{"success":true,"data":{"author":"Fanwang Meng, Paul W. Ayers et al. (theochem); mirror by Mao Lab, University of Michigan","bucketAccessType":"public","bucketName":"maomlab/B3DB","bucketPrefix":"","category":"Drug Discovery","cloudProvider":"huggingface","createdAt":"2026-11-22T01:09:20.905Z","description":"B3DB, the Blood-Brain Barrier Database, is a benchmark of small-molecule blood-brain barrier (BBB) permeability compiled from 50 published sources and categorized by the agreement between experimental references. It labels 7,807 compounds as BBB-permeable (BBB+) or not (BBB-), and gives numerical logBB values, the log ratio of brain to blood concentration, for 1,058 of them, together with computed physicochemical descriptors. This Hugging Face copy, prepared by the Mao Lab at the University of Michigan, mirrors the theochem/B3DB GitHub repository (the 2021 classification and 2023 regression releases) as train and test CSV configs: B3DB_classification, B3DB_classification_extended and B3DB_regression, with invalid SMILES removed or replaced in version 1.2.0 and a raw data summary of the sources. Use it to train and benchmark CNS drug-likeness and BBB penetration models for neuroscience drug discovery; load with datasets or pandas. License CC0 1.0, from the B3DB repository. Cite Meng et al., A curated diverse molecular database of blood-brain barrier permeability with chemical descriptors, Scientific Data 8, 289 (2021).","displayTitle":"B3DB: Blood-Brain Barrier Permeability Database, 7,807 Compounds with BBB+/BBB- Labels and 1,058 logBB Values","huggingFaceUrl":"https://huggingface.co/datasets/maomlab/B3DB","id":"e7eb97c1-a1f7-540a-b1c9-4babbcf995b1","license":"CC0-1.0","licenseEvidenceUrl":"https://github.com/theochem/B3DB/blob/main/LICENSE","objectCountEstimate":10,"probeStatus":"ok","referenceUrl":"https://www.nature.com/articles/s41597-021-01069-5","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"maomlab/B3DB\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"maomlab/B3DB\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=maomlab, license:cc0-1.0, size_categories:1K<n<10K, downloads=804"],"format":"mixed","generatedAt":"2026-11-22T01:10:21.441Z","layout":{"example":"B3DB_classification/test.csv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"B3DB_classification_index,compound_name,IUPAC_name,SMILES,CID,logBB,Y,Inchi,threshold,reference,group,comments,ClusterNo,MolCount\nB3DB_classification_669,chembl142158,5-chloro-2-[2-[(dimethylamino)methyl]phenyl]sulfanyl-4-fluoroaniline,CN(C)Cc1ccccc1Sc1cc(F)c(Cl)cc1N,10403162.0,0.2,1,\"InChI=1S/C15H16ClFN2S/c1-19(2)9-10-5-3-4-6-14(10)20-15-8-12(17)11(16)7-13(15)18/h3-8H,9,18H2,1-2H3\",,R20|,testing,chemical name corrected,212,3\nB3DB_classification_670,chembl190860,2-[2-[(dimethylamino)methyl]phenyl]sulfanyl-5","encoding":"utf8","key":"B3DB_classification/test.csv","truncatedAt":512}],"sampleObjects":["B3DB_classification/test.csv","B3DB_classification/train.csv","B3DB_classification_extended/test.csv","B3DB_classification_extended/train.csv","B3DB_regression/test.csv"],"sidecars":[{"bytes":"---\nversion: 1.2.0\nlanguage: en\nlicense: cc0-1.0\nsource_datasets: curated\ntask_categories:\n- tabular-classification\n- tabular-regression\ntags:\n- chemistry\n- biology\n- medical\npretty_name: Blood-Brain Barrier Database (B3DB)\ndataset_summary: Curation of 50 published resources of categorical and numeric measurements\n  of Blood-Brain Barrier penetration.\ncitation: \"@article{\\n  Meng_A_curated_diverse_2021,\\n  author = {Meng, Fanwang and\\\n  \\ Xi, Yang and Huang, Jinfeng and Ayers, Paul W.