USRFingerprint

class skfp.fingerprints.USRFingerprint(errors: str = 'raise', n_jobs: int | None = None, batch_size: int | None = None, verbose: int = 0)

USR (Ultrafast Shape Recognition) fingerprint.

The implementation uses RDKit. This is a descriptor-based fingerprint, which characterizes the shape of the molecule by encoding the relative positions of its atoms [1] [2].

Four points are considered: molecular centroid (ctd), the closest atom to centroid (cst), the farthest atom from centroid (fct), and atom the fartest from fct (ftf). Distances from all atoms to each of those four points are computed, and each of those distributions is summarized its first three moments: mean, variance, and skewness. Concretely, standard deviation and cubic root of skewness are used to keep the same unit. This results in 12 descriptors.

This is a 3D fingerprint, and requries molecules with conf_id integer property set. They can be generated with ConformerGenerator. Furthermore, only molecules with 3 or more atoms are allowed, to allow computation of all three moments.

Parameters:

• errors ({"raise", "NaN", "ignore"}, default="raise") – How to handle errors during fingerprint calculation. "raise" immediately raises any errors. "NaN" returns NaN values for molecules which resulted in errors. "ignore" suppresses errors and does not return anything for molecules with errors. This potentially results in less output vectors than input molecules, and should be used with caution.

• n_jobs (int, default=None) – The number of jobs to run in parallel. transform() is 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, default=0) – Controls the verbosity when computing fingerprints.

n_features_out

Number of output features, size of fingerprints.

Type:

int = 12

requires_conformers

Value is always True, as this fingerprint is 3D based. It always requires molecules with conformers as inputs, with conf_id integer property set.

Type:

bool = True

See also

USRCAT

Related fingerprint, which additionally uses pharmacophoric atom types.

References

[1]

Pedro J. Ballester and W. Graham Richards “Ultrafast shape recognition for similarity search in molecular databases” Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences 463.2081 (2007): 1307-1321

[2]

Pedro J. Ballester “Ultrafast shape recognition: method and applications” Future Medicinal Chemistry 3.1 (2011): 65-78

Examples

>>> from skfp.fingerprints import USRFingerprint
>>> from skfp.preprocessing import MolFromSmilesTransformer, ConformerGenerator
>>> smiles = ["CC=O"]
>>> fp = USRFingerprint()
>>> fp
USRFingerprint()

>>> mol_from_smiles = MolFromSmilesTransformer()
>>> mols = mol_from_smiles.transform(smiles)
>>> conf_gen = ConformerGenerator()
>>> mols = conf_gen.transform(mols)
>>> fp.transform(mols)  
array([[ 1.33723405,  0.39526642, ...        ,  0.94315243, -0.78539494]])

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 output feature names for transformation.
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])	Request metadata passed to the transform method.
transform(X[, copy])	Compute USR fingerprints.
transform_x_y(X, y[, copy])	Compute USR fingerprints.

fit(X, y=None, **fit_params)

Unused, kept for Scikit-learn compatibility.

Parameters:

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

• Y (any) – Unused, kept for Scikit-learn compatibility.

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

Return type:

self

fit_transform(X, y=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)

Get output feature names for transformation.

The feature names out will prefixed by the lowercased class name. For example, if the transformer outputs 3 features, then the feature names out are: [“class_name0”, “class_name1”, “class_name2”].

Parameters:

input_features (array-like of str or None, default=None) – Only used to validate feature names with the names seen in fit.

Returns:

feature_names_out – Transformed feature 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 = '$UNCHANGED$') → USRFingerprint

Request metadata passed to the transform method.

Note that this method is only relevant if enable_metadata_routing=True (see sklearn.set_config()). Please see 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.

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a Pipeline. Otherwise it has no effect.

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) → ndarray | csr_array

Compute USR fingerprints. If errors is set to "ignore", then in case of errors less than n_samples values may be returned.

Parameters:

• X ({sequence, array-like} of shape (n_samples,)) – Sequence containing RDKit Mol objects, with conformers generated and conf_id integer property set.

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

Returns:

X – Array with fingerprints.

Return type:

{ndarray, sparse matrix} of shape (n_samples, self.fp_size)

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

Compute USR fingerprints. If errors is set to "ignore", then in case of errors less than n_samples values may be returned. The returned values for X and y are properly synchronized.

Parameters:

• X ({sequence, array-like} of shape (n_samples,)) – Sequence containing RDKit Mol objects, with conformers generated and conf_id integer property set.

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

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

Returns:

• X ({ndarray, sparse matrix} of shape (n_samples, self.fp_size)) – Array with fingerprints.

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