ROCS-derived features for virtual screening

• DOI: 10.1007/s10822-016-9959-3
• Publication Date: 2016-09-08T09:21:51Z
• Authors: Steven Kearnes; Vijay Pande
• Keywords: Machine Learning; Models, Molecular; FOS: Computer and information sciences; Molecular Structure; Pharmaceutical Preparations; Statistics - Machine Learning; Drug Design; Computer-Aided Design; Machine Learning (stat.ML); 01 natural sciences; Algorithms; 0104 chemical sciences

See "Version information" section<br/>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.<br/>