},\\n  doi = {10.1038/s41597-021-01069-5},\\n\\\n  \\  journal = {Scientific Data},\\n  number = {289},\\n  title = {A curated diverse\\\n  \\ molecular database of blood-brain barrier permeability with chemical descriptors},\\n\\\n  \\  volume = {8},\\n  year = {2021},\\n  url = {https://www.nature.com/articles/s41597-021-01069-5},\\n\\\n  \\  publisher = {Springer Nature}\\n}\"\nsize_categories:\n- 1K<n<10K\nconfig_names:\n- B3DB_classification\n- B3DB_classification_extended\n- B3DB_regression\n- B3DB_regression_extended\nconfigs:\n- config_name: B3DB_classification\n  data_files:\n  - split: test\n    path: B3DB_classification/test.csv\n  - split: train\n    path: B3DB_classification/train.csv\n- config_name: B3DB_classification_extended\n  data_files:\n  - split: test\n    path: B3DB_classification_extended/test.csv\n  - split: train\n    path: B3DB_classification_extended/train.csv\n- config_name: B3DB_regression\n  data_files:\n  - split: test\n    path: B3DB_regression/test.csv\n  - split: train\n    path: B3DB_regression/train.csv\n- config_name: B3DB_regression_extended\n  data_files:\n  - split: train\n    path: B3DB_regression_extended/train-*\n  - split: test\n    path: B3DB_regression_extended/test-*\ndataset_info:\n- config_name: B3DB_classification\n  features:\n  - name: B3DB_classification_index\n    dtype: string\n  - name: compound_name\n    dtype: string\n  - name: IUPAC_name\n    dtype: string\n  - name: SMILES\n    dtype: string\n  - name: CID\n    dtype: float64\n  - name: logBB\n    dtype: float64\n  - name: Y\n    dtype: int64\n    description: 'Binary classification where ''O'' represents \"BBB-\" and ''1'' represents\n      \"BBB+\"      '\n  - name: Inchi\n    dtype: string\n  - name: threshold\n    dtype: float64\n  - name: reference\n    dtype: string\n  - name: group\n    dtype: string\n  - name: comments\n    dtype: string\n  - name: ClusterNo\n    dtype: int64\n  - name: MolCount\n    dtype: int64\n  splits:\n  - name: train\n    num_bytes: 656000\n    num_examples: 5855\n  - name: test\n    num_bytes: 218640\n    num_examples: 1951\n- config_name: B3DB_classification_extended\n  features:\n  - name: B3DB_classification_extended_index\n    dtype: string\n  - name: compound_name\n    dtype: string\n  - name: IUPAC_name\n    dtype: string\n  - name: SMILES\n    dtype: string\n  - name: CID\n    dtype: float64\n  - name: logBB\n    dtype: float64\n  - name: Y\n    dtype: int64\n    description: 'Binary classification where ''O'' represents \"BBB-\" and ''1'' represents\n      \"BBB+\"   '\n  - name: Inchi\n    dtype: string\n  - name: threshold\n    dtype: float64\n  - name: reference\n    dtype: string\n  - name: group\n    dtype: string\n  - name: comments\n    dtype: string\n  - name: ABC\n    dtype: float64\n  - name: ABCGG\n    dtype: float64\n  - name: nAcid\n    dtype: int64\n  - name: nBase\n    dtype: int64\n  - name: SpAbs_A\n    dtype: float64\n  - name: SpMax_A\n    dtype: float64\n  - name: SpDiam_A\n    dtype: float64\n  - name: SpAD_A\n    dtype: float64\n  - name: SpMAD_A\n    dtype: float64\n  - name: LogEE_A\n    dtype: float64\n  - name: VE1_A\n    dtype: float64\n  - name: VE2_A\n    dtype: float64\n  - name: VE3_A\n    dtype: float64\n  - name: VR1_A\n    dtype: float64\n  - name: VR2_A\n    dtype: float64\n  - name: VR3_A\n    dtype: float64\n  - name: nAromAtom\n    dtype: int64\n  - name: nAromBond\n    dtype: int64\n  - name: nAtom\n    dtype: int64\n  - name: nHeavyAtom\n    dtype: int64\n  - name: nSpiro\n    dtype: int64\n  - name: nBridgehead\n    dtype: int64\n  - name: nHetero\n    dtype: int64\n  - name: nH\n    dtype: int64\n  - name: nB\n    dtype: int64\n  - name: nC\n    dtype: int64\n  - name: nN\n    dtype: int64\n  - name: nO\n    dtype: int64\n  - name: n","encoding":"utf8","key":"README.md","name":"README.md","size":127905,"truncated":true}],"sourceObjectKey":"B3DB_classification/test.csv","starterCell":"import pandas as pd\ndf = pd.read_csv(\"hf://datasets/maomlab/B3DB/B3DB_classification/test.csv\")\ndf.head()","starterSamplePath":"B3DB_classification/test.csv","totalObjects":10},"summary":"B3DB, the Blood-Brain Barrier Database, is a benchmark of small-molecule blood-brain barrier (BBB) permeability compiled from 50 published sources and categorized by the agreement…","title":"B3DB: Blood-Brain Barrier Permeability Database, 7,807 Compounds with BBB+/BBB- Labels and 1,058 logBB Values","updatedAt":"2026-11-22T04:00:46.627Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/maomlab/B3DB"}}