Batch Effect Removal Method for Microarrays: Batch Profile Estimation, Correction, and Scoring

• Activity Number: 472
• Type: Contributed
• Date/Time: Wednesday, August 3, 2011 : 8:30 AM to 10:20 AM
• Sponsor: Biopharmaceutical Section
• Author(s): Tzu-Ming Chu*+ and Wenjun Bao and Russell Thomas and Russ Wolfinger
• Companies: SAS Institute Inc. and SAS Institute Inc. and Hamner Institute for Health Services and SAS Institute Inc.
• Keywords: batch correction ; batch profile ; batch scoring ; normalization ; cross validation

Abstract

Batch effect increases the variation among expression data and, hence, lowers the statistical power for investigating biological effects. When the corresponding proportion of variation associated with the batch effect is high, it is desirable to remove the batch effect from data. A robust batch effect removal method should be easily applicable to new batches. Here we discusse a simple, but robust grouped-batch-profile (GBP) normalization method that includes three steps: batch profile estimation, correction, and scoring. Genes with similar expression patterns across batches are grouped. The method assumes the availability of control samples in each batch, and the corresponding batch profile of each group is estimated by an ANOVA. Batch correction and scoring are based on the estimated profiles. A mouse lung tumorigenicity data set is used to illustrate GBP normalization through cross validation on 84 predictive models. On average, cross-validated predictive accuracy increase significantly from 0.56 to 0.66 after GBP normalization.