Discovering Neuraminidase Inhibitors via Computational and Experimental Studies

Influenza A viruses spread out worldwide causing several global concerns. Discovering neuraminidase inhibitors to prevent the influenza A virus is thus of great interests. In this work, a machine learning model was trained and tested to evaluate the ligand-binding affinity to neuraminidase. The model was then used to predict the possibility of compounds from the CHEMBL database, which is manually curated database of bioactive molecules with drug-like properties. The physical insights into the binding process of ligands to neuraminidase were clarified via molecular docking and molecular dynamics simulations. Experimental studies on enzymatic and antiviral activity as well as cytotoxicity have validated our computational results and suggested that 2 compounds were potential inhibitors of neuraminidase of the influenza A virus.