Dr. Chen’s research has focused on developing statistical methods and computational tools to incorporate multiple data sources, select biologically relevant markers, and predict clinical outcomes in a unified framework. Her work on Bayesian methodological development of data integration for regulatory network inference and pathway and gene selection for breast cancer survival prediction facilitates the identification of deregulated pathways with therapeutic relevance in subsets of human cancer. She is working on developing statistical methods to simultaneously select relevant pathways and SNPs for cancer genome-wide association studies. Dr. Chen’s work on nonparametric method improvement for the detection of nonlinear correlation has enabled the identification of key genes for the development of pathological conditions, which might have been missed by traditional methods to detect merely linear relationships. As a co-investigator for two studies using proteomics and other emerging technologies, two large-scale genomics studies, and one genetic epidemiology study, Dr. Chen also has works on identifying novel biomarker strategies to guide clinical decision making. Working with Dr. Haura’s group, she is developing statistical models to integrate multiple data sources to infer the signaling network and guide treatment decision in lung cancer.