The School of Biological Sciences Spring 2025 Seminar Series presents Dr. Andrew Kern

Abstract: As genomic datasets grow in size empiricists are faced with the daunting task of making sense of a flood of information. To keep pace with this explosion in data, computational methodologies are being rapidly developed to best utilize genomic sequence data from hundreds to tens of thousands of individuals for the purposes of evolutionary genetic inference. In this seminar I will talk about work done by my group to leverage supervised machine learning techniques for population genetic inference. In particular I will cover recent applications of deep learning on unreduced genotype matrices for a number of population genetic tasks including recombination rate estimation, geographic prediction, and spatial population genetic inference.