In a given feature space, SVM learning aims to construct a hyperplane to best separate training data with different class labels. (3-5) The SVM methodology was originally conceived for binary class label prediction of objects (6-8) on the basis of training data. (1, 2) Among machine learning approaches, support vector machines (SVM) have become increasingly popular. Supervised machine learning is a preferred approach for the prediction of compound properties including biological activity. Feature weight analysis in combination with feature mapping made it also possible to interpret individual predictions, thus balancing the black box character of SVM/SVR modeling. Furthermore, features were identified that had opposite effects on SVM and SVR predictions. The overlap between feature sets determining the predictive performance of SVM and SVR was only very small. Fingerprint features were frequently identified that contributed differently to the corresponding SVM and SVR models. On the basis of systematic feature weight analysis, rather surprising results were obtained. Herein, we have compared SVM and SVR calculations for the same compound data sets to evaluate which features are responsible for predictions. For the closely related SVM and SVR methods, fingerprints (i.e., bit string or feature set representations of chemical structure and properties) are generally preferred descriptors. In addition, support vector regression (SVR) has become a preferred approach for modeling nonlinear structure–activity relationships and predicting compound potency values.
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |