{"url":"/dataset/ps4","name":"PS4","full_name":null,"description_markdown":"A dataset of 18,731 proteins with their PDB code, index of the first residue in their respective DSSP file, their residue sequence and 9-category secondary structure sequence (including polyproline helices).","description_withheld":null,"homepage":"https://github.com/omarperacha/ps4-dataset","introduced_date":"2023-03-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/ps4-a-next-generation-dataset-for-protein","title":"PS4: a Next-Generation Dataset for Protein Single Sequence Secondary Structure Prediction","first_author":"Omar Peracha","url":null},"license":{"name":"CC0-1.0 license","url":"https://github.com/omarperacha/ps4-dataset/blob/main/LICENSE"},"modalities":[{"name":"Biology","url":"/datasets/modality/biology"}],"tasks":[{"name":"Protein Secondary Structure Prediction","url":"/task/protein-secondary-structure-prediction","datasets_with_task":"/datasets/task/protein-secondary-structure-prediction"},{"name":"Protein Annotation","url":"/task/protein-annotation","datasets_with_task":"/datasets/task/protein-annotation"},{"name":"Protein Folding","url":"/task/protein-folding","datasets_with_task":"/datasets/task/protein-folding"}],"languages":[],"variants":["PS4"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/protein-secondary-structure-prediction-on-ps4","task":"Protein Secondary Structure Prediction","dataset_variant":"PS4","rows":2,"metrics":["Q8"],"first_row_in_archive_order":{"model":"PS4-Mega","paper":"/paper/ps4-a-next-generation-dataset-for-protein","metrics":{"Q8":"0.782"},"code_links":[{"title":"omarperacha/ps4-dataset","url":"https://github.com/omarperacha/ps4-dataset"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/ps4-a-next-generation-dataset-for-protein","title":"PS4: a Next-Generation Dataset for Protein Single Sequence Secondary Structure Prediction","date":"2023-03-01","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+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."}