ERGFingerprint#

class skfp.fingerprints.ERGFingerprint(fuzz_increment: float = 0.3, min_path: int = 1, max_path: int = 15, variant: str = 'fuzzy', sparse: bool = False, n_jobs: int | None = None, batch_size: int | None = None, verbose: int = 0)#

Extended-Reduced Graph (ERG) fingerprint.

The implementation uses RDKit. This fingerprint is descriptor-based, but has variable length, depending on distance parameters. Originally described in [1].

This fingerprint can be seen as a hybrid of reduced graphs [2] and binding property (BP) pairs [3]. It uses fuzzy incrementation instead of counts.

First, input molecule is converted into a “reduced graph”, condensing pharmacophorically relevant information. On that graph, property points (PP) are identified. From those nodes, triplets (PP 1, topological distance, PP 2) are formed, using the shortest path distances on the reduced graph. They are not hashed, in contrast to Atom Pair approach, but rather all such triplets with distances between min_distance and max_distance are considered. For each triplet occurrence, its bit is incremented by 1 (resulting in triplet counts), and additionally, the fields for closest distances, i.e. dist-1 and dist+1, are also incremented by fuzz_increment (hence the fuzziness).

Six features are used for both computing the reduced graph and identifying property points, using SMARTS patterns definitions from [4]: - hydrogen bond donors - hydrogen bond acceptors - aromatic ring systems - hydrophobic (aliphatic) ring systems - positive formal atom charges - negative formal atom charges

Because we always use 6 features, the resulting fingerprints have length 21 * (max_distance - min_distance + 1).

Note that RDKit does not implement two features from the original paper, flip-flop flags (for donors and acceptors), and collapsing highly fused rings.

Parameters:

  • fuzz_increment (float, default=0.3) – How much to increment triplets occurrences and their closest neighboring fields by when they are detected. Controls how much weight is put on the similarity of pharmacophoric patterns. Default value of 0.3 was optimized for scaffold-hopping applications, but lower values around 0.1-0.2 can be considered for more “crisp” similarity.

  • min_path (int, default=1) – Minimal shortest path length to consider for calculating triplets on the reduced graph.

  • max_path (int, default=15) – Maximal shortest path length to consider for calculating triplets on the reduced graph.

  • variant ({"fuzzy", "bit", "count"}, default="fuzzy") – Fingerprint variant. Default “fuzzy” follows the original paper and results in floating point results. “bit” and “count” result in integer vectors for “crisp” calculation on the original graph, and they use zero fuzziness, ignoring the fuzz_incremement parameter.

  • 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, size of fingerprints. Equal to 21 * (max_path - min_path), 315 for default parameters.

Type:

int

requires_conformers#

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

Type:

bool = False

See also

TopologicalTorsionFingerprint

Related fingerprint, but uses 4-atom paths.

References

Examples

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

>>> fp.transform(smiles)
array([[0., 0., 0., ..., 0., 0., 0.],
       [0., 0., 0., ..., 0., 0., 0.],
       [0., 0., 0., ..., 0., 0., 0.],
       [0., 0., 0., ..., 0., 0., 0.]])

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 = '$UNCHANGED$') → ERGFingerprint#

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