Identification of Potential Inhibitors of SARS-CoV-2 Using Machine Learning, Molecular Docking and MD Simulation

Abstract

The advent of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the etiological agent of the coronavirus disease 2019 (COVID-19) pandemic, has promoted physical and mental health worldwide. Due to the unavailability of effective antiviral drugs, there is an unmet demand for a robust therapeutic approach for the development of anti-SARS-CoV-2 drugs. Myriad investigations have recognized ACE2 as the primary receptor of SARS-CoV-2, and this amalgamation of ACE2 with the spike protein of the subsequent coronavirus is paramount for viral entry into host cells and inducing infection. Consequently, limiting or restricting the accessibility of the causal virus to ACE2 offers an alternative therapeutic approach for averting this illness. Thus, the objective of the study was to determine the highly efficacious inhibitors exhibiting an augmented affinity for ACE2 protein and asses their pharmacological efficacy using molecular docking analysis. Machine learning algorithms were employed to govern the novel compounds by taking the ACE2-inhibiting compounds, Quninaprill, Moexipril, etc, and pre-established repurposed viral compounds, Birinapant, Remdesivir, etc., as test datasets. Structural stability was further confirmed via MD simulation approach which comparatively assessed the novel machine-learning, and pre-established compounds, followed by toxicity and pharmacophore studies. The study therefore concludes that the novel machine-learning compound (PubChem ID: 23658468) can be a potent therapeutic agent for combatting SARS-CoV-2.