refactor multi test set datasets; add seq id test splits to GO

a-r-j / ProteinWorkshop

Benchmarking framework for protein representation learning. Includes a large number of pre-training and downstream task datasets, models and training/task utilities. (ICLR 2024)

https://proteins.sh/

MIT License

194 stars 16 forks source link

refactor multi test set datasets; add seq id test splits to GO #72

Closed a-r-j closed 8 months ago

a-r-j commented 8 months ago

Improves API for multi test set datasets
Improves setup in base datamodule to avoid setting up all datasets at once
Adds caching to avoid duplicating in memory loading
Adds seq id splits to GO dataset.

amorehead commented 8 months ago

Besides the two comments above, LGTM!