Sequence homology composition can affect performance of fine-tuned protein language models for variant effect prediction

Summary

Sequence homology composition can affect how well a fine-tuned protein language model performs for variant effect prediction (1). Here, it was used to rank possible designs given several design constraints.

Figures

Ref (1)

See also

• Sequence clustering of training data affects variant effect prediction performance by PLMs

1.

Bixby E, Brunner G, Danciu D, Dela Rosa R, Deutschmann N, Ferragu C, et al. What comes after de novo ? Automated lead optimization of proteins with CRADLE-1. openRxiv; 2026. Available from: https://doi.org/10.64898/2026.03.06.710001