Knowledge discovery in the identification of differentially expressed genes in tumoricidal macrophage

Authors:
A. Fazel Famili;Ziying Liu;Pedro Carmona-Saez;Alaka Mullick
Affiliations:
Institute for Information Technology National Research Council of Canada, Ottawa, ON, Canada;Institute for Information Technology National Research Council of Canada, Ottawa, ON, Canada;Centro Nacional de Biotecnología (CNB – CSIC), Madrid, Spain;Biotechnology Research Institute, National Research Council of Canada, Montreal, QC, Canada
Venue:
IDA'05 Proceedings of the 6th international conference on Advances in Intelligent Data Analysis
Year:
2005

Citing 3
Cited 0

Original Contribution: Stacked generalization

Neural Networks
Interrelated Two-way Clustering: An Unsupervised Approach for Gene Expression Data Analysis

BIBE '01 Proceedings of the 2nd IEEE International Symposium on Bioinformatics and Bioengineering
A comparative study of feature selection and multiclass classification methods for tissue classification based on gene expression

Bioinformatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

High-throughput microarray data are extensively produced to study the effects of different treatments on cells and their behaviours. Understanding this data and identifying patterns of groups of genes that behave differently or similarly under a set of experimental conditions is a major challenge. This has motivated researchers to consider multiple methods to identify patterns in the data and study the behaviour of hundreds of genes. This paper introduces three methods, one of which is a new technique and two are from the literature. The three methods are cluster mapping, Rank Products and SAM. Using real data from a number of microarray experiments comparing the effects of two very different products that can activate macrophage tumoricidal activity we have identified groups of genes that share interesting expression patterns. These methods have helped us to gain an insight into the biological problem under study.