{"url":"/dataset/gad","name":"GAD","full_name":"Gene Associations Database","description_markdown":"**GAD**, or **Gene Associations Database**, is a corpus of gene-disease associations curated from genetic association studies.","description_withheld":null,"homepage":"https://maayanlab.cloud/Harmonizome/dataset/GAD+Gene-Disease+Associations","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Relation Extraction","url":"/task/relation-extraction","datasets_with_task":"/datasets/task/relation-extraction"},{"name":"Medical Relation Extraction","url":"/task/medical-relation-extraction","datasets_with_task":"/datasets/task/medical-relation-extraction"}],"languages":[],"variants":["GAD"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/bigbio/gad","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/relation-extraction-on-gad","task":"Relation Extraction","dataset_variant":"GAD","rows":3,"metrics":["F1","Micro F1"],"first_row_in_archive_order":{"model":"BioLinkBERT (large)","paper":"/paper/linkbert-pretraining-language-models-with","metrics":{"F1":"84.90","Micro F1":"84.90"},"code_links":[{"title":"michiyasunaga/LinkBERT","url":"https://github.com/michiyasunaga/LinkBERT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":0,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improving-biomedical-pretrained-language","title":"Improving Biomedical Pretrained Language Models with Knowledge","date":"2021-04-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/domain-specific-language-model-pretraining","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","date":"2020-07-31","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":14,"samples_ran":0,"samples_unverified":14,"pointer_only_for_licence":0,"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."}