|
Activity Number:
|
526
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #305408 |
|
Title:
|
A Mixture Model for Microarray Images with Saturated Pixels
|
|
Author(s):
|
Yan Yang*+
|
|
Companies:
|
Arizona State University
|
|
Address:
|
Dept of Mathematics and Statistics, Tempe, AZ, 85287,
|
|
Keywords:
|
Bias ; censoring ; EM algorithm ; image segmentation ; normal mixture model ; saturation
|
|
Abstract:
|
Signal saturation of a spotted microarray occurs when some pixel values of highly expressed spots on the array exceed the upper detection threshold of scanner software. In practice, spots with saturated pixels are often discarded, or the saturated values are used without adjustment to obtain spot summary measures, leading to biased estimation of gene expression levels or protein profiles. We develop a normal mixture model with a right-censored component that segments microarray images with saturated pixels. The expectation-maximization algorithm is implemented for maximum likelihood estimation of the mixture model. We demonstrate bias correction of the proposed method through a simulation study, and illustrate its capability of enhancing the dynamic range of detection beyond the saturation threshold with human peptide microarrays from a valley fever diagnosis study.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2009 program |
