Deep Learning for New Protein Design

The Supersized Science podcast features research and discoveries nationwide enabled by advanced computing technology and expertise at the Texas Advanced Computing Center of the University of Texas at Austin. The key to understanding proteins — such as those that govern cancer, COVID-19, and other diseases — is quite simple - for scientists, anyway. Identify their chemical structure and find which other proteins can bind to them. But there’s a catch in that the search space for proteins is enormous. For instance, a typical protein studied is made of 65 amino acids, and with 20 different amino acid choices at each binding position, there are 65 to the 20th power binding combinations, a number bigger than the estimated number of atoms there are in the universe. Joining host and TACC science writer Jorge Salazar on the podcast are Brian Coventry, a research scientist with the Institute for Protein Design, University of Washington and The Howard Hughes Medical Institute; and Nathaniel Bennett, a post-doctoral scholar at the Institute for Protein Design. Coventry and Bennett co-authored a study published May 2023 in the journal Nature Communications. In it their team used deep learning methods on TACC’s Frontera supercomputer to augment existing energy-based physical models in ‘do novo’ or from-scratch computational protein design, resulting in a 10-fold increase in success rates verified in the lab for binding a designed protein with its target protein. Music Credit: Raro Bueno, Chuzausen freemusicarchive.org/music/Chuzausen/ Story link: https://tacc.utexas.edu/news/latest-news/2023/08/03/deep-learning-for-new-protein-design/