Faculty Candidate Seminar

Talk Title: Machine Learning the Rules od Antibody-Virus Interactions

Tal did his PhD at Caltech with Rob Phillips, whose lab specializes in developing models that don’t just fit data, but provide deep insights into the underlying mechanisms. In his postdoc, Tal shifted lanes into immunology, joining Jesse Bloom’s lab at the Fred Hutch Cancer Center which studies the antibody response against viruses such as influenza, HIV, and SARS-CoV-2. Tal is a Damon Runyon Quantitative Biology Fellow, and today we will hear about one of his multidisciplinary research projects that combines concepts from physics, math, biology, and computer science to help us understand and augment our antibody response against viruses.

Abstract for advertising talk: Immunology is undergoing a paradigm shift where the objective has expanded from creating a stopgap vaccine against a currently-circulating virus to developing a universal vaccine that confers lifelong protection. My research uses biophysical modeling and machine learning to probe how the antibody response changes with each viral exposure, with the ultimate goals of making the antibody response programmable and guiding it to a maximally-protective configuration. My lab will initially build off my expertise with influenza, but future efforts will generalize these methods to other viruses such as HIV-1 and SARS-CoV-2 that are of interest to public health.