Evolutionary algorithm for feature subset selection in predicting tumor outcomes using microarray data

Authors:
Qihua Tan;Mads Thomassen;Kirsten M. Jochumsen;Jing Hua Zhao;Kaare Christensen;Torben A. Kruse
Affiliations:
Dept. of Biochemistry, Pharmacology and Genetics, Odense University Hospital, Odense C, Denmark and Epidemiology, Institute of Public Health, University of Southern Denmark, Odense C, Denmark;Dept. of Biochemistry, Pharmacology and Genetics, Odense University Hospital, Odense C, Denmark;Dept. of Biochemistry, Pharmacology and Genetics, Odense University Hospital, Odense C, Denmark;MRC Epidemiology Unit, Institute of Metabolic Science, Cambridge, UK;Epidemiology, Institute of Public Health, University of Southern Denmark, Odense C, Denmark;Dept. of Biochemistry, Pharmacology and Genetics, Odense University Hospital, Odense C, Denmark
Venue:
ISBRA'08 Proceedings of the 4th international conference on Bioinformatics research and applications
Year:
2008

Citing 3
Cited 1

Outcome signature genes in breast cancer: is there a unique set?

Bioinformatics
Feature Subset Selection and Ranking for Data Dimensionality Reduction

IEEE Transactions on Pattern Analysis and Machine Intelligence
A review of feature selection techniques in bioinformatics

Bioinformatics

Global feature subset selection on high-dimensional datasets using re-ranking-based EDAs

CAEPIA'11 Proceedings of the 14th international conference on Advances in artificial intelligence: spanish association for artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Feature subset selection for outcome prediction is a critical issue inlarge scale microarray experiments in cancer research. This paper introduces anintegrative approach that combines significant gene expression analysis, the geneticalgorithm and machine learning for selecting informative gene markersand for predicting tumor outcomes including survival outcomes. In case of survivaldata, full use of individual's survival information (both censored anduncensored) is made in selecting informative genes for survival outcome prediction.Applications of our method to published microarray data on epithelialovarian cancer survival and breast cancer metastasis have identified prognosticgenes that predict individual survival and metastatic outcomes with improvedpower while basing on considerably shorter gene lists.