{"url":"/dataset/pcba","name":"PCBA","full_name":null,"description_markdown":"PCBA dataset 11 is a collection of high-quality dose-response data, formulated as a multitask learning benchmark from 128 high-throughput screening (HTS) assays.","description_withheld":null,"homepage":"","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Drug Discovery","url":"/task/drug-discovery","datasets_with_task":"/datasets/task/drug-discovery"},{"name":"Molecular Property Prediction","url":"/task/molecular-property-prediction","datasets_with_task":"/datasets/task/molecular-property-prediction"}],"languages":[],"variants":["PCBA"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/drug-discovery-on-pcba","task":"Drug Discovery","dataset_variant":"PCBA","rows":2,"metrics":["AUC"],"first_row_in_archive_order":{"model":"GraphConv + dummy super node","paper":"/paper/learning-graph-level-representation-for-drug","metrics":{"AUC":"0.867"},"code_links":[{"title":"microljy/graph_level_drug_discovery","url":"https://github.com/microljy/graph_level_drug_discovery"},{"title":"ZJULearning/graph_level_drug_discovery","url":"https://github.com/ZJULearning/graph_level_drug_discovery"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/molecular-property-prediction-on-pcba","task":"Molecular Property Prediction","dataset_variant":"PCBA","rows":2,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"DumplingGNN","paper":"/paper/dumpling-gnn-hybrid-gnn-enables-better-adc","metrics":{"ROC-AUC":"88.87"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/dumpling-gnn-hybrid-gnn-enables-better-adc","title":"Dumpling GNN: Hybrid GNN Enables Better ADC Payload Activity Prediction Based on Chemical Structure","date":"2024-09-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/uni-mol-a-universal-3d-molecular","title":"Uni-Mol: A Universal 3D Molecular Representation Learning Framework","date":"2022-09-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-graph-level-representation-for-drug","title":"Learning Graph-Level Representation for Drug Discovery","date":"2017-09-12","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/convolutional-networks-on-graphs-for-learning","title":"Convolutional Networks on Graphs for Learning Molecular Fingerprints","date":"2015-09-30","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":26,"samples_ran":0,"samples_unverified":26,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":26,"samples_ran":0,"samples_unverified":26,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}