Protein Engineering seminars

David Baker presents recent advances in designing proteins for functions that natural evolution has not been required to solve. The approach begins with a desired structure or activity and uses deep learning to propose amino acid sequences expected to realise it. The resulting designs are translated into synthetic genes, produced as proteins and tested experimentally. The lecture connects computational design with laboratory characterisation, explaining how the combination can create new molecular functions relevant to medicine, technology and sustainability. Its focus is the construction and evaluation of proteins from scratch, extending the protein-design research recognised by the 2024 chemistry prize.

David Baker, Demis Hassabis and John Jumper examine two complementary computational problems: designing proteins with desired properties and predicting the structures adopted by natural amino acid sequences. Baker describes the development of methods for creating new protein structures and functions. Hassabis discusses the use of artificial intelligence to accelerate scientific discovery, while Jumper explains the integration of chemical and biological reasoning into protein-structure prediction. The programme connects sequence, three-dimensional structure and function, and shows how computational approaches changed what researchers can attempt in protein science. It preserves the distinction between de novo design and prediction while explaining why advances in both can support biological understanding and the creation of useful molecules.