Algorithms for gene expression analysis
Part 4. Bioinformatics
4.5. Computational Methods for High-throughput Genetic Analysis: Expression Profiling
Published Online: 15 NOV 2005
Copyright © 2005 John Wiley & Sons, Ltd
Encyclopedia of Genetics, Genomics, Proteomics and Bioinformatics
How to Cite
Brazma, A. and Culhane, A. C. 2005. Algorithms for gene expression analysis. Encyclopedia of Genetics, Genomics, Proteomics and Bioinformatics. 4:4.5:54.
- Published Online: 15 NOV 2005
A new genre of algorithms, which blends bioinformatics, statistics, and machine learning, is emerging to tackle the challenges of gene expression data analysis. Microarrays enable genome-scale high-throughout measurement of gene expression, and have produced unprecedented amounts of gene expression data. In this chapter, we present an overview of some of the many algorithms that have been employed in the analysis of these data. These include many well-known algorithms and new algorithms developed to address data-specific issues. We describe various clustering algorithms, including hierarchical and k-means, and ordination methods, such as principal component analysis, that can be applied to unsupervised exploration of data. We also provide an introduction to a number of supervised, meta-analysis, and gene selection methods. Where possible, we mention software tools that implement these algorithms. Finally, we stress the importance of a standard data format and data repositories for sharing of microarray gene expression data.
- principal component analysis