Department of Computer Science and Engineering, Southern Methodist University, 6425 North Ownby Drive, Dallas, TX 75205, USA. ' Department of Computer Science and Engineering, Southern Methodist University, 6425 North Ownby Drive, Dallas, TX 75205, USA
High-throughput microarrays have recently been developed to detect DNA Copy Number (DCN) aberrations. The resulting DCN data is often very noisy. Previous denoising methods proposed for DCN data assumed uniform spacing between adjacent probes, which is not true and can potentially result in erroneous output. To address this issue, we developed a novel stationary wavelet denoising scheme for DCN data. Empirical results on synthetic data showed that our method outperformed the best previous method by 4.6–12.7% in terms of the root mean squared error. Experiments on a real data set also confirmed the applicability of our method.
Comment on the Paper