Using Multiclass SVM methods for classification of DNA microarray data

One important application of gene expression microarray data is classification of samples into categories, such as the type of tumor. A classifier using Multiclass SVM [4] (Support Vector Machines) is described in this article. Our classifier involves dimension reduction using Multivariate Partial Least Squares (MPLS) for classification more than two classes. We use also two methods based on binary classifications: One-Against-All [5] and One-Against-One [6]. These three methods have been tested on a data set involving 125 tumor/normal thyroid human DNA microarrays samples. There are 66 Papillary throid carcinoma, 32 follicular throid carcinoma and 27 normal tissues. The most important thing is to find small number of genes that discriminate between these three classes with good accuracy. The best genes can be selected for Q-PCR validation. Molecular markers differentiating between throid cancer and normal tissues can help in clinical diagnostics and therapy methods. For error estimation we are use the bootstrap .632 [8] technique. Major issue with bootstrap estimators is their high computational cost. That is why we use a OpenMosix with MPI (Message Passing Interface) cluster technology for this system for parallel computation space