Fusing microarray experiments with multivariate regression

• Published in: Bioinformatics Vol. 21; no. suppl-2; pp. ii137 - ii143
• Main Authors: Gilks, Walter R., Tom, Brian D. M., Brazma, Alvis
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 01.09.2005; Oxford Publishing Limited (England)
• Subjects: Algorithms; Cell Cycle - physiology; Cell Cycle Proteins - metabolism; Data Interpretation, Statistical; Database Management Systems; Databases, Protein; Gene Expression Profiling - methods; Information Storage and Retrieval - methods; Laboratory tests; Multivariate Analysis; Noise levels; Oligonucleotide Array Sequence Analysis - methods; Regression Analysis; Schizosaccharomyces - cytology; Schizosaccharomyces - metabolism; Schizosaccharomyces pombe; Systems Integration
• ISSN: 1367-4803; 1367-4811; 1460-2059; 1367-4811
• DOI: 10.1093/bioinformatics/bti1123

Motivation: It is widely acknowledged that microarray data are subject to high noise levels and results are often platform dependent. Therefore, microarray experiments should be replicated several times and in several laboratories before the results can be relied upon. To make the best use of such extensive datasets, methods for microarray data fusion are required. Ideally, the fused data should distil important aspects of the data while suppressing unwanted sources of variation and be amenable to further informal and formal methods of analysis. Also, the variability in the quality of experimentation should be taken into account. Results: We present such an approach to data fusion, based on multivariate regression. We apply our methodology to data from a previous study on cell-cycle control in Schizosaccharomyces pombe. Availability: The algorithm implemented in R is freely available from the authors on request. Contact: wally.gilks@mrc-bsu.cam.ac.uk