Our research is at the junction of statistical and biological sciences. Our research interests lie in two interrelated directions:
Developing statistical methods for understanding biological questions, especially those related to large-scale genomic data;
Identifying, formulating, and resolving important, yet not previously addressed statistical questions arising from the frontiers of biology.
The specific topics we have examined include:
Statistics:
- Control of false discovery rates in multiple testing and asymmetric errors in binary classification
- Measures of association
- High-dimensional linear model inference and variable selection
- Bipartite network stochastic block model inference
Bioinformatics / Statistical Genomics:
- Statistical rigor in omics data analysis
- Statistical method development for single-cell omics data
- Statistical method development for bulk short-read RNA-seq data
- Using statistics to quantify the Central Dogma, the fundamental principle of molecular biology
- Comparative genomics: developing novel statistical methods to investigate conserved or divergent biological phenomena in different tissue and cell types across multiple species
- Identification of gene-gene and protein-DNA interactions using diverse genomic data
