Negative correlation based gene markers identification in integrative gene expression data
by Tao Zeng; Xuan Guo; Juan Liu
International Journal of Data Mining and Bioinformatics (IJDMB), Vol. 10, No. 1, 2014

Abstract: Along with the emergence and development of translational biomedicine, more and more genetic information has been applied in clinical practice. In the recent decade, the discovery of genetic markers for cancer prognosis obtains increasing attention and many methods have been developed. The 'element' methods use one or two independent genes to judge the Boolean status of disease. The 'set' methods use multiple gene markers as a whole to classify patients into different risks. And the advanced 'sets' methods use a group of different sets of biomarkers in an assembling manner. Either the existed 'set' or 'sets' methods only concern positive correlations among genes. However, the negative regulation, negative feedback, and functional repression are actually the relevant clues in cancer studies. Therefore, in this paper, based on the integrative gene expression data organised as gene-time-sample data or gene-sample-source data, we propose to mine Negatively Correlated Gene Sets (NCGSs) from multiple datasets, and use them along with the maximal positively correlated gene sets for prognosis classification. The experiment results suggest the promotions of cancer prognosis accuracy and meaningful pathogen relevance of gene markers by NCGS applications.

Online publication date: Tue, 21-Oct-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Data Mining and Bioinformatics (IJDMB):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com