Loading...
Loading...

Go to the content (press return)

Gene expression data classification combining hierarchical representation and efficient feature selection

Author
Bosio, M.; Bellot, P.; Salembier, P.; Oliveras, A.
Type of activity
Journal article
Journal
Journal of biological systems
Date of publication
2012-12
Volume
20
Number
4
First page
349
Last page
375
DOI
https://doi.org/10.1142/S0218339012400025 Open in new window
Repository
http://hdl.handle.net/2117/18425 Open in new window
URL
http://www.worldscientific.com/doi/pdfplus/10.1142/S0218339012400025 Open in new window
Abstract
A general framework for microarray data classification is proposed in this paper. It pro- duces precise and reliable classifiers through a two-step approach. At first, the original feature set is enhanced by a new set of features called metagenes. These new features are obtained through a hierarchical clustering process on the original data. Two different metagene generation rules have been analyzed, called Treelets clustering and Euclidean clustering. Metagenes creation is attractive for severa...
Citation
Bosio, M. [et al.]. Gene expression data classification combining hierarchical representation and efficient feature selection. "Journal of biological systems", Desembre 2012, vol. 20, núm. 4, p. 349-375.
Keywords
LDA, Microarray classification, Treelets, feature selection, hierarchical representation, metagenes
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants