Pattern recognition: Application of Support Vector Machines, Artificial Neural Networks and Decision Trees for anti-HIV activity prediction of organic compounds

Predicting the biological activity of molecules from their chemical structures is a principal problem in drug discovery. Pattern recognition has gained attention as methods covering this need. In this study three classification models for anti-HIV activity, based on pattern recognition methods such as Support Vector Machines, Artificial Neural Networks and Decision Trees, are developed. All models give good results in learning and prediction phases. These results indicate that these models can be used as an alternative tool for classification problems in structure anti-HIV activity relationship.