Activity Number:
|
485
- Bayesian Latent Variable Methods for Life Sciences
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 1, 2018 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Bayesian Statistical Science
|
Abstract #329323
|
Presentation
|
Title:
|
Bayesian Latent Class Models for Identifying Biomarkers in Circadian Patterns
|
Author(s):
|
Sung Duk Kim* and Paul S Albert
|
Companies:
|
National Cancer Institute and National Cancer Institute
|
Keywords:
|
Circadian pattern;
Latent class model;
Metabolite data;
Random effect
|
Abstract:
|
Researchers in biology and medicine have increasingly focused on characterizing circadian rhythms and their potential impact on disease. Epidemiological studies from recent decades have supported a unique role for circadian rhythm in metabolism. As evidenced by individuals working night or rotating shifts, but also by rodent models of circadian arrhythmia, disruption of the circadian cycle is strongly associated with metabolic imbalance. In this paper, we develop new statistical methodology for identifying biomarkers in circadian patterns using metabolites that are observed over time in a population of individuals. We develop latent class approach to incorporate circadian patterns with a harmonic representation that allows for individual variation in the phase-shift across subjects. Markov chain Monte Carlo sampling is used to carry out Bayesian posterior computation. Several variations of the proposed models are considered and compared using the deviance information criterion. We illustrate this methodology with high-dimensional metabolite data
|
Authors who are presenting talks have a * after their name.