{"url":"/dataset/ht-docking","name":"HT Docking","full_name":null,"description_markdown":"**HT Docking** is a dataset consisting of 200 million 3D complex structures and 2D structure scores across a consistent set of 13 million ``in-stock'' molecules over 15 receptors, or binding sites, across the SARS-CoV-2 proteome. It is used to study surrogate model accuracy for protein-ligand docking.","description_withheld":null,"homepage":"https://2019-ncovgroup.github.io/HTDockingDataRepo/","introduced_date":"2021-06-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/protein-ligand-docking-surrogate-models-a","title":"Protein-Ligand Docking Surrogate Models: A SARS-CoV-2 Benchmark for Deep Learning Accelerated Virtual Screening","first_author":"Austin Clyde","url":null},"license":{"name":"Unknown","url":null},"modalities":[],"tasks":[{"name":"task","url":null,"datasets_with_task":"/datasets/task/task"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["HT Docking"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"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."}