@ARTICLE{Scharpf2011, author = {Robert B Scharpf and Ingo Ruczinski and Benilton Carvalho and Betty Doan and Aravinda Chakravarti and Rafael A Irizarry}, title = {A multilevel model to address batch effects in copy number estimation using SNP arrays.}, journal = {Biostatistics}, year = {2011}, volume = {12}, pages = {33--50}, number = {1}, month = {Jan}, abstract = {Submicroscopic changes in chromosomal DNA copy number dosage are common and have been implicated in many heritable diseases and cancers. Recent high-throughput technologies have a resolution that permits the detection of segmental changes in DNA copy number that span thousands of base pairs in the genome. Genomewide association studies (GWAS) may simultaneously screen for copy number phenotype and single nucleotide polymorphism (SNP) phenotype associations as part of the analytic strategy. However, genomewide array analyses are particularly susceptible to batch effects as the logistics of preparing DNA and processing thousands of arrays often involves multiple laboratories and technicians, or changes over calendar time to the reagents and laboratory equipment. Failure to adjust for batch effects can lead to incorrect inference and requires inefficient post hoc quality control procedures to exclude regions that are associated with batch. Our work extends previous model-based approaches for copy number estimation by explicitly modeling batch and using shrinkage to improve locus-specific estimates of copy number uncertainty. Key features of this approach include the use of biallelic genotype calls from experimental data to estimate batch-specific and locus-specific parameters of background and signal without the requirement of training data. We illustrate these ideas using a study of bipolar disease and a study of chromosome 21 trisomy. The former has batch effects that dominate much of the observed variation in the quantile-normalized intensities, while the latter illustrates the robustness of our approach to a data set in which approximately 27\% of the samples have altered copy number. Locus-specific estimates of copy number can be plotted on the copy number scale to investigate mosaicism and guide the choice of appropriate downstream approaches for smoothing the copy number as a function of physical position. The software is open source and implemented in the R package crlmm at Bioconductor (http:www.bioconductor.org).}, doi = {10.1093/biostatistics/kxq043}, institution = {Department of Oncology, Johns Hopkins University School of Medicine, Baltimore, MD 21205, USA. rscharpf@jhsph.edu}, language = {eng}, medline-pst = {ppublish}, owner = {rscharpf}, pii = {kxq043}, pmcid = {PMC3006124}, pmid = {20625178}, timestamp = {2011.02.26}, url = {http://dx.doi.org/10.1093/biostatistics/kxq043} } @ARTICLE{Carvalho2007a, author = {Benilton Carvalho and Henrik Bengtsson and Terence P Speed and Rafael A Irizarry}, title = {Exploration, normalization, and genotype calls of high-density oligonucleotide SNP array data.}, journal = {Biostatistics}, year = {2007}, volume = {8}, pages = {485--499}, number = {2}, month = {Apr}, abstract = {In most microarray technologies, a number of critical steps are required to convert raw intensity measurements into the data relied upon by data analysts, biologists, and clinicians. These data manipulations, referred to as preprocessing, can influence the quality of the ultimate measurements. In the last few years, the high-throughput measurement of gene expression is the most popular application of microarray technology. For this application, various groups have demonstrated that the use of modern statistical methodology can substantially improve accuracy and precision of the gene expression measurements, relative to ad hoc procedures introduced by designers and manufacturers of the technology. Currently, other applications of microarrays are becoming more and more popular. In this paper, we describe a preprocessing methodology for a technology designed for the identification of DNA sequence variants in specific genes or regions of the human genome that are associated with phenotypes of interest such as disease. In particular, we describe a methodology useful for preprocessing Affymetrix single-nucleotide polymorphism chips and obtaining genotype calls with the preprocessed data. We demonstrate how our procedure improves existing approaches using data from 3 relatively large studies including the one in which large numbers of independent calls are available. The proposed methods are implemented in the package oligo available from Bioconductor.}, doi = {10.1093/biostatistics/kxl042}, institution = {Department of Biostatistics, Johns Hopkins University, Baltimore, MD 21205, USA.}, keywords = {Algorithms; Alleles; Data Interpretation, Statistical; Genotype; Humans; Oligonucleotide Array Sequence Analysis; Oligonucleotides; Polymorphism, Single Nucleotide}, owner = {rscharpf}, pii = {kxl042}, pmid = {17189563}, timestamp = {2008.08.07}, url = {http://dx.doi.org/10.1093/biostatistics/kxl042} }