Datasets for Mutation Effect Prediction (Master Thesis)

This upload contains datasets used in my Master's thesis on mutation effect prediction. Included files:- Benchmark datasets (UBE4B, GRB2, PTEN activity, PTEN abundance, Alpha-Amylase)- Blind evaluation datasets (DLG4 abundance and DLG4 binding)- PETase zero-shot dataset Original benchmark datasets were obtained from: - https://github.com/gitter-lab/metl-pub- https://github.com/Align-to-Innovate/the-protein-engineering-tournament-2023 Users should consult the original repositories for dataset provenance and licensing information. The PETase dataset is included solely for reproducibility of the analyses presented in the thesis.