top of page

OVERVIEW

Our research focuses on the development and application of advanced data integration methods to enhance the diagnosis, treatment, and prevention of complex diseases. A key aspect of our work involves integrating multi-omics data with biological knowledge to translate genomic and phenotypic data from electronic health records (EHR) into actionable clinical products. Our projects span both theoretical and applied research, including:

​

  • Developing novel data integration methods that combine multi-omics using machine learning and deep learning approaches

  • Predicting clinical outcomes by analyzing interactions between multi-omic features

  • Integrating multi-modal imaging with multi-omics data

  • Identifying gene-by-environment (GxE) interactions across various phenotypes and diseases

  • Constructing disease-disease networks using EHR-linked biobank data

  • Developing Immune health scores and foundation models for Immune Health

​

Our ongoing work continues to focus on providing clinical tools that leverage the interactions within and between different layers of genomic data. Our long-term research goal is to develop and evaluate sophisticated data integration methods that simultaneously account for individual variations in genomic (multi-omics) data, imaging data, phenotype data from EHRs, and environmental/lifelog data, all aimed at advancing precision medicine. Additionally, our research leverages artificial intelligence (AI)-driven approaches to further enhance healthcare outcomes, paving the way for more personalized and effective treatments.

overview.png

Lecture - Translational research, via data integration

Why Data Integration?

A central problem in translational research is that it’s difficult to understand the genetic architecture of a complex disease. Many genome-wide association studies (GWAS) exist—but most of the genetic loci that have been identified have negligible effects: Heritability, in many cases, isn’t found. That’s why we need alternative strategies to find underlying disease causes, said Assistant Professor of Informatics Dokyoon Kim, PhD—and a systems genomics approach, using data integration, can get the job done.

One Math Model to Explain Disease Phenotype

With the traditional approach, you can analyze a beautiful multi-omics data set, Dr. Kim continued—but you must handle the associations one pair at a time.  So he asked himself: Can I integrate everything into one mathematical model to predict outcome or explain disease phenotype?

bottom of page