Combined Support-Vector-Machine-Based Virtual Screening and Docking Method for the Discovery of IMP-1 Metallo-β-Lactamase Inhibitors

Metallo-β-lactamases can hydrolyze a broad range of β-lactam antibiotics and no effective inhibitors could be used in the clinic. Therefore, the discovery of metallo-β-lactamase inhibitors has attracted much attention in recent years. In this study, a support vector machine (SVM) that separates compounds into positives and negatives, combined with docking method was employed for virtual screening of IMP-1 metallo-β-lactamase inhibitors. Eight of the twenty five selected compounds were purchased for in vitro assays. Among them, four compounds show inhibitory potency against IMP-1. Two of them are found to have novel scaffolds, implying a good potential for further optimization.