Summary
Fitness prediction using inverse folding can be improved by including B-factor prediction and SASA prediction as auxiliary losses (1). However, the optimal balance for these still favors the majority of the loss focused on cross-entropy loss of residue identity.
Figures
Figure S8 of (1)
1.
Zhou B, Zheng L, Wu B, Tan Y, Lv O, Yi K, et al. Protein Engineering with Lightweight Graph Denoising Neural Networks. Journal of Chemical Information and Modeling. 2024;64(9):3650–61. Available from: https://doi.org/10.1021/acs.jcim.4c00036