{"url":"/dataset/gue","name":"GUE","full_name":"Genome Understanding Evaluation","description_markdown":"A collection of $28$ datasets across $7$ tasks constructed for genome language model evaluation. Contains seven tasks: promoter prediction. core promoter prediction, splice site prediction, covid variant classification, epigenetic marks prediction, and  transcription factor binding sites prediction on human and mouse.","description_withheld":null,"homepage":"https://github.com/Zhihan1996/DNABERT_2","introduced_date":"2023-06-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/dnabert-2-efficient-foundation-model-and","title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome","first_author":"Zhihan Zhou","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Promoter Detection","url":"/task/promoter-detection","datasets_with_task":"/datasets/task/promoter-detection"},{"name":"Core Promoter Detection","url":"/task/core-promoter-detection","datasets_with_task":"/datasets/task/core-promoter-detection"},{"name":"Splice Site Prediction","url":"/task/splice-site-prediction","datasets_with_task":"/datasets/task/splice-site-prediction"},{"name":"Covid Variant Prediction","url":"/task/covid-variant-prediction","datasets_with_task":"/datasets/task/covid-variant-prediction"},{"name":"Epigenetic Marks Prediction","url":"/task/epigenetic-marks-prediction","datasets_with_task":"/datasets/task/epigenetic-marks-prediction"},{"name":"Transcription Factor Binding Site Prediction (Human)","url":"/task/transcription-factor-binding-site-prediction-1","datasets_with_task":"/datasets/task/transcription-factor-binding-site-prediction-1"},{"name":"Transcription Factor Binding Site Prediction (Mouse)","url":"/task/transcription-factor-binding-site-prediction-2","datasets_with_task":"/datasets/task/transcription-factor-binding-site-prediction-2"},{"name":"Genome Understanding","url":"/task/genome-understanding","datasets_with_task":"/datasets/task/genome-understanding"}],"languages":[],"variants":["GUE"],"data_loaders":[],"num_papers_in_archive":13,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/core-promoter-detection-on-gue","task":"Core Promoter Detection","dataset_variant":"GUE","rows":1,"metrics":["MCC"],"first_row_in_archive_order":{"model":"DNABERT-2-117M","paper":"/paper/dnabert-2-efficient-foundation-model-and","metrics":{"MCC":"70.52"},"code_links":[{"title":"jerryji1993/dnabert","url":"https://github.com/jerryji1993/dnabert"},{"title":"magics-lab/dnabert_2","url":"https://github.com/magics-lab/dnabert_2"},{"title":"zhihan1996/dnabert_2","url":"https://github.com/zhihan1996/dnabert_2"},{"title":"frederikkemarin/bend","url":"https://github.com/frederikkemarin/bend"},{"title":"jimmylihui/genbench","url":"https://github.com/jimmylihui/genbench"},{"title":"jimmylihui/OpenGenome","url":"https://github.com/jimmylihui/OpenGenome"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/covid-variant-prediction-on-gue","task":"Covid Variant Prediction","dataset_variant":"GUE","rows":1,"metrics":["Avg F1"],"first_row_in_archive_order":{"model":"DNABERT-2-117M","paper":"/paper/dnabert-2-efficient-foundation-model-and","metrics":{"Avg F1":"71.02"},"code_links":[{"title":"jerryji1993/dnabert","url":"https://github.com/jerryji1993/dnabert"},{"title":"magics-lab/dnabert_2","url":"https://github.com/magics-lab/dnabert_2"},{"title":"zhihan1996/dnabert_2","url":"https://github.com/zhihan1996/dnabert_2"},{"title":"frederikkemarin/bend","url":"https://github.com/frederikkemarin/bend"},{"title":"jimmylihui/genbench","url":"https://github.com/jimmylihui/genbench"},{"title":"jimmylihui/OpenGenome","url":"https://github.com/jimmylihui/OpenGenome"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/epigenetic-marks-prediction-on-gue","task":"Epigenetic Marks