Talk by Alice Tang, Sirota Lab
In-person or Zoom (link below)
Abstract: Certain complex diseases, such as Alzheimer’s Disease (AD), are difficult to study and treat due to disease heterogeneity, lack of precise phenotyping, and limited understanding of molecular mechanisms underlying clinical manifestations. Electronic medical records (EMR) are emerging as a real world dataset with abundance of longitudinal human data across diagnoses, medications, and measurements with opportunity to derive insights without predefined selection criteria or limitations in scope. Recent developments of integrative heterogenous knowledge databases that combine knowledge across omics relationships provide a means to further identify associated molecular hypotheses underlying complex clinical phenotypes. We performed deep phenotyping and association analysis to characterize Alzheimer’s Disease and sex differences in the EMR against a control cohort, and identified differential comorbidities, medication use, and median lab values. Extending this work to apply machine learning, we trained predictive models for AD onset and identified prioritized genes via knowledge networks and genetic colocalization analysis. Our findings suggest that there are relationships between musculoskeletal disorders among females with AD and neurological or behavioral disorders among males with AD, with potential interactions across aging body systems. By leveraging clinical data to identify hypotheses for disease, we can further make steps towards better understanding molecular mechanisms in disease and improving precision medicine approaches.