Structure-conditioned masked language models for protein sequence design generalize beyond the native sequence space
D. Akpinaroglu, K. Seki, A. Guo, E. Zhu, M. J. Kelly, T. Kortemme
This paper introduces Frame2seq, a structure-conditioned masked language model for protein sequence design that generates novel, stable proteins with low sequence identity to native sequences.
bioRxiv · Dec 15, 2023 · PreprintBioengineering