schrodinger.application.matsci.mlearn.features module¶

Classes and functions to deal with ML features.

class schrodinger.application.matsci.mlearn.features.MomentData(flag, components, header, units)¶

Bases: tuple

__contains__(key, /)¶: Return key in self.

__len__()¶: Return len(self).

components¶: Alias for field number 1

count(value, /)¶: Return number of occurrences of value.

flag¶: Alias for field number 0

header¶: Alias for field number 2

index(value, start=0, stop=9223372036854775807, /)¶

Return first index of value.

Raises ValueError if the value is not present.

units¶: Alias for field number 3

schrodinger.application.matsci.mlearn.features.DescriptorUtility¶: alias of schrodinger.application.matsci.mlearn.features.DescriptorUtilitity

schrodinger.application.matsci.mlearn.features.get_distance_cell(struct, cutoff)[source]¶

Create an infrastructure Distance Cell. Struct MUST have the Chorus box properties.

Parameters

struct (schrodinger.structure.Structure) – Input structure
cutoff (float) – The cutoff for finding nearest neighbor atoms

Return type

schrodinger.structure.Structure, , schrodinger.infra.structure.DistanceCell, schrodinger.infra.structure.PBC

Returns

Supercell, an infrastructure Distance Cell that accounts for the PBC, and the pbc used to create it.

Raise

ValueError if struct is missing PBCs

schrodinger.application.matsci.mlearn.features.elemental_generator(struct, element, is_equal=True)[source]¶

schrodinger.application.matsci.mlearn.features.get_anion(struct)[source]¶

Get the most electronegative element in the structure (anion).

Parameters: struct (schrodinger.structure.Structure) – Input structure
Return type: str, float, int
Returns: Element, it’s electronegativity, number of anions in the cell

class schrodinger.application.matsci.mlearn.features.LatticeFeatures(features, element='Li', cutoff=4.0)[source]¶

Bases: schrodinger.application.matsci.mlearn.base.BaseFeaturizer

Class to generate lattice-based features.

FEATURES = {'anionFrameCoordination': 'Anion frame coordination', 'avgAnionAnionShortDistance': 'Average anion anion shortest distance', 'avgAtomicVol': 'Average atomic volume', 'avgElementAnionShortDistance': 'Average cation anion shortest distance', 'avgElementNeighborCount': 'Average cation count', 'avgNeighborCount': 'Average neighbor count', 'avgNeighborIon': 'Average neighbor ionicity', 'avgShortDistance': 'Average cation cation shortest distance', 'avgSublatticeEneg': 'Average sublattice electronegativity', 'avgSublatticeNeighborCount': 'Average sublattice neighbor count', 'avgSublatticeNeighborIon': 'Average sublattice neighbor ionicity', 'packingFraction': 'Crystal packing fraction', 'pathWidth': 'Average straight-line path width', 'pathWidthEneg': 'Average straight-line path electronegativity', 'ratioCount': 'Ratio of average cation to sublattice count', 'ratioIonicity': 'Ratio of average cation to sublattice electronegativity', 'stdNeighborCount': 'Standard deviation of neighbor count', 'stdNeighborIon': 'Standard deviation of neighbor ionicity', 'sublatticePackingFraction': 'Sublattice packing fraction', 'volPerAnion': 'Volume per anion'}¶

__init__(features, element='Li', cutoff=4.0)[source]¶: Initialize the object.

runFeature(feature)[source]¶

Get result from a feature.

Param: feature: One of the features listed in FEATURES.
Return type: int or float
Returns: Feature value

transform(structs)[source]¶

Get numerical features from structures. Also sets features names in self.labels. See parent class for more documentation.

Parameters: structs (list(schrodinger.structure.Structure)) – List of structures to be featurized
Return type: numpy array of shape [n_samples, n_features]
Returns: Transformed array

avgAtomicVol()[source]¶

Get average atomic volume.

Parameters: struct (schrodinger.structure.Structure) – Structure to be used for feature calculation
Return type: float
Returns: Average atomic volume (A^3)

avgNeighborCount()[source]¶

Get average neighbor count.

Return type: float
Returns: Average neighbor count

stdNeighborCount()[source]¶

Get standard deviation of neighbor count.

Return type: float
Returns: Average neighbor count

avgSublatticeEneg()[source]¶

Get average sublattice electronegativity.

Return type: float
Returns: Average sublattice electronegativity

avgSublatticeNeighborCount()[source]¶

Get average sublattice neighbor count.

Return type: float
Returns: Average sublattice neighbor count

avgNeighborIon()[source]¶

Get average neighbor ionicity.

Return type: float
Returns: Average neighbor ionicity

stdNeighborIon()[source]¶

Get standard deviation of neighbor ionicity.

Return type: float
Returns: Average neighbor ionicity

avgSublatticeNeighborIon()[source]¶

Get average sublattice neighbor ionicity.

Return type: float
Returns: Average sublattice neighbor count

volPerAnion()[source]¶

Get volume per anion.

Return type: float
Returns: Volume per anion

packingFraction(skip_element=None)[source]¶

Get packing fraction of the crystal.

Parameters: skip_element (str) – Element to skip
Return type: float
Returns: Packing fraction

effectiveRadius(atom)[source]¶

Get atom effective radius.

