Cen Wu

Cen Wu serves as Associate Professor in the Department of Statistics at Kansas State University and Faculty Scientist at the Johnson Cancer Research Center. His methodological research focuses on developing robust statistical machine learning approaches for high-dimensional cancer genomic data integration, addressing challenges where measurement dimensions far exceed sample sizes.

Dr. Wu earned his Ph.D. in Statistics from Michigan State University in 2013, followed by a postdoctoral fellowship in Biostatistics at Yale School of Public Health (2013-2015). He joined Kansas State University as Assistant Professor in 2015, was promoted to Associate Professor in 2021, and has maintained dual appointments in Statistics and Cancer Research since 2016.

His research program centers on Bayesian sparse learning methods for cancer genomics, with particular emphasis on robust variable selection techniques that accommodate outliers and heavy-tailed distributions common in genomic studies. He develops integrative approaches for multi-platform genomic data (mRNA expression, copy number variations, DNA methylation) to elucidate cancer etiology and identify prognostic markers. His work bridges theoretical statistics with practical clinical applications, including adaptive prediction of patient recruitment in clinical trials.

Analysis of his recent publications reveals consistent focus on gene-environment interaction modeling through advanced Bayesian frameworks, with increasing emphasis on longitudinal data structures and robust inference procedures. His methodological innovations frequently translate into practical R packages that implement these complex statistical techniques for broader research communities.

Dr. Wu actively contributes to the academic community as Associate Editor for TEST and BMC Genomics, and previously served as Guest Editor for a special issue on Bayesian Learning in Entropy. He maintains active collaborations with cancer researchers at the Johnson Cancer Research Center, applying his statistical expertise to real-world cancer genomics problems.

His laboratory develops and implements cutting-edge statistical methods through R packages including 'mixedBayes', 'pqrBayes', 'roben', and 'interep', which address specific challenges in high-dimensional data analysis for cancer research. Current projects focus on extending robust Bayesian frameworks to handle increasingly complex genomic data structures while maintaining computational efficiency.