Risk Prediction with Genome-Wide Association Studies

• Activity Number: 147
• Type: Invited
• Date/Time: Monday, August 1, 2011 : 10:30 AM to 12:20 PM
• Sponsor: Biometrics Section
• Author(s): Tianxi Cai*+ and Jessica Minnier
• Companies: Harvard University and Harvard University
• Keywords: risk prediction ; genetic pathways ; high dimensional data

Abstract

The complexity of the genetic architecture of human health and disease makes it difficult to identify genomic markers associated with disease risk or to construct accurate genetic risk prediction models. Accurate risk assessment is further complicated by the availability of a large number of markers that may be predominately unrelated to the outcome. Standard marginal association based analysis has limited power in identifying markers truly associated with disease, resulting in a large number of false positives and negatives. Simple additive modeling does not perform well when the underlying effects are highly interactive or non-linear. Additionally, these methods do not use information that may be available regarding genetic pathways or gene structure. We propose a multi-stage method relating markers to the risk of disease by first forming multiple gene-sets based on certain biological criteria and then aggregating information across all gene-sets. Prediction accuracy is assessed with bias-corrected ROC curves and AUC statistics. Numerical studies suggest that the model performs well in the presence of non-informative regions and both linear and non-linear effects.