{"url":"/dataset/dockstring","name":"dockstring","full_name":null,"description_markdown":"Regression dataset for molecular docking scores (predicted molecule-protein binding affinity). Contains ~250,000 molecules against 58 protein targets.","description_withheld":null,"homepage":"https://dockstring.github.io/","introduced_date":"2021-10-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/dockstring-easy-molecular-docking-yields","title":"DOCKSTRING: easy molecular docking yields better benchmarks for ligand design","first_author":"Miguel García-Ortegón","url":null},"license":{"name":"Apache-2.0 license","url":null},"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Graph Regression","url":"/task/graph-regression","datasets_with_task":"/datasets/task/graph-regression"}],"languages":[],"variants":["dockstring","ESR2","F2","KIT","PARP1","PGR "],"data_loaders":[],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/graph-regression-on-esr2","task":"Graph Regression","dataset_variant":"ESR2","rows":9,"metrics":["R2","RMSE"],"first_row_in_archive_order":{"model":"ESA (Edge set attention, no positional encodings)","paper":"/paper/masked-attention-is-all-you-need-for-graphs","metrics":{"R2":"0.697±0.000","RMSE":"0.486±0.697"},"code_links":[{"title":"davidbuterez/edge-set-attention","url":"https://github.com/davidbuterez/edge-set-attention"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/graph-regression-on-f2","task":"Graph Regression","dataset_variant":"F2","rows":9,"metrics":["R2","RMSE"],"first_row_in_archive_order":{"model":"ESA (Edge set attention, no positional encodings)","paper":"/paper/masked-attention-is-all-you-need-for-graphs","metrics":{"R2":"0.891±0.000","RMSE":"0.335±0.891"},"code_links":[{"title":"davidbuterez/edge-set-attention","url":"https://github.com/davidbuterez/edge-set-attention"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/graph-regression-on-kit","task":"Graph Regression","dataset_variant":"KIT","rows":9,"metrics":["R2","RMSE"],"first_row_in_archive_order":{"model":"PNA","paper":"/paper/principal-neighbourhood-aggregation-for-graph","metrics":{"R2":"0.843±0.000","RMSE":"0.430±0.843"},"code_links":[{"title":"rusty1s/pytorch_geometric","url":"https://github.com/rusty1s/pytorch_geometric"},{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl"},{"title":"lukecavabarrett/pna","url":"https://github.com/lukecavabarrett/pna"},{"title":"Saro00/DGN","url":"https://github.com/Saro00/DGN"},{"title":"alexOarga/haiku-geometric","url":"https://github.com/alexOarga/haiku-geometric/blob/main/haiku_geometric/nn/conv/pna_conv.py"},{"title":"cvignac/SMP","url":"https://github.com/cvignac/SMP"},{"title":"asarigun/GraphMixerNetworks","url":"https://github.com/asarigun/GraphMixerNetworks"},{"title":"changminwu/expandergnn","url":"https://github.com/changminwu/expandergnn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/graph-regression-on-parp1","task":"Graph Regression","dataset_variant":"PARP1","rows":9,"metrics":["R2","RMSE"],"first_row_in_archive_order":{"model":"ESA (Edge set attention, no positional encodings)","paper":"/paper/masked-attention-is-all-you-need-for-graphs","metrics":{"R2":"0.925±0.000","RMSE":"0.343±0.925"},"code_links":[{"title":"davidbuterez/edge-set-attention","url":"https://github.com/davidbuterez/edge-set-attention"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/masked-attention-is-all-you-need-for-graphs","title":"An end-to-end attention-based approach for learning on graphs","date":"2024-02-16","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/pure-transformers-are-powerful-graph-learners","title":"Pure Transformers are Powerful Graph Learners","date":"2022-07-06","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":7,"samples_unverified":0,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dropgnn-random-dropouts-increase-the","title":"DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks","date":"2021-11-11","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/do-transformers-really-perform-bad-for-graph","title":"Do Transformers Really Perform Bad for Graph Representation?","date":"2021-06-09","rows_on_this_dataset":4,"code_links":5,"syntology":null},{"paper":"/paper/how-attentive-are-graph-attention-networks","title":"How Attentive are Graph Attention Networks?","date":"2021-05-30","rows_on_this_dataset":4,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":6,"samples_unverified":10,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/principal-neighbourhood-aggregation-for-graph","title":"Principal Neighbourhood Aggregation for Graph Nets","date":"2020-04-12","rows_on_this_dataset":4,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":55,"samples_ran":33,"samples_unverified":22,"pointer_only_for_licence":48,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/how-powerful-are-graph-neural-networks","title":"How Powerful are Graph Neural Networks?","date":"2018-10-01","rows_on_this_dataset":4,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":3,"samples_unverified":7,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/graph-attention-networks","title":"Graph Attention Networks","date":"2017-10-30","rows_on_this_dataset":4,"code_links":93,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":106,"samples_ran":50,"samples_unverified":56,"pointer_only_for_licence":43,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semi-supervised-classification-with-graph","title":"Semi-Supervised Classification with Graph Convolutional Networks","date":"2016-09-09","rows_on_this_dataset":4,"code_links":55,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":58,"samples_ran":31,"samples_unverified":27,"pointer_only_for_licence":22,"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":255,"samples_ran":130,"samples_unverified":125,"pointer_only_for_licence":126,"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."}