Rational Protein Engineering using Data-Driven Generative Models
Designing proteins to perform particular functions remains a grand challenge in modern science that has the potential to revolutionize medicine, public health, materials, and engineering. Directed evolution has enabled massive strides in discovering new proteins, but the vast size of potential sequences and random nature of mutations makes this process very inefficient.
Under a new paradigm, Profs. Andrew Ferguson and Rama Ranganathan employ artificial intelligence to learn “nature’s blueprint” for protein design using data-driven deep generative models. Through a continuous computational-experimental feedback loop, their platform mimics millions of years of evolution to discover and test new synthetic proteins with unprecedented function.
Principal Investigators: Andrew Ferguson (UChicago), Rama Ranganathan (UChicago)