence and machine learning utilizing structure-based drug design strategy.

Since the coronavirus disease has been declared a global pandemic, it had posed a challenge among researchers and raised common awareness and collaborative efforts towards finding the solution. Caused by severe acute respiratory coronavirus syndrome-2 (SARS-CoV-2), coronavirus drug design strategy needs to be optimized. It is understandable that cognizance of the pathobiology of COVID-19 can help scientists in the development and discovery of therapeutically effective antiviral drugs by elucidating the unknown viral pathways and structures. Considering the role of artificial intelligence and machine learning with its advancements in the field of science, it is rational to use these methods which can aid in the discovery of new potent candidates in silico. Our review utilizes similar methodologies and focuses on RNA-dependent RNA polymerase (RdRp), based on its importance as an essential element for virus replication and also a promising target for COVID-19 therapeutics. Artificial neural network technique was used to shortlist articles with the support of PRISMA, from different research platforms including Scopus, PubMed, PubChem, and Web of Science, through a combination of keywords. "English language", from the year "2000" and "published articles in journals" were selected to carry out this research. We summarized that structural details of the RdRp reviewed in this analysis will have the potential to be taken into consideration when developing therapeutic solutions and if further multidisciplinary efforts are taken in this domain then potential clinical candidates for RdRp of SARS-CoV-2 could be successfully delivered for experimental validations.