Review of Integrative Analysis Challenges in Systems Biology

• Activity Number: 217
• Type: Invited
• Date/Time: Monday, August 2, 2010 : 2:00 PM to 3:50 PM
• Sponsor: Statistics in Biopharmaceutical Research Journal
• Author(s): Lei Zhu*+ and Kwan Lee and Amit Bhattacharyya and Edit Kurali and Amber Anderson
• Companies: GlaxoSmithKline and GlaxoSmithKline and GlaxoSmithKline and GlaxoSmithKline and GlaxoSmithKline
• Keywords: Integrative Analysis ; Omics Platform ; Metabolic Profiling ; Principal Component Analysis ; Partial Least Squares Discriminant Analysis ; Selection Bias

Abstract

Systems biology is making a paradigm shift in drug discovery from target-focused to a systems approach in the pharmaceutical industry. It studies the molecular level changes in a biological system as an integrated and interacting network of genes, proteins and metabolites instead of focusing on individual components. Integrative analysis of the molecular level data becomes very important. There are various challenges in the analysis: data preprocessing methods from various omics platform, the number of variables much larger than the number of subjects, wide differences in the number of variables per platform leading to imbalance in the platform contributions to the analysis, the issues of multicollinearity and multiple testing, and difficulty in proper model validation to avoid selection bias. This paper is a comprehensive review of statistical methods that address these challenges.