Support vector machines for quality control of DNA sequencing

Abstract

Background: Support vector machines, one of the non-parametric controlled classifiers, is a two-class classification method introduced in the context of statistical learning theory and structural risk minimization. Support vector machines are basically divided into two groups as linear support vector machines and nonlinear support vector machines. Nonlinear support vector machines are designed to make classifications by creating a plane in a space by mapping data to that higher dimensional input space. This method basically involves solving a quadratic programming problem. In this study, the support vector machines, which have an increasing rate of use in pattern recognition area, are used in the quality control of DNA sequencing data. Consequently, the classification of quality of all the DNA sequencing data will automatically be made as 'high quality/low quality'. Results: The proposed method is tested against a dataset created from public DNA sequences provided by InSNP. We first transformed all DNA chromatograms into feature vectors. An optimal hyperplane is first determined by applying SVM to the training dataset. The instances in the testing dataset are then labeled by using the hyperplane. Finally, the estimated class labels are compared against the true labels by computing a confusion matrix. As the confusion matrix reveals, our method successfully determines the labels of 23 out of 24 chromatograms. Conclusions: We devised a new method to fulfill the quality screening of DNA chromatograms. It is a composition of feature extraction and support vector machines. It has been tested on a public dataset and it provided quite satisfactory results. We believe that it is a strong solution for DNA sequencing institutions to be used in automatic quality labeling of DNA chromatograms.