CLEW - THE GENERATION OF PHARMACOPHORE HYPOTHESES THROUGH MACHINE LEARNING

The paper describes the program CLEW, which utilizes learning and geom etrical fitting to discover pharmacophores from a set of active and in active compounds. The program first divides the compounds into similar classes. It then utilizes machine learning to derive a set of rules t hat relate structure to activity for each class. Then it finds the com mon features among all classes. These common features are used by a ge ometrical fitting program that tries to a 3D fit between these feature s between minimized conformations for every active molecule in every c lass. Such a tit is used to infer a pharmacophore.