Approved Research

Multi-modality modeling and analyses of human-centric data to accelerate biomarker and therapeutic development

Lay summary

The main aim of this research project is to use machine learning models to analyze the vast and deep multi-modal dataset available in the UK Biobank. By integrating the different types of data, such as genetic, proteomics, digital imaging, and clinical, we hope to gain a better understanding of the underlying factors that contribute to the development of chronic complex diseases like obesity, diabetes, cardiovascular, and liver diseases.

Our research will focus on identifying novel biomarkers and therapeutic targets that can aid in early detection, accurate diagnosis and effective treatment of these diseases. We will also work to better characterize patient sub-populations for the different diseases of interest.

By using explainable machine learning approaches, we will connect the molecular phenotypes to clinical and disease phenotypes to identify novel biomarkers and therapeutic targets. Our methods will include, but are not limited to, conventional biostatistical approaches, modern machine learning algorithms, mendelian randomization, polygenic risk score analysis, and network-based causal modeling approaches.

We will analyze all available data in the UK Biobank, including genomics, metabolomics, proteomics, imaging, accelerometry, electronic health records, clinical biomarkers, and on-site visit information. This comprehensive approach will allow us to gain insights into the complex factors that contribute to the development of chronic diseases and identify potential targets for precision medicine.

The expected value of this research is significant, as it has the potential to accelerate drug discovery and development efforts and bring well-prosecuted biomarkers and treatments to patients more efficiently. The insights gained from this research can inform public health policies and interventions aimed at reducing the incidence of chronic diseases. Ultimately, we hope our research will lead to more effective diagnosis and treatment for patients with chronic diseases.