Identification of vasodilators from molecular descriptors by machine learning methods

Abstract Vasodilators have been extensively used in the treatment of various vascular diseases. With the aim of developing the accurate computational models for identifying vasodilators of diverse structures, several machine learning methods, such as C4.5 decision tree (C4.5 DT), k-nearest neighbor (k-NN), and support vector machine (SVM), were explored in this work. These identification models were trained by using 198 three-dimensional molecular descriptors and a group of 635 compounds including 308 vasodilators and 327 non-vasodilators, in which feature selection was conducted to optimize the training models and select the most appropriate descriptors for identifying the vasodilators. An independent validation set of 74 vasodilators and 87 non-vasodilators was subsequently used to evaluate the performance of the developed identification models. The identification rates of these models are in the range of 78.38% –97.30% for vasodilators and 83.91%–86.21% for non-vasodilators. Our investigation reveals that the explored machine learning methods, especially SVM, are potentially useful for the identification of vasodilators.