Prediction","dataset_variant":"GUE","rows":1,"metrics":["MCC"],"first_row_in_archive_order":{"model":"DNABERT-2-117M","paper":"/paper/dnabert-2-efficient-foundation-model-and","metrics":{"MCC":"55.98"},"code_links":[{"title":"jerryji1993/dnabert","url":"https://github.com/jerryji1993/dnabert"},{"title":"magics-lab/dnabert_2","url":"https://github.com/magics-lab/dnabert_2"},{"title":"zhihan1996/dnabert_2","url":"https://github.com/zhihan1996/dnabert_2"},{"title":"frederikkemarin/bend","url":"https://github.com/frederikkemarin/bend"},{"title":"jimmylihui/genbench","url":"https://github.com/jimmylihui/genbench"},{"title":"jimmylihui/OpenGenome","url":"https://github.com/jimmylihui/OpenGenome"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/promoter-detection-on-gue","task":"Promoter Detection","dataset_variant":"GUE","rows":1,"metrics":["MCC"],"first_row_in_archive_order":{"model":"DNABERT-2-117M","paper":"/paper/dnabert-2-efficient-foundation-model-and","metrics":{"MCC":"84.21"},"code_links":[{"title":"jerryji1993/dnabert","url":"https://github.com/jerryji1993/dnabert"},{"title":"magics-lab/dnabert_2","url":"https://github.com/magics-lab/dnabert_2"},{"title":"zhihan1996/dnabert_2","url":"https://github.com/zhihan1996/dnabert_2"},{"title":"frederikkemarin/bend","url":"https://github.com/frederikkemarin/bend"},{"title":"jimmylihui/genbench","url":"https://github.com/jimmylihui/genbench"},{"title":"jimmylihui/OpenGenome","url":"https://github.com/jimmylihui/OpenGenome"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/splice-site-prediction-on-gue","task":"Splice Site Prediction","dataset_variant":"GUE","rows":1,"metrics":["MCC"],"first_row_in_archive_order":{"model":"DNABERT-2-117M","paper":"/paper/dnabert-2-efficient-foundation-model-and","metrics":{"MCC":"84.99"},"code_links":[{"title":"jerryji1993/dnabert","url":"https://github.com/jerryji1993/dnabert"},{"title":"magics-lab/dnabert_2","url":"https://github.com/magics-lab/dnabert_2"},{"title":"zhihan1996/dnabert_2","url":"https://github.com/zhihan1996/dnabert_2"},{"title":"frederikkemarin/bend","url":"https://github.com/frederikkemarin/bend"},{"title":"jimmylihui/genbench","url":"https://github.com/jimmylihui/genbench"},{"title":"jimmylihui/OpenGenome","url":"https://github.com/jimmylihui/OpenGenome"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/transcription-factor-binding-site-prediction","task":"Transcription Factor Binding Site Prediction (Human)","dataset_variant":"GUE","rows":1,"metrics":["MCC"],"first_row_in_archive_order":{"model":"DNABERT-2-117M","paper":"/paper/dnabert-2-efficient-foundation-model-and","metrics":{"MCC":"70.10"},"code_links":[{"title":"jerryji1993/dnabert","url":"https://github.com/jerryji1993/dnabert"},{"title":"magics-lab/dnabert_2","url":"https://github.com/magics-lab/dnabert_2"},{"title":"zhihan1996/dnabert_2","url":"https://github.com/zhihan1996/dnabert_2"},{"title":"frederikkemarin/bend","url":"https://github.com/frederikkemarin/bend"},{"title":"jimmylihui/genbench","url":"https://github.com/jimmylihui/genbench"},{"title":"jimmylihui/OpenGenome","url":"https://github.com/jimmylihui/OpenGenome"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/transcription-factor-binding-site-prediction-1","task":"Transcription Factor Binding Site Prediction (Mouse)","dataset_variant":"GUE","rows":1,"metrics":["MCC"],"first_row_in_archive_order":{"model":"DNABERT-2-117M","paper":"/paper/dnabert-2-efficient-foundation-model-and","metrics":{"MCC":"67.99"},"code_links":[{"title":"jerryji1993/dnabert","url":"https://github.com/jerryji1993/dnabert"},{"title":"magics-lab/dnabert_2","url":"https://github.com/magics-lab/dnabert_2"},{"title":"zhihan1996/dnabert_2","url":"https://github.com/zhihan1996/dnabert_2"},{"title":"frederikkemarin/bend","url":"https://github.com/frederikkemarin/bend"},{"title":"jimmylihui/genbench","url":"https://github.com/jimmylihui/genbench"},{"title":"jimmylihui/OpenGenome","url":"https://github.com/jimmylihui/OpenGenome"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/dnabert-2-efficient-foundation-model-and","title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome","date":"2023-06-26","rows_on_this_dataset":7,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":23,"samples_ran":8,"samples_unverified":15,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":23,"samples_ran":8,"samples_unverified":15,"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."}