©1996-2009 All Rights Reserved. Online Journal of Bioinformatics. You may not store these pages in any form except for your own personal use. All other usage or distribution is illegal under international copyright treaties. Permission to use any of these pages in any other way besides the before mentioned must be gained in writing from the publisher. This article is exclusively copyrighted in its entirety to OJVR publications. This article may be copied once but may not be, reproduced or re-transmitted without the express permission of the editors.
OJB®
Online Journal of Bioinformatics ©
Volume 1: 26-41, 2001.
An unsupervised
neural network approach for discovery
of gene expression patterns in B-cell lymphoma.
Azuaje F
Department of Computer Science, Trinity
College, Ireland.
ABSTRACT
Azuaje F, An unsupervised neural network
approach for discovery of gene expression
patterns in B -cell lymphoma. Online J Bioinformatics 1:26-41, 2001: The automated interpretation of gene expression data
may play a crucial role in the classification and treatment of human cancers.
In this paper a new computational approach to the discovery and analysis of
gene expression patterns is illustrated and applied to the recognition of
B-cell malignancies. Using cDNA microarrays data
obtained from a previous study, an unsupervised and self-adaptive neural
network model known as Growing Cell Structures is able to identify normal and
diffuse large B-cell lymphoma (DLBCL) patients. Furthermore, it distinguishes
patients with molecularly distinct types of DLBCL without previous knowledge of
those subclasses.
Keywords:gene expression analysis, neural networks, data mining, decision support systems, molecular classification of cancer.