|
Activity Number:
|
23
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 6, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #307200 |
|
Title:
|
Application of Temporal Association Rules to a cDNA Microarray Experiment
|
|
Author(s):
|
Bruce Southey*+ and Sandra Rodriguez-Zas and Younhee Ko and Chengxiang Zhai
|
|
Companies:
|
University of Illinois and University of Illinois and University of Illinois and University of Illinois
|
|
Address:
|
1207 W. Gregory Drive, Urbana, IL, 61801,
|
|
Keywords:
|
microarray ; association rules ; data mining ; cDNA
|
|
Abstract:
|
The analysis of cDNA microarray experiments provides vast information on the magnitude of gene expression differences between multiple experimental conditions for thousands of genes. Traditional association rules were adapted to describe gene expression patterns over 5 times points in a honey bee microarray experiment. After normalization and analysis using a two-stage linear mixed model, association rules were applied simultaneously to the pairwise differences between time points. The pairwise differences were classified into three groups, significantly under-expressed, significantly over-expressed or not differently expressed. Our approach enabled the discovery of relationships between genes that were not obvious from the pairwise comparisons alone. The application of association rules enhanced the interpretation of results from the statistical analysis of microarray experiments.
|
