Selecting informative genes for discriminant analysis using multigene expression profiles

Xin Yan; Tian Zheng
January 2008
BMC Genomics;2008 Supplement 2, Vol. 9, Special section p1
Academic Journal
Background: Gene expression data extracted from microarray experiments have been used to study the difference between mRNA abundance of genes under different conditions. In one of such experiments, thousands of genes are measured simultaneously, which provides a high-dimensional feature space for discriminating between different sample classes. However, most of these dimensions are not informative about the between-class difference, and add noises to the discriminant analysis. Results: In this paper we propose and study feature selection methods that evaluate the "informativeness" of a set of genes. Two measures of information based on multigene expression profiles are considered for a backward information-driven screening approach for selecting important gene features. By considering multigene expression profiles, we are able to utilize interaction information among these genes. Using a breast cancer data, we illustrate our methods and compare them to the performance of existing methods. Conclusion: We illustrate in this paper that methods considering gene-gene interactions have better classification power in gene expression analysis. In our results, we identify important genes with relative large p-values from single gene tests. This indicates that these are genes with weak marginal information but strong interaction information, which will be overlooked by strategies that only examine individual genes.


Related Articles

  • Post-analysis follow-up and validation of microarray experiments. Chuaqui, Rodrigo F.; Bonner, Robert F.; Best, Carolyn J.M.; Gillespie, John W.; Flaig, Michael J.; Hewitt, Stephen M.; Phillips, John L.; Krizman, David B.; Tangrea, Michael A.; Ahram, Mamoun; Linehan, W. Marston; Knezevic, Vladimir; Emmert-Buck, Michael R. // Nature Genetics;Dec2002 Supplement 2, Vol. 32, p509 

    Measurement of gene-expression profiles using microarray technology is becoming increasingly popular among the biomedical research community. Although there has been great progress in this field, investigators are still confronted with a difficult question after completing their experiments: how...

  • Navigating gene expression using microarrays ? a technology review. Schulze, Almut; Downward, Julian // Nature Cell Biology;Aug2001, Vol. 3 Issue 8, pE190 

    Parallel quantification of large numbers of messenger RNA transcripts using microarray technology promises to provide detailed insight into cellular processes involved in the regulation of gene expression. This should allow new understanding of signalling networks that operate in the cell and of...

  • Exploiting big biology: Integrating large-scale biological data for function inference. Marcotte, Edward M.; Date, Shailesh V. // Briefings in Bioinformatics;Dec2001, Vol. 2 Issue 4, p51 

    The amount of data produced by molecular biologists is growing at an exponential rate. Some of the fastest growing sets of data are measurements of gene expression, comparable in quantity only to gene sequences and the vast biological literature. Both gene expression data and sequence data offer...

  • Evaluation of time profile reconstruction from complex two-color microarray designs. Fierro, Ana C.; Thuret, Raphael; Engelen, Kristof; Bernot, Gilles; Marchal, Kathleen; Pollet, Nicolas // BMC Bioinformatics;2008, Vol. 9, p1 

    Background: As an alternative to the frequently used "reference design" for two-channel microarrays, other designs have been proposed. These designs have been shown to be more profitable from a theoretical point of view (more replicates of the conditions of interest for the same number of...

  • Expression Quantitative Trait Loci Analysis of 13 Genes in the Rat Prostate. Yamashita, Satoshi; Wakazono, Kuniko; Nomoto, Tomoko; Tsujino, Yoshimi; Kuramoto, Takashi; Ushijima, Toshikazu // Genetics;Nov2005, Vol. 171 Issue 3, p1231 

    Differential expression of mRNA among animal strains is one of the mechanisms for their diversity. cDNA microarray analysis of the prostates of BUF/Nac (BUF) and ACI/N (ACI) rats, which show different susceptibility to prostate cancers, found 195 differentially expressed genes. To identify loci...

  • Robustness considerations in selecting efficient two-color microarray designs. Latif, A. H. M. Mahbub; Bretz, Frank; Brunner, Edgar // Bioinformatics;Sep2009, Vol. 25 Issue 18, p2355 

    The main goal of microarray experiments is to select a small subset of genes that are differentially expressed among competing mRNA samples. For a given set of such mRNA samples, it is possible to consider a number of two-color cDNA microarray designs with a fixed number of arrays. Appropriate...

  • Probabilistic estimation of microarray data reliability and underlying gene expression. Bilke, Sven; Breslin, Thomas; Sigvardsson, Mikael // BMC Bioinformatics;2003, Vol. 4, p40 

    Background: The availability of high throughput methods for measurement of mRNA concentrations makes the reliability of conclusions drawn from the data and global quality control of samples and hybridization important issues. We address these issues by an information theoretic approach, applied...

  • Inconsistencies over time in 5% of NetAffx probe-to-gene annotations. Perez-Iratxeta, Carolina; Andrade, Miguel A. // BMC Bioinformatics;2005, Vol. 6, p183 

    Background: DNA microarray probes are designed to match particular mRNA transcripts, often based on expressed sequences like ESTs, or cDNAs, many times incomplete. As a result, the relations between probes and genes can change as the sequence data are updated. However, it is frequent that the...

  • Novel developments for improved detection of specific mRNAs by DNA chips. Pioch, Daniel; Schweder, Thomas; Jürgen, Britta // Applied Microbiology & Biotechnology;Oct2008, Vol. 80 Issue 6, p953 

    Microarrays have revolutionized gene expression analysis as they allow for highly parallel monitoring of mRNA levels of thousands of genes in a single experiment. Since their introduction some 15 years ago, substantial progress has been achieved with regard to, e.g., faster or more sensitive...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics