Skip to content

datamol.data

The data module aims to provide a fast and convenient access to various molecular datasets.

cdk2(as_df=True, mol_column='mol')

Return the RDKit CDK2 dataset from RDConfig.RDDocsDir, 'Book/data/cdk2.sdf'.

Parameters:

Name Type Description Default
as_df bool

Whether to return a list mol or a pandas DataFrame.

 True
mol_column Optional[str]

Name of the mol column. Only relevant if as_df is True.

 'mol'
Source code in datamol/data.py 
36
37
38
39
40
41
42
43
44
45
46
def cdk2(as_df: bool = True, mol_column: Optional[str] = "mol"):
    """Return the RDKit CDK2 dataset from `RDConfig.RDDocsDir, 'Book/data/cdk2.sdf'`.

    Args:
        as_df: Whether to return a list mol or a pandas DataFrame.
        mol_column: Name of the mol column. Only relevant if `as_df` is True.
    """

    with pkg_resources.resource_stream("datamol", "data/cdk2.sdf") as f:
        data = read_sdf(f, as_df=as_df, mol_column=mol_column)
    return data

freesolv()

Return the FreeSolv dataset as a dataframe.

The dataset contains 642 molecules and the following columns: ['iupac', 'smiles', 'expt', 'calc'].

Warning

This dataset is only meant to be used as a toy dataset for pedagogic and testing purposes. It is not a dataset for benchmarking, analysis or model training.

Source code in datamol/data.py 
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
def freesolv():
    """Return the FreeSolv dataset as a dataframe.

    The dataset contains 642 molecules and the following columns:
    `['iupac', 'smiles', 'expt', 'calc']`.

    Warning:
        This dataset is only meant to be used as a toy dataset for pedagogic and
        testing purposes. **It is not** a dataset for benchmarking, analysis or
        model training.
    """

    with pkg_resources.resource_stream("datamol", "data/freesolv.csv") as f:
        data = pd.read_csv(f)
    return data

solubility(as_df=True, mol_column='mol')

Return the RDKit solubility dataset from RDConfig.RDDocsDir, 'Book/data/solubility.{train|test}.sdf'.

The dataframe or the list of molecules with contain a split column, either train or test.

Parameters:

Name Type Description Default
as_df bool

Whether to return a list mol or a pandas DataFrame.

 True
mol_column Optional[str]

Name of the mol column. Only relevant if as_df is True.

 'mol'
Source code in datamol/data.py 
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
def solubility(as_df: bool = True, mol_column: Optional[str] = "mol"):
    """Return the RDKit solubility dataset from `RDConfig.RDDocsDir, 'Book/data/solubility.{train|test}.sdf'`.

    The dataframe or the list of molecules with contain a `split` column, either `train` or `test`.

    Args:
        as_df: Whether to return a list mol or a pandas DataFrame.
        mol_column: Name of the mol column. Only relevant if `as_df` is True.
    """

    with pkg_resources.resource_stream("datamol", "data/solubility.train.sdf") as f:
        train = read_sdf(f, as_df=True, mol_column="mol", smiles_column=None)

    with pkg_resources.resource_stream("datamol", "data/solubility.test.sdf") as f:
        test = read_sdf(f, as_df=True, mol_column="mol", smiles_column=None)

    train = cast(pd.DataFrame, train)
    test = cast(pd.DataFrame, test)

    train["split"] = "train"
    test["split"] = "test"

    # NOTE(hadim): LMAO RDkit consistency xD
    test = test.rename(columns={"SMILES": "smiles"})

    data = pd.concat([train, test], ignore_index=True)

    if as_df:
        if mol_column is None:
            data = data.drop(columns=["mol"])

        render_mol_df(data)
        return data

    return from_df(data, mol_column=mol_column)