Prediction of low coverage prone regions for Illumina sequencing projects using a support vector machine

Abstract

Applications of next-generation sequencing technologies have the potential to bring revolutionary changes to medicine and biology. However, coverage bias can pose a challenge to short read data analysis tools, which rely on high coverage. To address this issue we have developed a support vector machine (SVM) based method for predicting low coverage prone (LCP) regions on a given genome. The developed SVM-based prediction of LCP regions on a given genome can assist data processing procedures based on Illumina sequencing technology, such as de novo sequencing and transcriptome analysis.