Summary
When designing Single chain variable fragments, Gibbs sampling was found to be less effective than either genetic algorithms or simple greedy hill-climbing (fitness functions were either PSSMs, BERT language models, or Gaussian processes; (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