{"success":true,"data":{"author":"DREAM Challenges organizers (Random Promoter DREAM Challenge 2022); packaged by Hugging Face Bio","bucketAccessType":"public","bucketName":"HuggingFaceBio/random-promoter-dream-2022","bucketPrefix":"","category":"Genomics & Bioinformatics","cloudProvider":"huggingface","createdAt":"2026-11-14T14:15:14.504Z","description":"Hugging Face packaging of the processed files from the Random Promoter DREAM Challenge 2022 (Zenodo record 10633252), a community benchmark for predicting gene expression from DNA sequence. Participants were given expression measurements for millions of randomly generated promoter sequences assayed in yeast and asked to train models that predict promoter activity, then scored on a separate set of designed test promoters. The supervised config has train, validation and labeled test splits with columns sequence, activity (measured promoter activity), sequence_length, source_file and row_id. Additional configs hold the unlabeled challenge test sequences, test subset membership IDs (the subsets used for scoring) and the public leaderboard IDs, each traced back to the archive member and line it came from. Measured 2026-11-14: the supervised split is four parquet files (two train shards of about 155 MB each, a 34 MB validation file and a small test file), about 0.35 GB, with repository storage of about 0.4 GB. Load with datasets.load_dataset('HuggingFaceBio/random-promoter-dream-2022', 'supervised') or pandas.read_parquet. Typical uses are sequence-to-function modelling, massively parallel reporter assay style regression, and benchmarking DNA language models and convolutional or transformer architectures for cis-regulatory grammar. The source Zenodo record is licensed CC BY 4.0; cite the DREAM Challenge data release.","displayTitle":"Random Promoter DREAM Challenge 2022","doi":"10.5281/zenodo.10633252","id":"383719ff-331a-53a7-8278-e1581a33f60c","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/api/records/10633252","objectCountEstimate":10,"probeStatus":"ok","referenceUrl":"https://doi.org/10.5281/zenodo.10633252","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"HuggingFaceBio/random-promoter-dream-2022\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"HuggingFaceBio/random-promoter-dream-2022\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=HuggingFaceBio, license:cc-by-4.0, size_categories:100K<n<1M, format:parquet, downloads=157"],"format":"mixed","generatedAt":"2026-11-14T14:15:25.250Z","layout":{"example":"challenge_test_sequences/train-00000-of-00001.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"50415231150415ccdf850115c4f0194c159696011500120000e6ef42206e0000005447434154090118434143415443415601000c43544147011c384343414154474141474347474354540505104143414747010601480c41434354012c0c47435441012b104747545441052d084754549e7200004701850c43474147014d0043017a045447017600540154011d1c5441475441415443018f1443474341435401bc05750054fe72001d72211c044141fe7200927200217a0047298efe7200a672000043fe7200c2720021c8fe56018a56010843434345920443432ee4000101fe3a025e3a02044347017305db017d0509493a004156ac020443436518e61e030172005461b6fee400b2e40001720175017f79905ae40081050043ee900311e40572751e0101fec8016ec80115e415728174fee400b6e4007a7200f2e6043556a1aea13fb5585ae400feac0255aca27200fe3a02413afe0204c602040047413afe9003869003045454717fe1150041e578010105f2e19a005411132548e5d8e1be0d05c6740400434d8f85dbe1ea11e40054453a01016a9003ce02040d720043fe7200c67200fe3c06a63c0611e4427200fe5601825601d67200c674040047419c41920043e5f94dab81060c544347474190418c055800548196005455ac859700410e580ae52600439e3e0ada7200c160651efe7200117221c372e400fe72007e","encoding":"hex","key":"challenge_test_sequences/train-00000-of-00001.parquet","truncatedAt":512}],"sampleObjects":["challenge_test_sequences/train-00000-of-00001.parquet","create_dataset.py","public_leaderboard_ids/train-00000-of-00001.parquet","supervised/test-00000-of-00001.parquet","supervised/train-00000-of-00002.parquet"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\ntask_categories:\n- text-regression\nlanguage:\n- en\ntags:\n- biology\n- dna\n- genomics\n- promoter\n- gene-expression\n- carbon\n---\n\n# Random Promoter DREAM Challenge 2022\n\nThis dataset repackages the processed Random Promoter DREAM Challenge 2022\nfiles from Zenodo record `10633252` for use with `datasets`.\n\nThe task is sequence-to-expression regression on synthetic yeast promoter\nsequences. The canonical supervised config contains random promoter training\nexamples, validation examples, and labeled designed test promoters.\n\n## Configs\n\n- `supervised`: `train`, `validation`, and `test` splits with promoter\n  sequences and measured activity.\n- `challenge_test_sequences`: unlabeled test sequences for submission-style\n  prediction workflows.\n- `test_subset_membership`: normalized IDs from `test_subset_ids.tar.gz`.\n- `public_leaderboard_ids`: normalized IDs from `public_leaderboard_ids.tar.gz`.\n\n## Schema\n\n`supervised`:\n\n- `sequence`: DNA sequence.\n- `activity`: measured promoter activity.\n- `sequence_length`: sequence length in base pairs.\n- `source_file`: source filename.\n- `row_id`: zero-based row index within the source split.\n\nID metadata configs:\n\n- `subset`: subset name inferred from the archive member.\n- `item_id`: raw ID token from the source line.\n- `row_id`: integer row ID when `item_id` is numeric; otherwise `-1`.\n- `source_member`: archive member path.\n- `line_number`: line number within the member.\n- `raw_line`: unmodified stripped source line.\n\n## Usage\n\n```py\nfrom datasets import load_dataset\n\nds = load_dataset(\"HuggingFaceBio/random-promoter-dream-2022\", \"supervised\")\ntrain = ds[\"train\"]\nvalidation = ds[\"validation\"]\ntest = ds[\"test\"]\n\nsubsets = load_dataset(\"HuggingFaceBio/random-promoter-dream-2022\", \"test_subset_membership\", split=\"train\")\n```\n\n## Source\n\nSource: Random Promoter DREAM Challenge 2022, Zenodo DOI\n`10.5281/zenodo.10633252`.\n\nThe source record is licensed CC BY 4.0. Cite the original DREAM Challenge data\nand paper when using this dataset.\n\n## Reproduction\n\nThis dataset repo includes `create_dataset.py`, the script used to download,\nconvert, and upload the configs.\n","encoding":"utf8","key":"README.md","name":"README.md","size":2145,"truncated":false}],"sourceObjectKey":"challenge_test_sequences/train-00000-of-00001.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"HuggingFaceBio/random-promoter-dream-2022\")\nprint(ds)","starterSamplePath":"challenge_test_sequences/train-00000-of-00001.parquet","totalObjects":10},"summary":"Hugging Face packaging of the processed files from the Random Promoter DREAM Challenge 2022 (Zenodo record 10633252), a community benchmark for predicting gene expression from DNA…","title":"Random Promoter DREAM Challenge 2022","updatedAt":"2026-11-14T17:47:35.901Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/HuggingFaceBio/random-promoter-dream-2022"}}