Speaker: Erick Matsen, PhD, Professor, Public Health Sciences Division, Fred Hutch
Some think that the future of computational biology research lies in large black box models and post-hoc interpretation. I prefer a future in which the models reflect the underlying biology and lead to mechanistic insight. In this talk, I will give two examples of how we can turbocharge classical biological probabilistic models via transformer architectures: first, to predict natural selection on antibodies, and second, to extend classical models of the antibody recombination process.
The Department of Epidemiology & Biostatistics welcomes all participants to our events. If you need a reasonable accommodation to participate in this event because of a disability, please contact Liz Buggs ([email protected])