|
Activity Number:
|
378
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #310111 |
|
Title:
|
Joint Exploration of Haplotype Information and High-Order SNP-Phenotype Associations via Gibbs Sampling
|
|
Author(s):
|
Jing Zhao*+
|
|
Companies:
|
Merck & Co., Inc.
|
|
Address:
|
UG1C46 PO Box 1000, North Wales, PA, 19454-1099,
|
|
Keywords:
|
Bayesian Variable Selection ; Hierarchical Models ; Gibbs Sampling ; Metropolis-Hasting Algorithm ; Single Nucleotide Polymorphism (SNP)
|
|
Abstract:
|
Haplotypes are believed to have important implications for identifying complex disease. However, obtaining haplotypes experimentally is considerable expensive. This paper presents a hierarchical Bayesian model and the associated variable (genotype) selection procedure that simultaneously reconstruct the haplotypes and locate the multi-locus genetic contributors to complex disease. We demonstrate that this approach is well suited to large model spaces and has reasonable power to detect high order genotype-phenotype associations. Gibbs sampling is implemented and the model with the highest visiting frequency is selected as the best model.
|
- 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 2007 program |
