{"success":true,"data":{"author":"Westlake University REPL lab (Su, Han, Zhou, Shan, Zhou and Yuan; SaProt)","bucketAccessType":"public","bucketName":"westlake-repl/AF2_UniRef50","bucketPrefix":"","category":"Structural Biology","cloudProvider":"huggingface","createdAt":"2026-11-14T14:15:14.578Z","description":"Pre-training dataset for SaProt (Protein Language Modeling with Structure-aware Vocabulary, ICLR 2024) from the Westlake University REPL lab, linked from the SaProt repository as the dataset used to pre-train the model. Proteins are UniRef50 representatives with AlphaFold2 predicted structures from the AlphaFold Protein Structure Database, each encoded as a structure-aware sequence that interleaves the amino acid letter with the Foldseek 3Di structural letter for every residue; per the SaProt documentation the character # marks residues in low-confidence regions (pLDDT below 70). Measured 2026-11-14: train.csv (21.9 GB) and valid.csv (11 MB) with columns uniprot_id and seq, plus the same training data as an LMDB database (train/data.mdb, 36.2 GB); repository storage about 62 GB. Open the CSVs with pandas, pyarrow or datasets; open the LMDB with the lmdb package as shown on the dataset card, where each record is JSON. Uses include pre-training or fine-tuning protein language models on combined sequence and structure tokens, Foldseek 3Di modelling, and transfer to mutation effect, stability and function prediction. The structures derive from AlphaFold DB, which EMBL-EBI and Google DeepMind distribute under CC BY 4.0; cite SaProt and AlphaFold DB.","displayTitle":"AF2_UniRef50: SaProt Structure-Aware Pre-training Set","id":"dd60cee2-dc22-59ac-92b6-b4767e923164","license":"CC-BY-4.0","licenseEvidenceUrl":"https://alphafold.ebi.ac.uk/download","objectCountEstimate":8,"probeStatus":"ok","referenceUrl":"https://openreview.net/forum?id=6MRm3G4NiU","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"westlake-repl/AF2_UniRef50\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"westlake-repl/AF2_UniRef50\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=westlake-repl, license:mit, size_categories:10M<n<100M, format:csv, downloads=210"],"format":"mixed","generatedAt":"2026-11-14T14:15:21.319Z","layout":{"example":"train.csv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"uniprot_id,seq\nA0A007,MdGlYlIlHvTlAlLqKvSvAlGvFnHpHlVdIaQdVdDpTcPvAlLvGvLdDdSlEvGnLlRlKvLvLcAlDvFsEvPeDqLeVdGeVfSeTdTdTlPvGcLlPvGvAsIlEsAnClEvAsAnKvSvTsGvAhKaVyIeLyGeGyPlHhTcElVfYvAvHpElNlLqVlHrEpSsIhDaYkVyGfVaGaEdGsVsTqIqMvPsElLvAvEvAcMvEvRvGvEhEdPsEqGqIgRqGrLiVdTgRpKvHhDdGnGdAhAdPdMdVdNaLsEvEvVsGaWdPgEdRpApGnLdPpMqDqRsYdYdSdIpMvAfPdRpPsFeAeTeMdIeSfSkReGaCdPpFaKaCfSqFqCdFsKsQvAsVdDdKrKdSiMhYgRdSaPlEcDrVvVvGvEvMvTvEcLcKcEpRvWvGvVhKaEeIyMeFhYpDyDpVaFpTlLpHpRlGvRrVlRlEsInClGvLvIlGvEvTvGvLdKrVhRaWyEeAyPeThReVl","encoding":"utf8","key":"train.csv","truncatedAt":512}],"sampleObjects":["train.csv","train/data.mdb","train/lock.mdb","valid.csv","valid/data.mdb"],"sidecars":[{"bytes":"---\nlicense: mit\nconfigs:\n- config_name: dataset\n  data_files:\n  - split: train\n    path: train.csv\n  - split: valid\n    path: valid.csv\n---\n\n``AF2_UniRef50`` is organized in LMDB format. If you want to load it, you have to first download it and then open the file using the ``lmdb`` package.\n\nHere is an example of how you can get samples:\n```\nimport lmdb\n\nlmdb_dir = \"/your/path/to/AF2_UniRef50/train\"\nwith lmdb.open(lmdb_dir, readonly=True).begin() as txn:\n    length = int(txn.get('length'.encode()).decode())\n    for i in range(length):\n        data_str = txn.get(str(i).encode()).decode()\n        data = json.loads(data_str)\n        print(data)\n        break\n``` ","encoding":"utf8","key":"README.md","name":"README.md","size":669,"truncated":false}],"sourceObjectKey":"train.csv","starterCell":"import pandas as pd\ndf = pd.read_csv(\"hf://datasets/westlake-repl/AF2_UniRef50/train.csv\")\ndf.head()","starterSamplePath":"train.csv","totalObjects":8},"summary":"Pre-training dataset for SaProt (Protein Language Modeling with Structure-aware Vocabulary, ICLR 2024) from the Westlake University REPL lab, linked from the SaProt repository as…","title":"AF2_UniRef50: SaProt Structure-Aware Pre-training Set","updatedAt":"2026-11-14T17:27:50.159Z","visibility":"public","websiteUrl":"https://github.com/westlake-repl/SaProt"}}