Efficient change point detection in genomic sequences of continuous measurements

Abstract

Motivation: Knowing the exact locations of multiple change points in genomic sequences serves several biological needs, for instance when data represent aCGH profiles and it is of interest to identify possibly damaged genes involved in cancer and other diseases. Only a few of the currently available methods deal explicitly with estimation of the number and location of change points, and moreover these methods may be somewhat vulnerable to deviations of model assumptions usually employed. Results: We present a computationally efficient method to obtain estimates of the number and location of the change points. The method is based on a simple transformation of data and it provides results quite robust to model misspecifications. The efficiency of the method guarantees moderate computational times regardless of the series length and the number of change points. Availability: The methods described in this article are implemented in the new R package cumSeg available from the Comprehensive R Archive Network at http://CRAN.R-project.org/package=cumSeg.