{"url":"/dataset/toxcast-scaffold","name":"ToxCast (Toxicity Forecaster)","full_name":null,"description_markdown":"ToxCast is an initiative by the U.S. Environmental Protection Agency (EPA) aimed at predicting the potential toxicity of various chemical compounds. It involves high-throughput screening assays that evaluate thousands of chemicals across multiple biological endpoints. These endpoints cover a wide range of effects, including cell cycle disruptions, interactions with steroid receptors, and cytotoxicity.","description_withheld":null,"homepage":"https://moleculenet.org/","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":["ToxCast","ToxCast (Toxicity Forecaster)"],"data_loaders":[],"num_papers_in_archive":15,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/molecular-property-prediction-on-toxcast-1","task":"Molecular Property Prediction","dataset_variant":"ToxCast","rows":8,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"DumplingGNN","paper":"/paper/dumpling-gnn-hybrid-gnn-enables-better-adc","metrics":{"ROC-AUC":"78.2"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/drug-discovery-on-toxcast","task":"Drug Discovery","dataset_variant":"ToxCast","rows":5,"metrics":["AUC"],"first_row_in_archive_order":{"model":"TrimNet","paper":"/paper/trimnet-learning-molecular-representation","metrics":{"AUC":"0.777"},"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/graph-classification-on-toxcast","task":"Graph Classification","dataset_variant":"ToxCast","rows":3,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"GMT","paper":"/paper/accurate-learning-of-graph-representations-1","metrics":{"ROC-AUC":"65.44"},"code_links":[{"title":"JinheonBaek/GMT","url":"https://github.com/JinheonBaek/GMT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/drug-discovery-on-toxcast-scaffold","task":"Drug Discovery","dataset_variant":"ToxCast (Toxicity Forecaster)","rows":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"GLAM","paper":"/paper/an-adaptive-graph-learning-method-for","metrics":{"AUC":"0.744"},"code_links":[{"title":"yvquanli/GLAM","url":"https://github.com/yvquanli/GLAM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"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/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/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":"2026-09-24T18:15:14+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/git-mol-a-multi-modal-large-language-model","title":"GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text","date":"2023-08-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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/an-adaptive-graph-learning-method-for","title":"An adaptive graph learning method for automated molecular interactions and properties predictions","date":"2022-06-23","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":"2026-09-24T18:15:14+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/chemrl-gem-geometry-enhanced-molecular","title":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","date":"2021-06-11","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/accurate-learning-of-graph-representations-1","title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","date":"2021-02-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":5,"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/grover-self-supervised-message-passing","title":"Self-Supervised Graph Transformer on Large-Scale Molecular Data","date":"2020-06-18","rows_on_this_dataset":2,"code_links":3,"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":2,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+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/are-learned-molecular-representations-ready","title":"Analyzing Learned Molecular Representations for Property Prediction","date":"2019-04-02","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":3,"samples_unverified":12,"pointer_only_for_licence":0,"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/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":7,"samples_harvested":76,"samples_ran":31,"samples_unverified":45,"pointer_only_for_licence":21,"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."}