*4.1.2. Support Vector machine based classification*

Support Vector Machine (SVM) is a non-probabilistic binary linear classifier. Given a set of training examples, each marked as belonging to one of two categories, an SVM training algorithm builds a model that assigns new examples one of the two categories. An SVM is called the maximum margin classifier that optimizes the margin between the example points belonging to two classes so that their gap is maximized.

A newly developed siRNA designing tool enables improved selection of potent siRNAs by application of a Support Vector machine based optimization of a set of eight siRNA selection parameters. The support vector machine is trained with the feature set of 200 highly efficient and 200 poorly efficient siRNA candidates, collected from siRecords, a database of validated siRNAs [12]. The support vector machine is trained using a Gaussian kernel and Sequential Minimal Optimization (SMO) algorithm [13]. It has been tested with huge number of experimentally validated data samples from four different sources and gave sufficiently good result.
