{"url":"/dataset/ncbi-disease-corpus","name":"NCBI Datasets","full_name":null,"description_markdown":"NCBI Datasets is a valuable resource that simplifies the process of gathering data from various NCBI databases. Whether you’re a researcher, scientist, or bioinformatician, NCBI Datasets provides an efficient way to access sequence information, annotations, and metadata for genes and genomes.","description_withheld":null,"homepage":"https://ncbi.github.io/datasets/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Feature Engineering","url":"/task/feature-engineering","datasets_with_task":"/datasets/task/feature-engineering"}],"languages":[],"variants":["NCBI Datasets"],"data_loaders":[],"num_papers_in_archive":11,"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."}