|
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 - #303748 |
|
Title:
|
Bayesian Analysis of iTRAQ Data with Nonrandom Missing: Identification of Differentially Expressed Proteins
|
|
Author(s):
|
Ruiyan Luo*+ and Hongyu Zhao
|
|
Companies:
|
Yale University and Yale University
|
|
Address:
|
300 George St., 503, New Haven, CT, 06511,
|
|
Keywords:
|
iTRAQ ; hierarchical model ; non-ignorable missing
|
|
Abstract:
|
iTRAQ is a technique that allows simultaneous quantitation of proteins in multiple samples. Variation and non-ignorable missing are two important issues involved in iTRAQ data. In this paper, we describe a Bayesian hierarchical model to infer the protein relative expression and hence identify the differentially expressed proteins. We model the measured peptide intensities as the results of both protein concentrations and peptide specific effects. The variations of these two effects across experiments are modeled as random effects. We also explicitly model the missing probability of a peptide in a spectrum. We implement an MCMC approach to simulate the posterior distributions. The estimates based on the MCMC samples have smaller variance and bias than those calculated from fold changes.
|
