Chemistry

Chemistry and cheminformatics-oriented data cleaning functions.

maccs_keys_fingerprint(df, mols_column_name)

Convert a column of RDKIT mol objects into MACCS Keys Fingerprints.

Returns a new dataframe without any of the original data. This is intentional to leave the user with the data requested.

This method does not mutate the original DataFrame.

Examples:

Functional usage

>>> import pandas as pd
>>> import janitor.chemistry
>>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})
>>> maccs = janitor.chemistry.maccs_keys_fingerprint(
...     df=df.smiles2mol('smiles', 'mols'),
...     mols_column_name='mols'
... )
>>> len(maccs.columns)
167

Method chaining usage

>>> import pandas as pd
>>> import janitor.chemistry
>>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})
>>> maccs = (
...     df.smiles2mol('smiles', 'mols')
...         .maccs_keys_fingerprint(mols_column_name='mols')
... )
>>> len(maccs.columns)
167

If you wish to join the maccs keys fingerprints back into the original dataframe, this can be accomplished by doing a join, because the indices are preserved:

>>> joined = df.join(maccs)
>>> len(joined.columns)
169

Parameters:

Name	Type	Description	Default
df	DataFrame	A pandas DataFrame.	required
mols_column_name	Hashable	The name of the column that has the RDKIT mol objects.	required

Returns:

Type	Description
DataFrame	A new pandas DataFrame of MACCS keys fingerprints.

Source code in janitor/chemistry.py

@pf.register_dataframe_method
@deprecated_alias(mols_col="mols_column_name")
def maccs_keys_fingerprint(
    df: pd.DataFrame, mols_column_name: Hashable
) -> pd.DataFrame:
    """Convert a column of RDKIT mol objects into MACCS Keys Fingerprints.

    Returns a new dataframe without any of the original data.
    This is intentional to leave the user with the data requested.

    This method does not mutate the original DataFrame.

    Examples:
        Functional usage

        >>> import pandas as pd
        >>> import janitor.chemistry
        >>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})
        >>> maccs = janitor.chemistry.maccs_keys_fingerprint(
        ...     df=df.smiles2mol('smiles', 'mols'),
        ...     mols_column_name='mols'
        ... )
        >>> len(maccs.columns)
        167

        Method chaining usage

        >>> import pandas as pd
        >>> import janitor.chemistry
        >>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})
        >>> maccs = (
        ...     df.smiles2mol('smiles', 'mols')
        ...         .maccs_keys_fingerprint(mols_column_name='mols')
        ... )
        >>> len(maccs.columns)
        167

        If you wish to join the maccs keys fingerprints back into the
        original dataframe, this can be accomplished by doing a `join`,
        because the indices are preserved:

        >>> joined = df.join(maccs)
        >>> len(joined.columns)
        169

    Args:
        df: A pandas DataFrame.
        mols_column_name: The name of the column that has the RDKIT mol
            objects.

    Returns:
        A new pandas DataFrame of MACCS keys fingerprints.
    """

    maccs = [GetMACCSKeysFingerprint(m) for m in df[mols_column_name]]

    np_maccs = []

    for macc in maccs:
        arr = np.zeros((1,))
        DataStructs.ConvertToNumpyArray(macc, arr)
        np_maccs.append(arr)
    np_maccs = np.vstack(np_maccs)
    fmaccs = pd.DataFrame(np_maccs)
    fmaccs.index = df.index
    return fmaccs

molecular_descriptors(df, mols_column_name)

Convert a column of RDKIT mol objects into a Pandas DataFrame of molecular descriptors.

Returns a new dataframe without any of the original data. This is intentional to leave the user only with the data requested.

This method does not mutate the original DataFrame.

The molecular descriptors are from the rdkit.Chem.rdMolDescriptors:

Chi0n, Chi0v, Chi1n, Chi1v, Chi2n, Chi2v, Chi3n, Chi3v,
Chi4n, Chi4v, ExactMolWt, FractionCSP3, HallKierAlpha, Kappa1,
Kappa2, Kappa3, LabuteASA, NumAliphaticCarbocycles,
NumAliphaticHeterocycles, NumAliphaticRings, NumAmideBonds,
NumAromaticCarbocycles, NumAromaticHeterocycles, NumAromaticRings,
NumAtomStereoCenters, NumBridgeheadAtoms, NumHBA, NumHBD,
NumHeteroatoms, NumHeterocycles, NumLipinskiHBA, NumLipinskiHBD,
NumRings, NumSaturatedCarbocycles, NumSaturatedHeterocycles,
NumSaturatedRings, NumSpiroAtoms, NumUnspecifiedAtomStereoCenters,
TPSA.

Examples:

Functional usage

>>> import pandas as pd
>>> import janitor.chemistry
>>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})
>>> mol_desc = (
...     janitor.chemistry.molecular_descriptors(
...         df=df.smiles2mol('smiles', 'mols'),
...         mols_column_name='mols'
...     )
... )
>>> mol_desc.TPSA
0    34.14
1    37.30
Name: TPSA, dtype: float64

Method chaining usage

>>> import pandas as pd
>>> import janitor.chemistry
>>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})
>>> mol_desc = (
...     df.smiles2mol('smiles', 'mols')
...     .molecular_descriptors(mols_column_name='mols')
... )
>>> mol_desc.TPSA
0    34.14
1    37.30
Name: TPSA, dtype: float64

If you wish to join the molecular descriptors back into the original dataframe, this can be accomplished by doing a join, because the indices are preserved:

>>> joined = df.join(mol_desc)
>>> len(joined.columns)
41

Parameters:

Name	Type	Description	Default
df	DataFrame	A pandas DataFrame.	required
mols_column_name	Hashable	The name of the column that has the RDKIT mol objects.	required

Returns:

Type	Description
DataFrame	A new pandas DataFrame of molecular descriptors.

Source code in janitor/chemistry.py

@pf.register_dataframe_method
@deprecated_alias(mols_col="mols_column_name")
def molecular_descriptors(
    df: pd.DataFrame, mols_column_name: Hashable
) -> pd.DataFrame:
    """Convert a column of RDKIT mol objects into a Pandas DataFrame
    of molecular descriptors.

    Returns a new dataframe without any of the original data. This is
    intentional to leave the user only with the data requested.

    This method does not mutate the original DataFrame.

    The molecular descriptors are from the `rdkit.Chem.rdMolDescriptors`:

    ```text
    Chi0n, Chi0v, Chi1n, Chi1v, Chi2n, Chi2v, Chi3n, Chi3v,
    Chi4n, Chi4v, ExactMolWt, FractionCSP3, HallKierAlpha, Kappa1,
    Kappa2, Kappa3, LabuteASA, NumAliphaticCarbocycles,
    NumAliphaticHeterocycles, NumAliphaticRings, NumAmideBonds,
    NumAromaticCarbocycles, NumAromaticHeterocycles, NumAromaticRings,
    NumAtomStereoCenters, NumBridgeheadAtoms, NumHBA, NumHBD,
    NumHeteroatoms, NumHeterocycles, NumLipinskiHBA, NumLipinskiHBD,
    NumRings, NumSaturatedCarbocycles, NumSaturatedHeterocycles,
    NumSaturatedRings, NumSpiroAtoms, NumUnspecifiedAtomStereoCenters,
    TPSA.
    ```

    Examples:
        Functional usage

        >>> import pandas as pd
        >>> import janitor.chemistry
        >>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})
        >>> mol_desc = (
        ...     janitor.chemistry.molecular_descriptors(
        ...         df=df.smiles2mol('smiles', 'mols'),
        ...         mols_column_name='mols'
        ...     )
        ... )
        >>> mol_desc.TPSA
        0    34.14
        1    37.30
        Name: TPSA, dtype: float64

        Method chaining usage

        >>> import pandas as pd
        >>> import janitor.chemistry
        >>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})
        >>> mol_desc = (
        ...     df.smiles2mol('smiles', 'mols')
        ...     .molecular_descriptors(mols_column_name='mols')
        ... )
        >>> mol_desc.TPSA
        0    34.14
        1    37.30
        Name: TPSA, dtype: float64

        If you wish to join the molecular descriptors back into the original
        dataframe, this can be accomplished by doing a `join`,
        because the indices are preserved:

        >>> joined = df.join(mol_desc)
        >>> len(joined.columns)
        41

    Args:
        df: A pandas DataFrame.
        mols_column_name: The name of the column that has the RDKIT mol
            objects.

    Returns:
        A new pandas DataFrame of molecular descriptors.
    """
    descriptors = [
        CalcChi0n,
        CalcChi0v,
        CalcChi1n,
        CalcChi1v,
        CalcChi2n,
        CalcChi2v,
        CalcChi3n,
        CalcChi3v,
        CalcChi4n,
        CalcChi4v,
        CalcExactMolWt,
        CalcFractionCSP3,
        CalcHallKierAlpha,
        CalcKappa1,
        CalcKappa2,
        CalcKappa3,
        CalcLabuteASA,
        CalcNumAliphaticCarbocycles,
        CalcNumAliphaticHeterocycles,
        CalcNumAliphaticRings,
        CalcNumAmideBonds,
        CalcNumAromaticCarbocycles,
        CalcNumAromaticHeterocycles,
        CalcNumAromaticRings,
        CalcNumAtomStereoCenters,
        CalcNumBridgeheadAtoms,
        CalcNumHBA,
        CalcNumHBD,
        CalcNumHeteroatoms,
        CalcNumHeterocycles,
        CalcNumLipinskiHBA,
        CalcNumLipinskiHBD,
        CalcNumRings,
        CalcNumSaturatedCarbocycles,
        CalcNumSaturatedHeterocycles,
        CalcNumSaturatedRings,
        CalcNumSpiroAtoms,
        CalcNumUnspecifiedAtomStereoCenters,
        CalcTPSA,
    ]
    descriptors_mapping = {f.__name__.strip("Calc"): f for f in descriptors}

    feats = dict()
    for name, func in descriptors_mapping.items():
        feats[name] = [func(m) for m in df[mols_column_name]]
    return pd.DataFrame(feats)

morgan_fingerprint(df, mols_column_name, radius=3, nbits=2048, kind='counts')

Convert a column of RDKIT Mol objects into Morgan Fingerprints.

Returns a new dataframe without any of the original data. This is intentional, as Morgan fingerprints are usually high-dimensional features.

This method does not mutate the original DataFrame.

Examples:

Functional usage

>>> import pandas as pd
>>> import janitor.chemistry
>>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})

• For "counts" kind

>>> morgans = janitor.chemistry.morgan_fingerprint(
...     df=df.smiles2mol('smiles', 'mols'),
...     mols_column_name='mols',
...     radius=3,      # Defaults to 3
...     nbits=2048,    # Defaults to 2048
...     kind='counts'  # Defaults to "counts"
... )
>>> set(morgans.iloc[0])
{0.0, 1.0, 2.0}

• For "bits" kind

>>> morgans = janitor.chemistry.morgan_fingerprint(
...     df=df.smiles2mol('smiles', 'mols'),
...     mols_column_name='mols',
...     radius=3,      # Defaults to 3
...     nbits=2048,    # Defaults to 2048
...     kind='bits'    # Defaults to "counts"
...  )
>>> set(morgans.iloc[0])
{0.0, 1.0}

Method chaining usage

>>> import pandas as pd
>>> import janitor.chemistry
>>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})

• For "counts" kind

>>> morgans = (
...     df.smiles2mol('smiles', 'mols')
...     .morgan_fingerprint(
...         mols_column_name='mols',
...         radius=3,      # Defaults to 3
...         nbits=2048,    # Defaults to 2048
...         kind='counts'  # Defaults to "counts"
...     )
... )
>>> set(morgans.iloc[0])
{0.0, 1.0, 2.0}

• For "bits" kind

>>> morgans = (
...     df
...     .smiles2mol('smiles', 'mols')
...     .morgan_fingerprint(
...         mols_column_name='mols',
...         radius=3,    # Defaults to 3
...         nbits=2048,  # Defaults to 2048
...         kind='bits'  # Defaults to "counts"
...     )
... )
>>> set(morgans.iloc[0])
{0.0, 1.0}

If you wish to join the morgan fingerprints back into the original dataframe, this can be accomplished by doing a join, because the indices are preserved:

>>> joined = df.join(morgans)
>>> len(joined.columns)
2050

Parameters:

Name	Type	Description	Default
df	DataFrame	A pandas DataFrame.	required
mols_column_name	str	The name of the column that has the RDKIT mol objects	required
radius	int	Radius of Morgan fingerprints.	3
nbits	int	The length of the fingerprints.	2048
kind	Literal['counts', 'bits']	Whether to return counts or bits.	'counts'

Raises:

Type	Description
ValueError	If kind is not one of "counts" or "bits".

Returns:

Type	Description
DataFrame	A new pandas DataFrame of Morgan fingerprints.

Source code in janitor/chemistry.py

@pf.register_dataframe_method
@deprecated_alias(mols_col="mols_column_name")
def morgan_fingerprint(
    df: pd.DataFrame,
    mols_column_name: str,
    radius: int = 3,
    nbits: int = 2048,
    kind: Literal["counts", "bits"] = "counts",
) -> pd.DataFrame:
    """Convert a column of RDKIT Mol objects into Morgan Fingerprints.

    Returns a new dataframe without any of the original data. This is
    intentional, as Morgan fingerprints are usually high-dimensional
    features.

    This method does not mutate the original DataFrame.

    Examples:
        Functional usage

        >>> import pandas as pd
        >>> import janitor.chemistry
        >>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})

        - For "counts" kind

        >>> morgans = janitor.chemistry.morgan_fingerprint(
        ...     df=df.smiles2mol('smiles', 'mols'),
        ...     mols_column_name='mols',
        ...     radius=3,      # Defaults to 3
        ...     nbits=2048,    # Defaults to 2048
        ...     kind='counts'  # Defaults to "counts"
        ... )
        >>> set(morgans.iloc[0])
        {0.0, 1.0, 2.0}

        - For "bits" kind

        >>> morgans = janitor.chemistry.morgan_fingerprint(
        ...     df=df.smiles2mol('smiles', 'mols'),
        ...     mols_column_name='mols',
        ...     radius=3,      # Defaults to 3
        ...     nbits=2048,    # Defaults to 2048
        ...     kind='bits'    # Defaults to "counts"
        ...  )
        >>> set(morgans.iloc[0])
        {0.0, 1.0}

        Method chaining usage

        >>> import pandas as pd
        >>> import janitor.chemistry
        >>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})

        - For "counts" kind

        >>> morgans = (
        ...     df.smiles2mol('smiles', 'mols')
        ...     .morgan_fingerprint(
        ...         mols_column_name='mols',
        ...         radius=3,      # Defaults to 3
        ...         nbits=2048,    # Defaults to 2048
        ...         kind='counts'  # Defaults to "counts"
        ...     )
        ... )
        >>> set(morgans.iloc[0])
        {0.0, 1.0, 2.0}

        - For "bits" kind

        >>> morgans = (
        ...     df
        ...     .smiles2mol('smiles', 'mols')
        ...     .morgan_fingerprint(
        ...         mols_column_name='mols',
        ...         radius=3,    # Defaults to 3
        ...         nbits=2048,  # Defaults to 2048
        ...         kind='bits'  # Defaults to "counts"
        ...     )
        ... )
        >>> set(morgans.iloc[0])
        {0.0, 1.0}

        If you wish to join the morgan fingerprints back into the original
        dataframe, this can be accomplished by doing a `join`,
        because the indices are preserved:

        >>> joined = df.join(morgans)
        >>> len(joined.columns)
        2050

    Args:
        df: A pandas DataFrame.
        mols_column_name: The name of the column that has the RDKIT
            mol objects
        radius: Radius of Morgan fingerprints.
        nbits: The length of the fingerprints.
        kind: Whether to return counts or bits.

    Raises:
        ValueError: If `kind` is not one of `"counts"` or `"bits"`.

    Returns:
        A new pandas DataFrame of Morgan fingerprints.
    """
    acceptable_kinds = ["counts", "bits"]
    if kind not in acceptable_kinds:
        raise ValueError(f"`kind` must be one of {acceptable_kinds}")

    if kind == "bits":
        fps = [
            GetMorganFingerprintAsBitVect(m, radius, nbits, useChirality=True)
            for m in df[mols_column_name]
        ]
    elif kind == "counts":
        fps = [
            GetHashedMorganFingerprint(m, radius, nbits, useChirality=True)
            for m in df[mols_column_name]
        ]

    np_fps = []
    for fp in fps:
        arr = np.zeros((1,))
        DataStructs.ConvertToNumpyArray(fp, arr)
        np_fps.append(arr)
    np_fps = np.vstack(np_fps)
    fpdf = pd.DataFrame(np_fps)
    fpdf.index = df.index
    return fpdf

smiles2mol(df, smiles_column_name, mols_column_name, drop_nulls=True, progressbar=None)

Convert a column of SMILES strings into RDKit Mol objects.

Automatically drops invalid SMILES, as determined by RDKIT.

This method mutates the original DataFrame.

Examples:

Functional usage

>>> import pandas as pd
>>> import janitor.chemistry
>>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})
>>> df = janitor.chemistry.smiles2mol(
...    df=df,
...    smiles_column_name='smiles',
...    mols_column_name='mols'
... )
>>> df.mols[0].GetNumAtoms(), df.mols[0].GetNumBonds()
(3, 2)
>>> df.mols[1].GetNumAtoms(), df.mols[1].GetNumBonds()
(5, 4)

Method chaining usage

>>> import pandas as pd
>>> import janitor.chemistry
>>> df = df.smiles2mol(
...     smiles_column_name='smiles',
...     mols_column_name='rdkmol'
... )
>>> df.rdkmol[0].GetNumAtoms(), df.rdkmol[0].GetNumBonds()
(3, 2)

A progressbar can be optionally used.

• Pass in "notebook" to show a tqdm notebook progressbar. (ipywidgets must be enabled with your Jupyter installation.)
• Pass in "terminal" to show a tqdm progressbar. Better suited for use with scripts.
• None is the default value - progress bar will not be shown.

Parameters:

Name	Type	Description	Default
df	DataFrame	pandas DataFrame.	required
smiles_column_name	Hashable	Name of column that holds the SMILES strings.	required
mols_column_name	Hashable	Name to be given to the new mols column.	required
drop_nulls	bool	Whether to drop rows whose mols failed to be constructed.	True
progressbar	Optional[str]	Whether to show a progressbar or not.	None

Raises:

Type	Description
ValueError	If progressbar is not one of "notebook", "terminal", or None.

Returns:

Type	Description
DataFrame	A pandas DataFrame with new RDKIT Mol objects column.

Source code in janitor/chemistry.py

@pf.register_dataframe_method
@deprecated_alias(smiles_col="smiles_column_name", mols_col="mols_column_name")
def smiles2mol(
    df: pd.DataFrame,
    smiles_column_name: Hashable,
    mols_column_name: Hashable,
    drop_nulls: bool = True,
    progressbar: Optional[str] = None,
) -> pd.DataFrame:
    """Convert a column of SMILES strings into RDKit Mol objects.

    Automatically drops invalid SMILES, as determined by RDKIT.

    This method mutates the original DataFrame.

    Examples:
        Functional usage

        >>> import pandas as pd
        >>> import janitor.chemistry
        >>> df = pd.DataFrame({"smiles": ["O=C=O", "CCC(=O)O"]})
        >>> df = janitor.chemistry.smiles2mol(
        ...    df=df,
        ...    smiles_column_name='smiles',
        ...    mols_column_name='mols'
        ... )
        >>> df.mols[0].GetNumAtoms(), df.mols[0].GetNumBonds()
        (3, 2)
        >>> df.mols[1].GetNumAtoms(), df.mols[1].GetNumBonds()
        (5, 4)

        Method chaining usage

        >>> import pandas as pd
        >>> import janitor.chemistry
        >>> df = df.smiles2mol(
        ...     smiles_column_name='smiles',
        ...     mols_column_name='rdkmol'
        ... )
        >>> df.rdkmol[0].GetNumAtoms(), df.rdkmol[0].GetNumBonds()
        (3, 2)

    A progressbar can be optionally used.

    - Pass in "notebook" to show a `tqdm` notebook progressbar.
      (`ipywidgets` must be enabled with your Jupyter installation.)
    - Pass in "terminal" to show a `tqdm` progressbar. Better suited for use
      with scripts.
    - `None` is the default value - progress bar will not be shown.

    Args:
        df: pandas DataFrame.
        smiles_column_name: Name of column that holds the SMILES strings.
        mols_column_name: Name to be given to the new mols column.
        drop_nulls: Whether to drop rows whose mols failed to be
            constructed.
        progressbar: Whether to show a progressbar or not.

    Raises:
        ValueError: If `progressbar` is not one of
            `"notebook"`, `"terminal"`, or `None`.

    Returns:
        A pandas DataFrame with new RDKIT Mol objects column.
    """
    valid_progress = ["notebook", "terminal", None]
    if progressbar not in valid_progress:
        raise ValueError(f"progressbar kwarg must be one of {valid_progress}")

    if progressbar is None:
        df[mols_column_name] = df[smiles_column_name].apply(
            lambda x: Chem.MolFromSmiles(x)
        )
    else:
        if progressbar == "notebook":
            tqdmn().pandas(desc="mols")
        elif progressbar == "terminal":
            tqdm.pandas(desc="mols")
        df[mols_column_name] = df[smiles_column_name].progress_apply(
            lambda x: Chem.MolFromSmiles(x)
        )

    if drop_nulls:
        df = df.dropna(subset=[mols_column_name])
    df = df.reset_index(drop=True)
    return df