Title: De novo protein design with multi-objective fitness functions

Abstract: We have developed a protein design pipeline, called EvoPro, that uses iterative rounds of deep learning-based structure prediction and sequence optimization to evolve protein sequences for prespecified design goals. Two design projects will be described that make use of EvoPro: the creation of a set of de novo proteins where binding of protein A to protein B induces a conformational change in protein B that allows binding to protein C, and the design of protein-based vaccines for dengue virus.