CARMA: A platform for analyzing microarray datasets that incorporate replicate measures

The incorporation of statistical models that account for experimental variability provides a necessary framework for the interpretation of microarray data. A robust experimental design coupled with an analysis of variance (ANOVA) incorporating a model that accounts for known sources of experimental...

Full description

Saved in:
Bibliographic Details
Published in:BMC bioinformatics 2006-03, Vol.7 (1), p.149-149, Article 149
Main Authors: Greer, Kevin A, McReynolds, Matthew R, Brooks, Heddwen L, Hoying, James B
Format: Article
Language:English
Subjects:
Analysis of Variance
Animals
Computational Biology - methods
Computational Biology - statistics & numerical data
Computer Simulation - statistics & numerical data
Databases, Genetic - statistics & numerical data
Mice
Models, Statistical
Oligonucleotide Array Sequence Analysis - statistics & numerical data
Software
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The incorporation of statistical models that account for experimental variability provides a necessary framework for the interpretation of microarray data. A robust experimental design coupled with an analysis of variance (ANOVA) incorporating a model that accounts for known sources of experimental variability can significantly improve the determination of differences in gene expression and estimations of their significance. To realize the full benefits of performing analysis of variance on microarray data we have developed CARMA, a microarray analysis platform that reads data files generated by most microarray image processing software packages, performs ANOVA using a user-defined linear model, and produces easily interpretable graphical and numeric results. No pre-processing of the data is required and user-specified parameters control most aspects of the analysis including statistical significance criterion. The software also performs location and intensity dependent lowess normalization, automatic outlier detection and removal, and accommodates missing data. CARMA provides a clear quantitative and statistical characterization of each measured gene that can be used to assess marginally acceptable measures and improve confidence in the interpretation of microarray results. Overall, applying CARMA to microarray datasets incorporating repeated measures effectively reduces the number of gene incorrectly identified as differentially expressed and results in a more robust and reliable analysis.
ISSN:1471-2105
1471-2105
DOI:10.1186/1471-2105-7-149