Join us in person: Engineering 2, Room 192
Description: Understanding the clinical significance of personal genome variation is a major challenge in the field of precision medicine. Most genetic variants identified in clinical sequencing studies are rare variants of uncertain significance, which has motivated the development of a variety of machine learning tools to predict the pathogenicity and molecular impact of individual variants. Genome-wide association studies have, in parallel, identified numerous genetic loci associated with complex disease risk, but determining the underlying causal variants and genes at these loci remains a challenge. Nilah Monnier Ioannidis will discuss strategies for pathogenicity prediction and variant interpretation, including recent advances in deep learning methods that predict molecular phenotypes (gene expression, chromatin accessibility, epigenetic modifications) directly from DNA sequence, and investigate the application of these methods to explain variation across individuals in the context of personal genome interpretation.
Speaker bio: Nilah Monnier Ioannidis is an assistant professor at UC Berkeley in the Center for Computational Biology (CCB) and Department of Electrical Engineering and Computer Sciences (EECS), where she works on machine learning tools to predict the functional impact of genetic variation, and other computational methods for personal genome interpretation. She was previously a postdoc at Stanford University in the Department of Biomedical Data Science and completed her Ph.D. in biophysics at Harvard University.