{"url":"/dataset/muv","name":"MUV","full_name":null,"description_markdown":"The Maximum Unbiased Validation (MUV) dataset is a benchmark dataset selected from PubChem BioAssay. It was created by applying a refined nearest-neighbor analysis. The MUV dataset is specifically designed for the validation of virtual screening techniques.","description_withheld":null,"homepage":"","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Graph Classification","url":"/task/graph-classification","datasets_with_task":"/datasets/task/graph-classification"},{"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":["MUV"],"data_loaders":[],"num_papers_in_archive":12,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/drug-discovery-on-muv","task":"Drug Discovery","dataset_variant":"MUV","rows":5,"metrics":["AUC"],"first_row_in_archive_order":{"model":"TrimNet","paper":"/paper/trimnet-learning-molecular-representation","metrics":{"AUC":"0.851"},"code_links":[{"title":"yvquanli/TrimNet","url":"https://github.com/yvquanli/TrimNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/molecular-property-prediction-on-muv-1","task":"Molecular Property Prediction","dataset_variant":"MUV","rows":5,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"Deep-CBN","paper":"/paper/integrating-convolutional-layers-and-biformer","metrics":{"ROC-AUC":"99.8"},"code_links":[{"title":"akianfar/Deep-CBN","url":"https://github.com/akianfar/Deep-CBN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/graph-classification-on-muv","task":"Graph Classification","dataset_variant":"MUV","rows":2,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"GTOT-Tuning","paper":"/paper/fine-tuning-graph-neural-networks-via-graph","metrics":{"ROC-AUC":"80"},"code_links":[{"title":"youjibiying/gtot-tuning","url":"https://github.com/youjibiying/gtot-tuning"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/integrating-convolutional-layers-and-biformer","title":"Integrating convolutional layers and biformer network with forward-forward and backpropagation training","date":"2025-02-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pre-training-graph-neural-networks-on","title":"Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck","date":"2025-02-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-graph-neural-networks-by","title":"Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns","date":"2023-12-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":13,"samples_ran":13,"samples_unverified":0,"pointer_only_for_licence":13,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bioact-het-a-heterogeneous-siamese-neural","title":"BioAct-Het: A Heterogeneous Siamese Neural Network for Bioactivity Prediction Using Novel Bioactivity Representatio","date":"2023-10-15","rows_on_this_dataset":1,"code_links":1,"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/fine-tuning-graph-neural-networks-via-graph","title":"Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transport","date":"2022-03-20","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/trimnet-learning-molecular-representation","title":"TrimNet: learning molecular representation from triplet messages for biomedicine","date":"2020-11-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pre-training-graph-neural-networks","title":"Strategies for Pre-training Graph Neural Networks","date":"2019-05-29","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":14,"samples_ran":10,"samples_unverified":4,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/relational-pooling-for-graph-representations","title":"Relational Pooling for Graph Representations","date":"2019-03-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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/low-data-drug-discovery-with-one-shot","title":"Low Data Drug Discovery with One-shot Learning","date":"2016-11-10","rows_on_this_dataset":1,"code_links":0,"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":"2026-09-25T09:33:49+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":"2026-09-25T09:33:49+00:00","papers_with_samples":5,"samples_harvested":58,"samples_ran":25,"samples_unverified":33,"pointer_only_for_licence":19,"papers_with_no_sample_that_ran":2,"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."}