Atlantis Press Paper Details: Oncogenes and Subtypes of Diffuse Large B-Cell Lymphoma Discoveries from Microarray Database

This paper presents an effective analysis scheme for Diffuse Large B-Cell Lymphoma (DLBCL) microarray datasets. Analysis of variable (ANOVA) is a well known statistics tools. It is useful to get the oncogenes to distinguish the normal and cancerous tissues. But, it can not further obtain the sub-types of cancerous tissues effectively. Hierarchical clustering is a well known analysis method for data mining. Therefore, it is also useful and fit to classify oncogenes to obtain some sub-types. ANOVA and hierarchical clustering both are employed to help us analyze B-cell Lymphoma datasets. In our analysis results, ANOVA can obtain 11 oncogenes of DLBCL from Stanford DLBCL microarray database successfully and accurately. Then, the 11 oncogenes are used for hierarchical clustering to identify the sub-types of cancerous tissues. In our hierarchical clustering analysis, we use 20 GC B-like DLBCL and 15 Activated B-like DLBCL actual samples used for analyzing. The analysis result shows that the hierarchical clustering can distinguish GC B-like DLBCL and Activated B-like DLBCL samples successfully.

		back to author index

title:		Oncogenes and Subtypes of Diffuse Large B-Cell Lymphoma Discoveries from Microarray Database
publication:		JCIS-2006 Proceedings
part of series:		Advances in Intelligent Systems Research
ISBN:		978-90-78677-01-7
ISSN:		1951-6851
DOI:		doi:10.2991/jcis.2006.224 (how to use a DOI)
author(s):		Ching-Hao Lai, Jun-Dong Chang, Meng-Hsiun Tsai
corresponding author:		Meng-Hsiun Tsai
publication date:		October 2006
keywords:		Microarray, Analysis of Variance (ANOVA), hierarchical clustering, Diffuse Large B-Cell Lymphoma (DLBCL), data mining.
abstract:		This paper presents an effective analysis scheme for Diffuse Large B-Cell Lymphoma (DLBCL) microarray datasets. Analysis of variable (ANOVA) is a well known statistics tools. It is useful to get the oncogenes to distinguish the normal and cancerous tissues. But, it can not further obtain the sub-types of cancerous tissues effectively. Hierarchical clustering is a well known analysis method for data mining. Therefore, it is also useful and fit to classify oncogenes to obtain some sub-types. ANOVA and hierarchical clustering both are employed to help us analyze B-cell Lymphoma datasets. In our analysis results, ANOVA can obtain 11 oncogenes of DLBCL from Stanford DLBCL microarray database successfully and accurately. Then, the 11 oncogenes are used for hierarchical clustering to identify the sub-types of cancerous tissues. In our hierarchical clustering analysis, we use 20 GC B-like DLBCL and 15 Activated B-like DLBCL actual samples used for analyzing. The analysis result shows that the hierarchical clustering can distinguish GC B-like DLBCL and Activated B-like DLBCL samples successfully.
copyright:		© Atlantis Press. This article is distributed under the terms of the Creative Commons Attribution License, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited.
full text:		JCIS06-CSI-182.pdf (370 K)