MHFPFingerprint

class skfp.fingerprints.MHFPFingerprint(fp_size: int = 2048, radius: int = 3, min_radius: int = 1, sssr_rings: bool = True, isomeric_smiles: bool = False, kekulize: bool = True, variant: str = 'bit', sparse: bool = False, n_jobs: int | None = None, batch_size: int | None = None, verbose: int = 0)

MinHashed FingerPrint (MHFP).

The implementation uses RDKit. This is a hashed fingerprint [1], where fragments are computed based on circular substructures around each atom.

Subgraphs are created around each atom with increasing radius, starting with just an atom itself. It is then transformed into a canonical SMILES and hashed into an integer. In each iteration, it is increased by another atom (one “hop” on the graph). The resulting hashes are MinHashed. Depending on variant argument, either those values are returned, or they are further folded (with modulo) into a vector of size fp_size.

Additionally, the SMILES strings of the symmetrized smallest set of smallest rings (SSSR) are included by default, to incorporate ring information for small radii.

Parameters:

• fp_size (int, default=2048) – Size of output vectors, i.e. number of bits for each fingerprint. Must be positive.

• radius (int, default=3) – Number of iterations performed, i.e. maximum radius of resulting subgraphs. Another common notation uses diameter, therefore ECFP4 has radius 2.

• min_radius (int, default=1) – Initial radius of subgraphs.

• sssr_rings (bool, default=True) – Whether to include the symmetrized smallest set of smallest rings (SSSR) in addition to circular subgraphs.

• isomeric_smiles (bool, default=False) – Whether to use isomeric SMILES, instead of just the canonical SMILES.

• kekulize (bool, default=True) – Whether to kekulize the subgraphs before SMILES generation.

• variant ({"bit", "count", "raw_hashes"}, default="bit") – Fingerprint variant. “raw_hashes” follows the original paper and results in raw integer values of hashes. “bit” and “count” result in integer vectors with hashes folded with modulo operation into a fp_size length.

• sparse (bool, default=False) – Whether to return dense NumPy array, or sparse SciPy CSR array.

• 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. Equal to fp_size.

Type:

int

requires_conformers

This fingerprint uses only 2D molecular graphs and does not require conformers.

Type:

bool = False

See also

ECFPFingerprint

Related fingerprint, which uses atom invariants instead of raw SMILES strings.

SECFPFingerprint

Related fingerprint, which hashes subgraph SMILES and folds the resulting vector.

References

[1]

Daniel Probst and Jean-Louis Reymond “A probabilistic molecular fingerprint for big data settings” Journal of Cheminformatics 10, 1-12 (2018)

Examples

>>> from skfp.fingerprints import MHFPFingerprint
>>> smiles = ["O", "CC", "[C-]#N", "CC=O"]
>>> fp = MHFPFingerprint()
>>> fp
MHFPFingerprint()

>>> fp.transform(smiles)
array([[0, 0, 0, ..., 0, 0, 1],
       [0, 1, 0, ..., 0, 0, 1],
       [1, 1, 0, ..., 1, 1, 0],
       [0, 0, 1, ..., 1, 0, 1]], dtype=uint8)

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])

fit(X: Sequence[str | Mol], y: Any | None = 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: Sequence[str | Mol], y: Any | 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)

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 = '$UNCHANGED$') → MHFPFingerprint

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