In structure-based virtual screening, compound ranking through a consensus of scores from a variety of docking programs or scoring functions, rather than ranking by scores from a single program, provides better predictive performance and reduces target performance variability. We developed a consensus scoring technique using gradient boosting that provides improved performance over traditional consensus approaches. We now expand these efforts by considering multiple poses in addition to scores, pose differences between diverse docking algorithms and the incorporation of ensemble docking techniques. The resulting expansion of input data requires machine learning approaches to build a robust docking consensus applicable to new drug targets.<br/>

Data set expansion in consensus scoring for protein-ligand docking

255th National Meeting (2018)

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