BaseFilter#

class skfp.bases.BaseFilter(condition_names: list[str], allow_one_violation: bool = False, return_type: str = 'mol', n_jobs: int | None = None, batch_size: int | None = None, verbose: int | dict = 0)#

Base class for molecular filters.

Filters take a list of molecules and check which ones fulfill the conditions specified. It can be used to create both common types of filters:

  • “pass” filters, where molecules have to fit into a given range of properties, e.g. Lipinski Rule of 5

  • “reject” filters, where molecules cannot contain certain properties like toxic functional groups, e.g. PAINS filters

This class is not meant to be used directly. If you want to create custom filters, inherit from this class and override the ._apply_mol_filter() method. It gets a single molecule and outputs a boolean, whether it passes the filter or not. Note that for “reject” filters it should return True if molecule should be kept, i.e. does not contain any undesirable property.

Parameters:

  • condition_names (list[str]) – Names of filter conditions, e.g. physicochemical properties and their limits, or SMARTS patterns.

  • allow_one_violation (bool, default=False) – Whether to allow violating one of the rules for a molecule. This makes the filter less restrictive.

  • return_type ({"mol", "indicators", "condition_indicators"}, default="mol") –

    What values to return as the filtering result.

    • "mol" - return a list of molecules remaining in the dataset after filtering

    • "indicators" - return a binary vector with indicators which molecules pass the filter (1) and which would be removed (0)

    • "condition_indicators" - return a Pandas DataFrame with molecules in rows, filter conditions in columns, and 0/1 indicators whether a given condition was fulfilled by a given molecule

  • n_jobs (int, default=None) – The number of jobs to run in parallel. transform_x_y() and transform() are parallelized over the input molecules. None means 1 unless in a joblib.parallel_backend context. -1 means using all processors. See scikit-learn documentation on n_jobs for more details.

  • batch_size (int, default=None) – Number of inputs processed in each batch. None divides input data into equal-sized parts, as many as n_jobs.

  • verbose (int or dict, default=0) – Controls the verbosity when filtering molecules. If a dictionary is passed, it is treated as kwargs for tqdm(), and can be used to control the progress bar.

Methods

fit(X[, y])

Unused, kept for scikit-learn compatibility.

fit_transform(X[, y])

The same as .transform() method, kept for scikit-learn compatibility.

get_feature_names_out([input_features])

Get filter condition names.

get_metadata_routing()

Get metadata routing of this object.

get_params([deep])

Get parameters for this estimator.

set_output(*[, transform])

Set output container.

set_params(**params)

Set the parameters of this estimator.

set_transform_request(*[, copy])

Configure whether metadata should be requested to be passed to the transform method.

transform(X[, copy])

Apply a filter to input molecules.

transform_x_y(X, y[, copy])

Apply a filter to input molecules.
fit(X: Sequence[str | Mol], y: ndarray | None = None)#

Unused, kept for scikit-learn compatibility.

Parameters:

  • X (any) – Unused, kept for scikit-learn compatibility.

  • y (any) – Unused, kept for scikit-learn compatibility.

Return type:

self

fit_transform(X: Sequence[str | Mol], y: ndarray | None = None, **fit_params)#

The same as .transform() method, kept for scikit-learn compatibility.

Parameters:

  • X (any) – See .transform() method.

  • y (any) – See .transform() method.

  • **fit_params (dict) – Unused, kept for scikit-learn compatibility.

Returns:

X_new – See .transform() method.

Return type:

any

get_feature_names_out(input_features=None) → ndarray#

Get filter condition names. They correspond to molecular descriptors (for physicochemical filters) or SMARTS patterns (for substructural filters).

Parameters:

input_features (array-like of str or None, default=None) – Unused, kept for scikit-learn compatibility.

Returns:

feature_names_out – Filter condition names.

Return type:

ndarray of str objects

get_metadata_routing()#

Get metadata routing of this object.

Please check User Guide on how the routing mechanism works.

Returns:

routing – A MetadataRequest encapsulating routing information.

Return type:

MetadataRequest

get_params(deep=True)#

Get parameters for this estimator.

Parameters:

deep (bool, default=True) – If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns:

params – Parameter names mapped to their values.

Return type:

dict

set_output(*, transform=None)#

Set output container.

See Introducing the set_output API for an example on how to use the API.

Parameters:

transform ({"default", "pandas", "polars"}, default=None) –

Configure output of transform and fit_transform.

  • ”default”: Default output format of a transformer

  • ”pandas”: DataFrame output

  • ”polars”: Polars output

  • None: Transform configuration is unchanged

Added in version 1.4: “polars” option was added.

Returns:

self – Estimator instance.

Return type:

estimator instance

set_params(**params)#

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:

**params (dict) – Estimator parameters.

Returns:

self – Estimator instance.

Return type:

estimator instance

set_transform_request(*, copy: bool | None | str = '$UNCHANGED$') → BaseFilter#

Configure whether metadata should be requested to be passed to the transform method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to transform if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to transform.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

copy (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for copy parameter in transform.

Returns:

self – The updated object.

Return type:

object

transform(X: Sequence[str | Mol], copy: bool = False) → list[str | Mol] | ndarray#

Apply a filter to input molecules. Output depends on return_type attribute.

Parameters:

  • X ({sequence of str or Mol}) – Sequence containing SMILES strings or RDKit Mol objects.

  • copy (bool, default=False) – Copy the input X or not.

Returns:

X – or array of shape (n_samples, n_conditions) List with filtered molecules or indicators.

Return type:

list of shape (n_samples,) or array of shape (n_samples,)

transform_x_y(X: Sequence[str | Mol], y: ndarray, copy: bool = False) → tuple[list[str | Mol], ndarray] | tuple[ndarray, ndarray]#

Apply a filter to input molecules. Output depends on return_type attribute.

Parameters:

  • X ({sequence of str or Mol}) – Sequence containing SMILES strings or RDKit Mol objects.

  • y (array-like of shape (n_samples,)) – Array with labels for molecules.

  • copy (bool, default=False) – Copy the input X or not.

Returns:

  • X (list of shape (n_samples,) or array of shape (n_samples,)) – or array of shape (n_samples, n_conditions) List with filtered molecules or indicators.

  • y (np.ndarray of shape (n_samples,)) – Array with labels for molecules.