{"url":"/dataset/bace-scaffold","name":"BACE (β-secretase enzyme)","full_name":null,"description_markdown":"The BACE dataset focuses on inhibitors of human beta-secretase 1 (BACE-1).\r\nIt includes both quantitative (IC50 values) and qualitative (binary labels) binding results. The dataset comprises small molecule inhibitors across a wide range of affinities, spanning three orders of magnitude (from nanomolar to micromolar IC50 values).\r\nSpecifically, it provides:\r\n154 BACE inhibitors for affinity prediction.\r\n20 BACE inhibitors for pose prediction.\r\n34 BACE inhibitors for free energy prediction.","description_withheld":null,"homepage":"https://drugdesigndata.org/about/grand-challenge-4/bace","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":["BACE","BACE (β-secretase enzyme)"],"data_loaders":[],"num_papers_in_archive":22,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/molecular-property-prediction-on-bace-1","task":"Molecular Property Prediction","dataset_variant":"BACE","rows":20,"metrics":["ROC-AUC","RMSE"],"first_row_in_archive_order":{"model":"MolXPT","paper":"/paper/molxpt-wrapping-molecules-with-text-for","metrics":{"ROC-AUC":"88.4"},"code_links":[{"title":"zequnl/molxpt","url":"https://huggingface.co/zequnl/molxpt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/drug-discovery-on-bace","task":"Drug Discovery","dataset_variant":"BACE","rows":6,"metrics":["AUC"],"first_row_in_archive_order":{"model":"TrimNet","paper":"/paper/trimnet-learning-molecular-representation","metrics":{"AUC":"0.878"},"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-bace","task":"Graph Classification","dataset_variant":"BACE","rows":2,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"G-Tuning","paper":"/paper/fine-tuning-graph-neural-networks-by","metrics":{"ROC-AUC":"84.79"},"code_links":[{"title":"zjunet/G-Tuning","url":"https://github.com/zjunet/G-Tuning"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/drug-discovery-on-bace-scaffold","task":"Drug Discovery","dataset_variant":"BACE (β-secretase enzyme)","rows":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"GLAM","paper":"/paper/an-adaptive-graph-learning-method-for","metrics":{"AUC":"0.888"},"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/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/a-bayesian-flow-network-framework-for","title":"A Bayesian Flow Network Framework for Chemistry Tasks","date":"2024-07-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/self-guided-masked-autoencoders-for-domain","title":"Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning","date":"2024-02-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":8,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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/structure-to-property-chemical-element","title":"Structure to Property: Chemical Element Embeddings and a Deep Learning Approach for Accurate Prediction of Chemical Properties","date":"2023-09-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/molxpt-wrapping-molecules-with-text-for","title":"MolXPT: Wrapping Molecules with Text for Generative Pre-training","date":"2023-05-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/molecular-structure-property-co-trained","title":"Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model","date":"2022-11-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","rows_on_this_dataset":5,"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/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/chemberta-2-towards-chemical-foundation","title":"ChemBERTa-2: Towards Chemical Foundation Models","date":"2022-09-05","rows_on_this_dataset":1,"code_links":2,"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/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/optimal-transport-graph-neural-networks","title":"Optimal Transport Graph Neural Networks","date":"2020-06-08","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/locally-constant-networks","title":"Oblique Decision Trees from Derivatives of ReLU Networks","date":"2019-09-30","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":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/n-gram-graph-a-novel-molecule-representation","title":"N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules","date":"2018-06-24","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":0,"samples_unverified":14,"pointer_only_for_licence":0,"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":10,"samples_harvested":79,"samples_ran":37,"samples_unverified":42,"pointer_only_for_licence":16,"papers_with_no_sample_that_ran":3,"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."}