Hae Kyung Im (UChicago): AI+Science Schmidt Fellows Speaker Series

Organized by the University of Chicago’s Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship Program.

Agenda
4:00pm – 4:45pm:  Presentation
4:45pm – 5:00pm:  Q&A
5:00pm – 5:30pm: Reception

Meeting location
William Eckhardt Research Center. Room 401
5640 S Ellis Avenue, Chicago, IL 60637
Map It

Abstract: Genetic association studies have identified many disease causing genes, providing valuable insights into potential cures. However, the complex, multifactorial, and polygenic nature of most common diseases presents a significant challenge to further progress. While hundreds of thousands of genomic loci have been linked to various diseases, the mechanisms through which they contribute to disease remain largely unknown. Several predictive methods have been developed to explain the downstream effects of genetic variation. However, the high costs and limited sample sizes often hinder the generation of sufficient data for these methods to be fully effective. In this talk, I will provide an overview of the current state of complex disease genetics, describe traditional population-based approaches, and show how the integration of large-scale deep learning models, capable of learning the grammar of DNA, can significantly enhance our ability to address challenging problems. I will present examples involving single-cell RNA sequencing data and transcription factor binding, demonstrating how these models can expand the number of predictable features by several orders of magnitude, thereby advancing our understanding of disease biology.

Bio: Hae Kyung Im is Associate Professor of Medicine and Human Genetics. They are a member of Committee on Genetics, Genomics and Systems Biology at University of Chicago. With her team, they focus on the development of quantitative and computational techniques, along with specialized tools, to navigate through extensive genomic and high-dimensional datasets. Their ultimate objective is to uncover meaningful insights that have the potential to be translated into advancements for human health enhancement. This involves harnessing the power of AI to analyze and interpret biomarkers, allowing for more effective and targeted exploration of data, and facilitating the identification of valuable patterns and correlations that can drive improvements in healthcare outcomes.

Parking
Campus North Parking
5505 S Ellis Ave
Map It