Novel Methodologies for Gene Network Interaction Analysis and Network Modeling with Applications to Cancer Research and Cardiovascular Disease

• Activity Number: 144
• Type: Invited
• Date/Time: Monday, August 2, 2010 : 10:30 AM to 12:20 PM
• Sponsor: International Indian Statistical Association
• Author(s): Bala Rajaratnam*+ and Sang-Yun Oh
• Companies: Stanford University and Stanford University
• Keywords: Covariance matrix ; Graphical model ; Network model ; Multivariate analysis ; Precision matrix

Abstract

Making sense of the many complex relationships in high dimensional data and developing inferential procedures is one of the major challenges facing statisticians today. Complex relationships between genes/proteins are often understood in terms of networks and pathways. Hence network models that capture dependences in the covariance parameter (or its inverse) in a sparse manner can be very useful in capturing the essence of the main interactions between many variables. In this paper we propose a range of new methods to estimate the (inverse) covariance matrix in a sparse manner that is suitable for genomic and biomedical applications, and thus estimate the underlying biological networks which are present in such data sets. We compare our method to others in the literature to assess its effectiveness in high dimensional problems.