Integrative analysis of transcriptomic and metabolomic data via sparse canonical correlation analysis with incorporation of biological information

摘要

Integrative analyses of different high dimensional data types are becomingincreasingly popular. Similarly, incorporating prior functional relationshipsamong variables in data analysis has been a topic of increasing interest as ithelps elucidate underlying mechanisms among complex diseases. In this paper,the goal is to assess association between transcriptomic and metabolomic datafrom a Predictive Health Institute (PHI) study including healthy adults at highrisk of developing cardiovascular diseases. To this end, we develop statisticalmethods for identifying sparse structure in canonical correlation analysis(CCA) with incorporation of biological/structural information. Our proposedmethods use prior network structural information among genes and amongmetabolites to guide selection of relevant genes and metabolites in sparse CCA,providing insight on the molecular underpinning of cardiovascular disease. Oursimulations demonstrate that the structured sparse CCA methods outperformseveral existing sparse CCA methods in selecting relevant genes and metaboliteswhen structural information is informative and are robust to mis-specifiedstructural information. Our analysis of the PHI study reveals that a number ofgenes and metabolic pathways including some known to be associated withcardiovascular diseases are enriched in the subset of genes and metabolitesselected by our proposed approach.