Discovery of potential RSV fusion protein inhibitors from benzimidazole derivatives using QSAR, molecular docking, and ADMET evaluation methods.

Respiratory syncytial virus (RSV) is a leading cause of severe lower respiratory tract infections in infants, the elderly, and immunocompromised individuals worldwide. The pathogenic mechanism of RSV is closely linked to the membrane fusion process mediated by its fusion glycoprotein (F protein), which has consequently emerged as a critical target for developing anti-RSV therapeutics. At present, there is a lack of specific clinical treatments for RSV, and traditional drug discovery approaches are often time-consuming and expensive. In this context, quantitative structure-activity relationship (QSAR)-assisted drug design offers notable advantages. In this study, we collected a dataset consisting of 156 benzimidazole derivatives against F protein from publicly available sources. Transferable, reproducible, and interpretable 2D-QSAR inhibitory activity and cytotoxicity prediction models were constructed using Genetic Algorithm (GA) and Multiple Linear Regression (MLR). Following rigorous statistical validation, the best inhibitory activity model achieved R