omtx/lula-data-public-train-test download history

omtx/lula-data-public-train-test is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 207 times (73 in the last 7 days), and 318 times in total. It ranks #66,183 among datasets by monthly downloads.

LULA Data Public Train/Test This dataset contains 6,819,817 protein-small-molecule pairs with binary bioactivity labels and fixed train/test splits. Fields pair_id: stable identifier for the protein-molecule pair. canonical_smiles: canonical molecule SMILES. protein_se

Open omtx/lula-data-public-train-test on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.