Precision Genomic Medicine |
Genome-powered Precision Medicine Our lab's research mission is to advance precision medicine by integrating large-scale genomic and clinical data, including electronic health records (EHR)-linked biobank databases, to improve our understanding of the genetic basis of complex diseases and to develop more accurate predictive models for personalized treatment. By applying AI and machine learning algorithms, we aim to identify genetic risk factors for various diseases and to develop more inclusive and diverse training models to mitigate predictive biases. Our future research direction in this area includes expanding AI/ML in clinical practice to move beyond diagnosis of individual diseases and towards a broader system for detecting multiple diseases. Integration of AI/ML systems to analyze multiple data types, such as genomic, phenotypic, imaging, electronic health record, and social factors data, will enable us to learn faster from extended data types and develop more advanced, in-depth predictive models to assist in identifying new biomarkers for more accurate disease diagnosis and risk predictions. Additionally, we aim to develop AI/ML-based predictive models linking functional genomic and environmental perturbations to changes in phenotypes, which have the potential to revolutionize our understanding of disease mechanisms and improve patient outcomes.
|
Psychiatric Genetics |
Decoding the Genetic Basis of Mental Health Outcomes for Precision Psychiatry We focus on studying the genetic basis of various cognitive, psychological and psychiatric outcomes, such as cognitive ability, suicidal behaviors, depression, bipolar disorder, mood disorders, or ADHD, by integrating multi-modal biomedical data, including neuroimaging and genomic data. Our goal is to develop better diagnostic tools and personalized treatments for psychiatric diseases.
|
Imaging Genetics |
Unlocking the Genetic Secrets of Mental Health: Integrating Brain Neuroimaging and Genomic Data We aim to integrate neuroimaging and genomic data to better understand the genetic basis of mental health outcomes and to develop more accurate predictive models for personalized treatment. Our research involves applying AI and machine learning algorithms to analyze multi-modal data, such as imaging (MRI), genetic (genotype), and diagnostic interview (K-SADS) data, to classify individuals’ state of mental health outcomes.
|
Salutogenesis |
Genetic Underpinning of the Process of Health Restoration Our lab recognizes that salutogenesis, the process by which individuals move from a less healthy to a healthier state, is not yet fully understood. This process may involve various physiological systems and domains, and it is different from traditional pharmacological treatments that target specific molecular pathways. Therefore, we aim to develop innovative analytical tools using AI/ML modeling to integrate individual genetic data with multi-modal clinical and environmental data. Our goal is to create multiscale computational models that can explain how physiological and biopsychosocial networks dynamically change over time during the process of human health restoration. Through our research, we hope to advance the understanding of salutogenesis and to develop personalized treatments that take into account an individual's genetic makeup and health history. |