Our lab is interested in developing methods for the inference of gene regulatory mechanism and prediction of biomarkers based on genetic, genomic and epigenetic and clinical data. Our approaches are diverse, including machine learning, statistical modeling, and optimization methods.

Recently, we expanded our research interest to the area of microbiome studies. We have released MiMeNet for modeling microbiome-metabolome interaction, PopPhy-CNN and Meta-Signer for host phenotype prediction using metagenomics data based on the use of combinations of modeling techniques mentioned above.

Research Thrusts

Microbiome Data Analysis and Modeling

Genomics Data Modeling

Omics Data Analysis

Metagenomics Data Analysis

DNA Methylation and Enhancer Predicition

Biomarker Detection

Modeling Host-Microbiome Interaction

Modeling Gene Regulation, Cellular Heterogeneity

Omics analysis for cancer and disease mechanisms