RSchmirler / data-repo_plm-finetune-eval

Data repository for "Fine-tuning protein language models boosts predictions across diverse tasks"
https://www.nature.com/articles/s41467-024-51844-2
Creative Commons Attribution 4.0 International
18 stars 2 forks source link

wrong data in "./training_data/SecStr/test.pkl" #1

Closed LAJ-THU closed 2 months ago

LAJ-THU commented 2 months ago

When I was running the Embedding_Generation_GPU.ipynb notebook, I found that the test data provided in ./training_data/SecStr/test.pkl had wrong arrangement as indicated by the screenshot, with columns corresponding to wrong type of data

<img width="897" alt="image" src="https://github.com/user-attachments/assets/27593e19-a9d9-45ac-ab10-f25f9cc85ddd" Xnip2024-08-15_20-37-53

RSchmirler commented 2 months ago

Sorry for that, I just added the correct data. Something got mixed up there...