Protein design and variant prediction using autoregressive generative models

The ability to design functional sequences is central to protein engineering and biotherapeutics. Here the authors introduce a deep generative alignment-free model for sequence design applied to highly variable regions and design and test a diverse nanobody library with improved properties for selec...

Full description

Bibliographic Details

Published in:	Nature Communications
Main Authors:	Jung-Eun Shin, Adam J. Riesselman, Aaron W. Kollasch, Conor McMahon, Elana Simon, Chris Sander, Aashish Manglik, Andrew C. Kruse, Debora S. Marks
Format:	Article
Language:	English
Published:	Nature Portfolio 2021-04-01
Online Access:	https://doi.org/10.1038/s41467-021-22732-w