Most uses of protein-ligand docking involves a set of molecules being docked to a single protein target using a single docking program. A variety of consensus docking approaches for virtual screening and pose prediction have been developed in the last 20 years, much of which only considers combinations of the docking score. Here we compare traditional consensus scoring methods with a novel, unsupervised gradient boosting approach using the common performance metrics ROCAUC and EF1 on 21 benchmark targets from DUD-E. These methods are readily applicable to new targets in academic research and overcome the potentially poor performance of using a single docking method on a new target.<br/>

Machine learning consensus scoring improves performance across targets in structure-based virtual screening

255th National Meeting (2018)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.