|
Title:
|
EXPLORATION OF HIGH-DIMENSIONAL TIME SERIES USING REGULARIZED REDUCED RANK APPROACH: APPLICATION IN TIME-COURSE MICROARRAY DATA ANALYSIS |
|
Author(s):
|
Adam Zagdański , Rafal Kustra |
|
ISBN:
|
978-972-8924-63-8 |
|
Editors:
|
Hans Weghorn and Ajith P. Abraham |
|
Year:
|
2008 |
|
Edition:
|
Single |
|
Keywords:
|
Time-course microarray, reduced-rank model, regularization, canonical analysis. |
|
Type:
|
Short Paper |
|
First Page:
|
129 |
|
Last Page:
|
133 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
In this paper, we propose a multivariate analytic framework which can deal with a large number of short, correlated time
series data. The method is motivated by time-course microarray studies and relies on a reduced-rank multivariate model
for time series. Our contribution lies in adopting a regularization technique in covariance structure estimation, and in a
novel cross-validation scheme to pick optimal model parameters. We show applications of our approach in visualizing
high-dimensional microarray time series and in discriminating its components. The method can be also used to identify
components of interest (e.g. cell-cycle regulated genes). |
|
|
|
|
|
|
