IN SILICO MOLECULAR DOCKING AND MACHINE LEARNING–BASED LEAD OPTIMIZATION FOR NOVEL INHIBITORS TARGETING SARS-CoV-2 MAIN PROTEASE

Background: The SARS-CoV-2 pandemic, responsible for COVID-19, highlighted an urgent need for effective antiviral therapies.The viral main protease (Mpro), which plays a crucial role in viral replication and maturation, remains one of the most promising therapeutic targets for small-molecule inhibition.Aim: To identify and optimize novel inhibitors against SARS-CoV-2 Mpro using an integrated computational strategy combining molecular docking and machine learning for rapid lead discovery and optimization.Method: A library of small molecules was screened using structure-based molecular docking against the active site of SARS-CoV-2 Mpro (PDB ID: 6LU7).Top candidates were subjected to machine learning-based QSAR models and molecular dynamics validation to optimize binding affinity, drug-likeness, and ADMET properties.Results: Several candidate compounds demonstrated strong predicted binding affinity (ΔG < -9.0 kcal/mol), stable residue interactions in the active site, and improved drug-like properties after machine learning-guided optimization.The top hits showed Jigneshkumar Modasiya, V.