An Integrated Computational Approach for Drug Discovery Against SARS-CoV-2

Abstract

The novel coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has killed thousands   and infected millions of people worldwide. Urgent development of potential drugs against SARS-CoV-2 could be helpful to save millions lives around the world. In the last few years, significant development has been made in virtual screening (VS) and drug development. Drug screening through virtual method has evolved from traditional similarity searching, which utilizes advanced application domain like similarity search, data mining, and machine- learning approaches, which require large and representative training-set compounds to learn robust decision rules. Tremendous growth of public domain-available chemical databases including FDA -approved drugs and structural database of druggable targets of SARS-CoV-2, has generated huge effort to design, analyze, and apply novel learning methodologies to develop novel drug molecules against SARS-CoV-2. In this review, we focus on machine-learning techniques within the context of ligand-based virtual screening to develop potential drugs against SARS-CoV-2.