Summary
scFvs generated using BERT PLMs tend to have more mutations, and tend to be tighter binders, compared to those generated using PSSMs. In turn, PSSMs for Ab engineering outperforms random.
Figures
Ref (1)
1.
Li L, Gupta E, Spaeth J, Shing L, Jaimes R, Engelhart E, et al. Machine learning optimization of candidate antibody yields highly diverse sub-nanomolar affinity antibody libraries. Nature Communications. 2023;14(1). Available from: https://doi.org/10.1038/s41467-023-39022-2