A scoring scheme for the rapid and automatic classification of molecules into drugs and nondrugs was developed. The method is a valuable new tool that can aid in the selection and prioritization of compounds from large compound collections for purchase or biological testing and that can replace a considerable amount of laborious manual work by a more unbiased approach. It is based on the extraction of knowledge from large databases of drugs and nondrugs. The method was set up by using atom type descriptors for encoding the molecular structures and by training a feedforward neural network for classifying the molecules. It was parametrized and validated by using large databases of drugs and nondrugs (169 331 molecules from the Available Chemicals Directory, ACD, and 38 416 molecules from the World Drug Index, WDI). The method revealed features in the molecular descriptors that either qualify or disqualify a molecule for being a drug and classified 83% of the ACD and 77% of the WDI adequately.
Support vector machine (SVM) and artificial neural network (ANN) systems were applied to a drug/nondrug classification problem as an example of binary decision problems in early-phase virtual compound filtering and screening. The results indicate that solutions obtained by SVM training seem to be more robust with a smaller standard error compared to ANN training. Generally, the SVM classifier yielded slightly higher prediction accuracy than ANN, irrespective of the type of descriptors used for molecule encoding, the size of the training data sets, and the algorithm employed for neural network training. The performance was compared using various different descriptor sets and descriptor combinations based on the 120 standard Ghose-Crippen fragment descriptors, a wide range of 180 different properties and physicochemical descriptors from the Molecular Operating Environment (MOE) package, and 225 topological pharmacophore (CATS) descriptors. For the complete set of 525 descriptors cross-validated classification by SVM yielded 82% correct predictions (Matthews cc = 0.63), whereas ANN reached 80% correct predictions (Matthews cc = 0.58). Although SVM outperformed the ANN classifiers with regard to overall prediction accuracy, both methods were shown to complement each other, as the sets of true positives, false positives (overprediction), true negatives, and false negatives (underprediction) produced by the two classifiers were not identical. The theory of SVM and ANN training is briefly reviewed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.