Transductive Support Vector Machines: Promising Approach to Model Small and Unbalanced Datasets

Semi-supervised methods dealing with a combination of labeled and unlabeled data become more and more popular in machine-learning area, but not still used in chemoinformatics. Here, we demonstrate that Transductive Support Vector Machines (TSVM) - a semi-supervised large-margin classification method - can be particularly useful to build the models on small and unbalanced datasets which often represent a difficult problem in QSAR. Both TSVM and ordinary SVM have been applied to build classification models on 10 DUD datasets. The "transductive effect" (the difference in predictive performance between transductive and ordinary support vector machines) was investigated as a function of: (a) active/inactive ratio, (b) descriptor weighting, and (c) the training and test sets size and composition.