Title :
Gene analysis framework for biomarker mining
Author :
Fukuta, Kentaro ; Nagashima, Tomomasa ; Uozumi, Takashi ; Okada, Yoshifumi
Author_Institution :
Satellite Venture Bus. Lab., Muroran Inst. of Technol., Muroran, Japan
Abstract :
A biomarker is a substance that is used as a biological parameter of pathological or psychological conditions. Recent progress of bioinformatics technology has enabled large-scale screening of biomarker candidates. As described in this paper, we introduce a gene analysis method, LEAF, for finding informative genes from gene expression data, and propose an additional algorithm for extending LEAF. An iterative forward selection method incorporating the concept of LOOCV, LEAF also provides a discrimination power score (DPS) of genes. Our method shows that the biological functions of extracted genes accorded well with past findings. Our method is a useful tool for many researchers engaged in bioinformatics.
Keywords :
bioinformatics; data mining; gene therapy; iterative methods; DPS; LEAF; LOOCV; bioinformatics technology; biological functions; biological parameter; biomarker candidates; biomarker mining; discrimination power score; gene analysis framework; gene expression data; iterative forward selection method; pathological conditions; psychological conditions; Biological processes; Cancer; Gene expression; Indexes; Ontologies; Proteins; biomarkers; cancer classification; data mining; gene expression profiles;
Conference_Titel :
Computer Information Systems and Industrial Management Applications (CISIM), 2010 International Conference on
Conference_Location :
Krackow
Print_ISBN :
978-1-4244-7817-0
DOI :
10.1109/CISIM.2010.5643669
