An international research team led by the University of Washington scientists has successfully applied reinforcement learning, a type of machine learning where a computer program learns to make decisions through different actions and feedback to develop a new protein design software.
Researchers took a “top-down” approach to carry out the design, where they begin with a specification of the desired properties of the protein structure, such as overall symmetry and porosity.
The research is a significant milestone in using artificial intelligence to conduct protein research and has overcome the limitations of other methods, paving a new approach to science. The team believes this method could allow the community to create therapeutic proteins, vaccines and other molecules.
“Our approach is unique because we use reinforcement learning to solve the problem of creating protein shapes that fit together like pieces of a puzzle,” said co-lead author Isaac D. Lutz, a doctoral student at the UW Medicine Institute for Protein Design. “This simply was not possible using prior approaches and has the potential to transform the types of molecules we can build.”