Online Program Home
My Program

Abstract Details

Activity Number: 535 - Contributed Poster Presentations: Section on Statistics in Genomics and Genetics
Type: Contributed
Date/Time: Wednesday, August 1, 2018 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics in Genomics and Genetics
Abstract #333135
Title: Bayesian Nonparametric Regressions Regarding Correlated Regions and Its Application for Differentially Methylated Regions
Author(s): Suvo Chatterjee* and Duchwan Ryu and Shrabanti Chowdhury
Companies: Northern Illinois University and Northern Illinois University and Icahn School of Medicine at Mount Sinai
Keywords:
Abstract:

The identification of Differentiated methylated regions (DMRs) provides a comprehensive survey of epigenetic differences among human tissues and identifies genomic regions which play a key role in various human diseases. Currently there are several proposed functional approaches which emphasize on region-based identification but all of them overlook the key idea of dependency among neighboring regions and how to account for it. This paper proposes to develop a Bayesian functional modeling approach to identify DMRs which will be parsimonious to address the large dimensionality of whole-genomic sequencing and will incorporate potential dependency among neighboring regions of CpG sites. We consider an effective method to estimate functions that are defined on intervals and may be associated to each other. The proposed method uses sequential Monte Carlo approach to model for this dependency and more specifically uses dynamically weighted particle filter with Bayesian non-parametric smoothing splines


Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program