Title: Analysing DNA copy number changes using Fused Margin Regression

Authors: Yuanjian Feng, Guoqiang Yu, Tian-Li Wang, Ie-Ming Shih, Yue Wang

Addresses: Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, Arlington, VA 22203, USA. ' Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, Arlington, VA 22203, USA. ' Departments of Gynecology/Obstetrics and Oncology, Johns Hopkins Medical Institutions, Baltimore, MD 21231, USA. ' Departments of Gynecology/Obstetrics, Oncology and Pathology, Johns Hopkins Medical Institutions, Baltimore, MD 21231, USA. ' Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, Arlington, VA 22203, USA

Abstract: DNA copy number change is an important form of structural variations in human genomes. Detecting copy number changes using DNA array data is a challenging task due to high density genomic loci, low signal to noise ratios, and normal tissue contamination. We propose Fused Margin Regression (FMR) method that combines a variable fusion rule and robust ε-insensitive loss criterion to estimate piecewise constant segments of the underlying copy number profile. We tested FMR method on both simulation and real CGH and SNP array datasets, and observed competitively improved performance as compared to several widely-adopted existing methods.

Keywords: DNA copy number change detection; CGH copy number; SNP copy number; regularised regression; l₁-norm regularisation; FMR; fused margin regression; SVR; support vector regression; segmentation; variable fusion; structural variations; human genomes; DNA array data.

DOI: 10.1504/IJFIPM.2010.033242

International Journal of Functional Informatics and Personalised Medicine, 2010 Vol.3 No.1, pp.3 - 15

Published online: 14 May 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article