{"success":true,"data":{"author":"Murat Cihan Sorkun, Abhishek Khetan, Suleyman Er (AMD group); mirror by Mao Lab, University of Michigan","bucketAccessType":"public","bucketName":"maomlab/AqSolDB","bucketPrefix":"","category":"Drug Discovery","cloudProvider":"huggingface","createdAt":"2026-11-22T01:09:20.940Z","description":"AqSolDB is a curated reference set of experimental aqueous solubility values for 9,982 unique compounds, merged from nine publicly available solubility datasets by the Autonomous Energy Materials Discovery (AMD) group. Each compound has a name, SMILES, InChI and InChIKey, the solubility as log mol/L (logS), the standard deviation across sources, the number of occurrences, a reliability group from the curation, and RDKit descriptors such as molecular weight, logP, molar refractivity, hydrogen bond donors and acceptors, rotatable bonds and ring counts. This Hugging Face copy from the Mao Lab at the University of Michigan mirrors the official mcsorkun/AqSolDB repository (2019) as a 7,488-row train and 2,494-row test split, with a few SMILES that RDKit could not parse replaced in version 1.1.0. Use it to train and benchmark solubility prediction for drug discovery, environmental fate and materials; load with datasets or pandas. Released under CC0 1.0 on Harvard Dataverse (DOI 10.7910/DVN/OVHAW8). Cite Sorkun, Khetan and Er, AqSolDB, a curated reference set of aqueous solubility and 2D descriptors for a diverse set of compounds, Scientific Data 6, 143 (2019).","displayTitle":"AqSolDB: Curated Aqueous Solubility (logS) of 9,982 Unique Compounds from Nine Public Datasets","doi":"10.7910/DVN/OVHAW8","huggingFaceUrl":"https://huggingface.co/datasets/maomlab/AqSolDB","id":"da76d595-4b57-5591-9bbc-bdf52aecb84c","license":"CC0-1.0","licenseEvidenceUrl":"https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/OVHAW8","objectCountEstimate":4,"probeStatus":"ok","referenceUrl":"https://github.com/mcsorkun/AqSolDB","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"maomlab/AqSolDB\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"maomlab/AqSolDB\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=maomlab, license:mit, size_categories:1K<n<10K, format:csv, downloads=581"],"format":"mixed","generatedAt":"2026-11-22T01:10:22.025Z","layout":{"example":"AqSolDB/test.csv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"ID,Name,InChI,InChIKey,SMILES,Y,SD,Ocurrences,Group,MolWt,MolLogP,MolMR,HeavyAtomCount,NumHAcceptors,NumHDonors,NumHeteroatoms,NumRotatableBonds,NumValenceElectrons,NumAromaticRings,NumSaturatedRings,NumAliphaticRings,RingCount,TPSA,LabuteASA,BalabanJ,BertzCT,ClusterNo,MolCount,group\nF-1054,propyl 2-(6-methoxynaphthalen-2-yl)propanoate,\"InChI=1S/C17H20O3/c1-4-9-20-17(18)12(2)13-5-6-15-11-16(19-3)8-7-14(15)10-13/h5-8,10-12H,4,9H2,1-3H3\",ROGSRAKQDLOYRS-UHFFFAOYSA-N,CCCOC(=O)C(C)c1ccc2cc(OC)ccc2c1,-5.82,0.0,1,","encoding":"utf8","key":"AqSolDB/test.csv","truncatedAt":512}],"sampleObjects":["AqSolDB/test.csv","AqSolDB/train.csv"],"sidecars":[{"bytes":"---\nversion: 1.1.0\nlanguage: en\nlicense: mit\nsource_datasets: curated\ntask_categories:\n- tabular-regression\ntags:\n- chemistry\n- cheminformatics\npretty_name: Aqueous Solubility Database (AqSolDB)\ndataset_summary: >-\n  AqsolDB contains solubility data for 9,982 unique compounds, curated from nine publicly available aqueous solubility datasets.