#machine learning
Mar 2026
How to make the most of your masked language model for protein engineering
This work proposes a flexible, effective sampling method for masked language models (MLMs), and reports results from an extensive in vitro head-to-head evaluation for the antibody engineering setting, revealing that the choice of sampling method can have a substantial impact, motivating future research into this under-explored area.
Calvin McCarter, Nicholas Bhattacharya, Sebastian W. Ober et al.
· arXiv.org · 1 citation