|
Activity Number:
|
372
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #304029 |
|
Title:
|
Bayesian Modeling of ChIP-Chip Data via a Modified Ising Model
|
|
Author(s):
|
Qianxing Mo*+ and Faming Liang
|
|
Companies:
|
Memorial Sloan-Kettering Cancer Center and Texas A&M University
|
|
Address:
|
307 E 63rd street, 3rd floor, New York, NY, 10065,
|
|
Keywords:
|
Affymetrix tiling arrays ; Agilent promoter array ; ChIP-chip ; Gibbs sampler ; Ising model ; Spatial statistics
|
|
Abstract:
|
ChIP-chip experiments are procedures that combine chromatin immunoprecipitation and microarray to study the binding sites of specific proteins on DNA. We propose a simple, but powerful approach to the data via a modified Ising model. The proposed method naturally takes into account the spatial structure of the data and can be used to analyze data from multiple platforms. The method is illustrated using two publicly available data sets, and compared with three alternative Bayesian methods. The numerical results indicate that the proposed method performs as well as the other three methods for the data from Affymetrix platform, but significantly outperforms the other three methods for the data from Agilent platform. In addition, we find that the proposed method has better operating characteristics in terms of sensitivities and false discovery rates under various simulation scenarios.
|
