Working with Penn collaborators, we are currently developing methods for analysis of high-throughout genomic data. Our application areas include genome-wide association studies of neuroblastoma, eQTL analysis of human heart failure data and metagenomic data analysis of human gut microbiome. In the area of statistical genomics, our recent research has focused on developing statistical and computational methods for analysis of genetic pathways and networks, novel methods for analysis of eQTL data and methods for analysis of microbiome and metagenomics data. These collaborations have led to publications in Science, Nature, Nature Genetics, Nature Medicine, Developmental Cell, PNAS etc and have motivated many of our methodological research projects.

The focus of our methodological research is to formulate the problems in genetics and genomics as interesting statistcal problems and to develop novel statistical models and computational methods to solve these problems. We are particuarly interested in developing high dimensional statistical methods for analysis of genomic data. Our major methodological contributions include additive genetic gamma frailty models for genetic linkage analysis, sparse signal detection problems for copy number variants analysis, Hidden Markov random field models for network-based analysis of genomic data, methods for high dimensional regression analysia and methods for analysis of high dimensional compositional data. We have published statistical methodological and theoretical papers in JASA, JRSS-B, Biometrika, Annals of Applied Statistics, Annals of Statistics etc.

We are also interested in developing statistical and computational methods for big data, especially in health data sciences. Prof. Li is the Director of Center of Statistics in Big Data.

Our lab is actively recruiting students in Biostatisics, Applied Mathematics and Computational Science and Genomics and Computational Biology.