SVM feature selection and sample regression for Chinese medicine research

In this paper, SVM based feature selection methods are introduced for regression problem of COX2 inhibitor activity prediction in Chinese medicine Quantitative Structure-Activity Relationship (QSAR) research. We develop a recursive SVM feature selection algorithm for regression and compare its performance with Genetic Algorithm and SVM Recursive Feature Elimination (SVM-RFE) algorithm. Experiments on real Chinese medicine dataset show that our method is a fast and accurate algorithm for Chinese medicine regression problem with a small number of samples.