Application Of Support Vector Regression To Quantitative Structure-activity Relationship

Quantitative structure-activity relationship is a method building a statistical model. The model can quantificationally predict structure-activity relationship of molecule, and bioactivity of new molecules can be known. Structure of molecule, which is described by parameters in physical chemistry, biochemistry and quantum chemistry, includes functional group, minor structure, molecular fragment, chemical composition. Bioactivity is toxicity, carcinogenicity, pathogenesis, teratogeny and biodegradation. Quantitative structure-activity relationship, which is a research hot topic, is widely applied to drug design, toxic analysis biodegradation and antitumor activity of camptothecin derivatives etc. The kernel of quantitative structure-activity relationship is the model that is built by algorithms. Now, many machine learning methods, such as artificial neural network and multivariate regression analysis, are applied to quantitative structure-activity relationship. In this paper, support vector regression is applied to quantitative structure-activity relationship. Biodegradation and antitumor activity of camptothecin derivatives are sample data. Biodegradation is a process in which toxicant molecules are broken into carbon dioxide and water. A lot of experiments are done to get data of biodegradation, and much money and time is spent. Experiments are reduced by quantitative structure-activity relationship, then a lot of work, money and time is saved. Camptothecin derivatives are a kind of prospective anticancer medication. Experiments suggest support vector regression is...