ROCS-Derived Features for Virtual Screening
This work addresses the need for more effective virtual screening methods in drug discovery, though it is incremental as it builds upon the existing ROCS tool.
The authors tackled the problem of improving virtual screening performance by decomposing the ROCS color force field into novel color similarity features that can be weighted using machine learning, resulting in significant improvements in ROC AUC scores compared to standard ROCS in cross-validation experiments.
Rapid overlay of chemical structures (ROCS) is a standard tool for the calculation of 3D shape and chemical ("color") similarity. ROCS uses unweighted sums to combine many aspects of similarity, yielding parameter-free models for virtual screening. In this report, we decompose the ROCS color force field into "color components" and "color atom overlaps", novel color similarity features that can be weighted in a system-specific manner by machine learning algorithms. In cross-validation experiments, these additional features significantly improve virtual screening performance (ROC AUC scores) relative to standard ROCS.