Gene expression data classification using consensus independent component analysis.
10.1016/S1672-0229(08)60022-4
- Author:
Chun-Hou ZHENG
1
;
De-Shuang HUANG
;
Xiang-Zhen KONG
;
Xing-Ming ZHAO
Author Information
1. College of Information and Communication Technology, Qufu Normal University, Rizhao 276826, China.
- Publication Type:Journal Article
- MeSH:
Artificial Intelligence;
Colonic Neoplasms;
classification;
genetics;
Computational Biology;
Data Interpretation, Statistical;
Databases, Genetic;
Discriminant Analysis;
Gene Expression Profiling;
statistics & numerical data;
Glioma;
classification;
genetics;
Humans;
Leukemia;
classification;
genetics;
Models, Statistical;
Neoplasms;
classification;
genetics;
Oligonucleotide Array Sequence Analysis;
statistics & numerical data;
Principal Component Analysis
- From:
Genomics, Proteomics & Bioinformatics
2008;6(2):74-82
- CountryChina
- Language:English
-
Abstract:
We propose a new method for tumor classification from gene expression data, which mainly contains three steps. Firstly, the original DNA microarray gene expression data are modeled by independent component analysis (ICA). Secondly, the most discriminant eigenassays extracted by ICA are selected by the sequential floating forward selection technique. Finally, support vector machine is used to classify the modeling data. To show the validity of the proposed method, we applied it to classify three DNA microarray datasets involving various human normal and tumor tissue samples. The experimental results show that the method is efficient and feasible.
