EcoSta 2021: Start Registration
View Submission - EcoSta2021
A0237
Title: Integrative graphical modeling and network mediation analysis Authors:  Min Jin Ha - UT MD Anderson Cancer Center (United States) [presenting]
Francesco Stingo - University of Florence (Italy)
Veera Baladandayuthapani - University of Michigan (United States)
James Long - University of Texas MD Anderson Cancer Center (United States)
Abstract: Integrative network modeling of data arising from multiple genomic platforms provides insight into the holistic picture of the interactive system and the flow of information across many disease domains, including cancer. The basic data structure consists of a sequence of hierarchically ordered datasets for each individual subject, facilitating the integration of diverse inputs, such as genomics, transcriptomic, and proteomic data. In such contexts, a primary analytical task is to model the layered architecture of networks where the vertices can be naturally partitioned into ordered layers, dictated by multiple platforms, and exhibit both undirected and directed relationships. Given the underlying multi-layered graphical structure of data, we will discuss the Bayesian node-wise selection (BANS) approach to recover the multi-layered graphical structure, and causal mediation analysis framework that quantifies the paths one variable in a layer causes changes in another in the downstream layers.