\ncitation: >-\n  @article{\n    author = {Murat Cihan Sorkun, Abhishek Khetan \\& Süleyman Er},\n    title = {AqSolDB, a curated reference set of aqueous solubility and 2D descriptors for a diverse set of compounds},\n    journal = {Scientific Data},\n    year = {2019},\n    volume = {6},\n    number = {143},\n    month = {aug},\n    url = {https://www.nature.com/articles/s41597-019-0151-1},\n    publisher = {Springer Nature}\nsize_categories:\n- 1K<n<10K\nconfig_names:\n- AqSolDB\nconfigs:\n- config_name: AqSolDB\n  data_files:\n  - split: test\n    path: AqSolDB/test.csv\n  - split: train\n    path: AqSolDB/train.csv\ndataset_info:\n- config_name: AqSolDB\n  features:    \n    - name: \"ID\"\n      dtype: string\n    - name: \"Name\"\n      dtype: string\n    - name: \"InChI\"\n      dtype: string\n    - name: \"InChIKey\"\n      dtype: string\n    - name: \"SMILES\"\n      dtype: string\n    - name: \"Y\"\n      dtype: float64\n    - name: \"SD\"\n      dtype: float64\n    - name: \"Ocurrences\"\n      dtype: int64\n    - name: \"Group\"\n      dtype: string\n    - name: \"MolWt\"\n      dtype: float64\n    - name: \"MolLogP\"\n      dtype: float64\n    - name: \"MolMR\"\n      dtype: float64\n    - name: \"HeavyAtomCount\"\n      dtype: float64\n    - name: \"NumHAcceptors\"\n      dtype: float64\n    - name: \"NumHDonors\"\n      dtype: float64\n    - name: \"NumHeteroatoms\"\n      dtype: float64\n    - name: \"NumRotatableBonds\"\n      dtype: float64\n    - name: \"NumValenceElectrons\"\n      dtype: float64\n    - name: \"NumAromaticRings\"\n      dtype: float64\n    - name: \"NumSaturatedRings\"\n      dtype: float64\n    - name: \"NumAliphaticRings\"\n      dtype: float64\n    - name: \"RingCount\"\n      dtype: float64\n    - name: \"TPSA\"\n      dtype: float64\n    - name: \"LabuteASA\"\n      dtype: float64\n    - name: \"BalabanJ\"\n      dtype: float64\n    - name: \"BertzCT\"\n      dtype: float64\n    - name: \"ClusterNo\"\n      dtype: int64\n    - name: \"MolCount\"\n      dtype: int64\n    - name: \"group\"\n      dtype: string\n  splits:\n    - name: train\n      num_bytes: 1737344\n      num_examples: 7488\n    - name: test\n      num_bytes: 578736\n      num_examples: 2494\n---\n\n# Aqueous Solubility Database (AqSolDB)\n\nAqSolDB is created by the Autonomous Energy Materials Discovery [AMD] research group, consists of aqueous solubility values of \n9,982 unique compounds curated from 9 different publicly available aqueous solubility datasets. This openly accessible dataset, \nwhich is the largest of its kind, and will not only serve as a useful reference source of measured solubility data, but also \nas a much improved and generalizable training data source for building data-driven models.\n\nThis is a mirror of the [official Github repo](https://github.com/mcsorkun/AqSolDB) where the dataset was uploaded in 2019.\n\n[Updates 2025.08.01 - version 1.1.0]\nReplaced invalid SMILES strings that could not be parsed by RDKit with valid SMILES.\n- 'CC1=[C-]C=C[NH+2]([O-])C1' -> 'Cc1ccc[n+]([O-])c1'\n- 'O=C([O-])C1=C[NH+2]([O-])CC=C1' -> 'O=C(O)c1ccc[n+]([O-])c1'\n\n\n## Quickstart Usage\n\n### Load a dataset in python\nEach subset can be loaded into python using the Huggingface [datasets](https://huggingface.co/docs/datasets/index) library.\nFirst, from the command line install the `datasets` library\n\n    $ pip install datasets\n\nthen, from within python load the datasets library\n\n    >>> import datasets\n   \nand load one of the `AqSolDB` datasets, e.g.,\n\n    >>> AqSolDB = datasets.load_dataset(\"maomlab/AqSolDB\", name = \"AqSolDB\")\n    Downloading readme: 100%|████████████████████| 10.2k/10.2k [00:00<00:00, 4.41MB/s]\n    Downloading data: 100%|█████████████████████████| 972k/972k [00:02<00:00, 432kB/s]\n    Downloading data: 100%|█████�","encoding":"utf8","key":"README.md","name":"README.md","size":8826,"truncated":true}],"sourceObjectKey":"AqSolDB/test.csv","starterCell":"import pandas as pd\ndf = pd.read_csv(\"hf://datasets/maomlab/AqSolDB/AqSolDB/test.csv\")\ndf.head()","starterSamplePath":"AqSolDB/test.csv","totalObjects":4},"summary":"AqSolDB is a curated reference set of experimental aqueous solubility values for 9,982 unique compounds, merged from nine publicly available solubility datasets by the Autonomous…","title":"AqSolDB: Curated Aqueous Solubility (logS) of 9,982 Unique Compounds from Nine Public Datasets","updatedAt":"2026-11-22T04:00:56.687Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/maomlab/AqSolDB"}}