Activity Number:
|
191
|
Type:
|
Invited
|
Date/Time:
|
Tuesday, August 13, 2002 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Physical & Engineering Sciences*
|
Abstract - #300103 |
Title:
|
Prediction and Classification by Partial Least Squares Using Gene Expression Data
|
Author(s):
|
David Rocke*+ and Danh Nguyen
|
Affiliation(s):
|
University of California, Davis and Texas A&M University
|
Address:
|
2343 Academic Surge Building, 1 Shields Avenue, Davis, California, 95616,
|
Keywords:
|
dimension reduction ; microarray ; principal components ; survival analysis
|
Abstract:
|
One major challenge in using gene expression data to predict and classify is the high dimensionality of the data. Typically, the number of samples may be in the tens to hundreds, and the number of variables (genes) may be in the thousands. In such cases, dimension reduction or variable selection is required. We review the application of partial least squares as a method of dimension reduction for use with gene expression data, and show how it can be used for classification and survival analysis, as well as for prediction of uncensored quantitative variables.
|