{"url":"/dataset/proteinkg25","name":"ProteinKG25","full_name":null,"description_markdown":"ProteinKG25 is a large-scale KG dataset with aligned descriptions and protein sequences respectively to GO terms and proteins entities. ProteinKG25 contains 4,990,097 triplets (4,879,951 Protein-GO triplets and 110,146 GO-GO triplets), 612,483 entities (565,254 proteins and 47,229 GO terms) and 31 relations.","description_withheld":null,"homepage":"https://github.com/zjunlp/OntoProtein/","introduced_date":"2022-01-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/ontoprotein-protein-pretraining-with-gene-1","title":"OntoProtein: Protein Pretraining With Gene Ontology Embedding","first_author":"Ningyu Zhang","url":null},"license":null,"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Link Prediction","url":"/task/link-prediction","datasets_with_task":"/datasets/task/link-prediction"}],"languages":[],"variants":["ProteinKG25"],"data_loaders":[],"num_papers_in_archive":8,"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":"2026-09-24T18:15:14+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."}