Exploration of QSAR-Based Virtual Screening for the Discovery of Quinolone-Based Antibacterial Drugs
This paper explores quantitative structure–activity relationship (QSAR) modelling as a route to virtual screening of quinolone antibacterials.
Using 2D autocorrelation descriptors, a binary logistic regression model was trained to distinguish active antibacterial compounds. On the training set the model reached overall accuracy, sensitivity, and specificity of 91.80%, 90.62%, and 93.10%, with an ROC AUC of 0.933. It correctly classified 93% of held-out test compounds, supporting its use for rapid early-stage antibacterial discovery.