Research

My research interests lie at the intersection of Bayesian statistics, large-scale data analysis, genomics, bioinformatics, and biostatistics. I develop and apply statistical and computational methods for complex high-dimensional data, with particular emphasis on problems arising in genomics, next-generation sequencing, molecular data analysis, and public health research.

A central theme of my work is Bayesian and Empirical Bayes inference for large-scale studies, where thousands or millions of features—such as genes, SNPs, proteins, microbial strains, or genomic variants—are analyzed simultaneously to identify associations, signals, or underlying biological structure. In these settings, I am particularly interested in posterior probabilities, local false discovery rates, uncertainty quantification, and robust methods for extracting reliable evidence from noisy, heterogeneous, and high-dimensional data.

Much of my applied work has focused on genomics and bioinformatics, including next-generation sequencing data, variant calling, gene expression analysis, cell-type decomposition, and microbial strain mixture estimation. These problems are scientifically important and statistically challenging because they often involve complex dependence structures, measurement error, low signal-to-noise ratios, and the need for reproducible and scalable computational tools.

I am also interested in translating advanced statistical methods into practical, accessible, and open-source software. My work includes the development of statistical software and analytical pipelines for local false discovery rate estimation, variant calling, cell composition estimation, and strain mixture identification. More broadly, I aim to build methods that are not only theoretically sound, but also useful for scientists, analysts, and decision-makers working with real-world biological and public health data.

Recently, my research has expanded to include Bayesian approaches for nutrition exposure assessment and usual intake estimation, with applications to public health surveillance and risk assessment. This work connects my broader interest in Bayesian methodology with Health Canada’s applied research context, where statistical methods can support evidence-based decision-making and policy-relevant analysis.