Tal Einav, Ph.D.
Assistant Professor at the La Jolla Institute (LJI) for Immunology
Affiliate Professor of Bioengineering at the University of California, San Diego
Although influenza is one of the best-studied viruses, vaccine effectiveness remains around 20-50%. Surprisingly, a sizable fraction of individuals will show little-to-no antibody response following vaccination, yet we cannot identify these individuals a priori nor ascertain whether a different vaccine would have served them better. In this talk, we demonstrate how machine learning can leverage the wealth of prior studies to forecast vaccine responses. By leveraging model interpretability, we quantify the importance of factors such as age, sex, and prior immunity, paving the way for more nuanced vaccine recommendation schemes. We will discuss when these predictions are accurate, when they fall short, and some of the exciting possibilities for the future of this field.
Dr. Tal Einav runs the Computational Immunology Lab at LJI. His work lies at the intersection of various disciplines – computer science, biology, engineering – striving to tackle problems that are out of reach with traditional techniques. Dr. Einav’s career trajectory included a year-long sabbatical as a software developer, teaching summer courses (200 hours in 2 weeks!) at the Marine Biology Laboratory, and training at Caltech and the Fred Hutch Cancer Center.