|
Activity Number:
|
445
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
International Indian Statistical Association
|
| Abstract - #303318 |
|
Title:
|
Predictive Models of Complex Traits: Inference of Statistical Dependencies and Predictive Geometry
|
|
Author(s):
|
Sayan Mukherjee*+
|
|
Companies:
|
Duke University
|
|
Address:
|
Ciemas Building-101 Sciences Dr, Durham, NC, 27708,
|
|
Keywords:
|
|
|
Abstract:
|
Tumor progression is a complex (disease) trait. The challenge in modeling tumorigenesis is heterogeneity with respect to phenotype, stages of the disease, and genotype or gene expression variation. This is particularly challenging in the case of high-dimensional data. We first develop an approach for modeling tumor progression in both the space of genes as well as a priori defined pathways. We infer both pathways relevant across stages of progression as well as localized to individual stages. Our modeling tools are (Bayesian) hierarchical or multi-task regression models as well as a generalization inverse regression based on inference of gradients on manifolds. The second part of the talk describes a method to decompose pathways or gene networks into sub-networks.
|
- 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 2009 program |