Parameters: atom (schrodinger.structure._StructureAtom) – Atom
Return type: float
Returns: Effective radius

sublatticePackingFraction()[source]¶

Get packing fraction of the sublattice crystal.

Return type: float
Returns: Packing fraction

avgElementNeighborCount()[source]¶

Get average element neighbor count.

Return type: float
Returns: Average number of bonds per element

avgAnionAnionShortDistance()[source]¶

Get average anion anion shortest distance.

Return type: float
Returns: Average anion anion shortest distance

avgElementAnionShortDistance()[source]¶

Get average element anion shortest distance.

Return type: float
Returns: Average element anion shortest distance

avgShortDistance()[source]¶

Get average element element shortest distance.

Return type: float
Returns: Average element element shortest distance

anionFrameCoordination()[source]¶

Get anion framework coordination.

Return type: float
Returns: Anion framework coordination

pathWidth(eval_eneg=False)[source]¶

Evaluate average straight line path width. See the reference in the constructor for more info.

Parameters: eval_eneg (bool) – If True, return average over electronegativity, instead of distance
Return type: float
Returns: Average path or electronegativity

pathWidthEneg()[source]¶

Evaluate average straight line path electronegativity.

Return type: float
Returns: Average electronegativity along the path

ratioIonicity()[source]¶

Get ratio ionicity.

Return type: float
Returns: Ratio ionicity

ratioCount()[source]¶

Get ratio neighbor count.

Return type: float
Returns: Ratio neighbor count

fit(data, data_y=None)¶

Fit and return self. Anything that evaluates properties related to the passed data should go here. For example, compute physical properties of a stucture and save them as class property, to be used in the transform method.

Parameters

data (numpy array of shape [n_samples, n_features]) – Training set
data_y (numpy array of shape [n_samples]) – Target values

Return type

BaseFeaturizer

Returns

self object with fitted data

fit_transform(X, y=None, **fit_params)¶

Fit to data, then transform it.

Fits transformer to X and y with optional parameters fit_params and returns a transformed version of X.

X : {array-like, sparse matrix, dataframe} of shape (n_samples, n_features)

yndarray of shape (n_samples,), default=None: Target values.
**fit_paramsdict: Additional fit parameters.

X_newndarray array of shape (n_samples, n_features_new): Transformed array.

get_params(deep=True)¶

Get parameters for this estimator.

deepbool, default=True: If True, will return the parameters for this estimator and contained subobjects that are estimators.

paramsmapping of string to any: Parameter names mapped to their values.

set_params(**params)¶

Set the parameters of this estimator.

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

**paramsdict: Estimator parameters.

selfobject: Estimator instance.

class schrodinger.application.matsci.mlearn.features.Ligand(st, metal_atom, new_to_old, coordination_idxs)[source]¶

Bases: object

Manage a ligand.

__init__(st, metal_atom, new_to_old, coordination_idxs)[source]¶

Create an instance.

Parameters

st (schrodinger.structure.Structure) – the structure
metal_atom (schrodinger.structure._StructureAtom) – the metal atom
new_to_old (dict) – the map of new indices (extracted ligand) to old indices (original structure)
coordination_idxs (list) – contains groups of indicies (new indices) of coordinating atoms

getVec(point)[source]¶

Return a vector pointing from the metal atom to the given point.

Parameters: point (numpy.array) – the point in Ang.
Return type: numpy.array
Returns: the vector in Ang.

getCentroid(st, idxs)[source]¶

Return the centroid vector of the given coordination atom indices.

Parameters

st (schrodinger.structure.Structure) – the structure
idxs (list) – the coordination indices

Return type

numpy.array

Returns

the centroid vector in Ang.

getCoordinationVec(st, idxs)[source]¶

Return a coordination vector pointing from the metal atom to the centroid of the given coordination atom indices.

Parameters

st (schrodinger.structure.Structure) – the structure
idxs (list) – the coordination indices

Return type

numpy.array

Returns

the coordination vector in Ang.

getStoichiometry()[source]¶

Return the stoichiometry.

Return type: str
Returns: the stoichiometry

getDenticity()[source]¶

Return the denticity.

Return type: int
Returns: the denticity

getHapticity()[source]¶

Return the hapticity.

Return type: int
Returns: the hapticity

getHapticCharacter()[source]¶

Return the haptic character.

Return type: int
Returns: the haptic character

getBiteAngle()[source]¶

Return the bite angle in degrees.

Return type: float or None
Returns: the bite angle in degrees

getAtomConeAngle(atom)[source]¶

Return the cone angle for the given atom in degrees.

Parameters: atom (schrodinger.structure._StructureAtom) – the atom
Return type: float
Returns: the cone angle for the given atom in degrees

getConeAngle()[source]¶

Return the cone angle in degrees.

Return type: float
Returns: the cone angle in degrees

getBondLength()[source]¶

Return the bond length in Ang.

Return type: float
Returns: the bond length in Ang.

getDescriptors()[source]¶

Return descriptors.

Return type: dict
Returns: (label, data) pairs

class schrodinger.application.matsci.mlearn.features.Complex(st, logger=None, nonmetallic_centers=())[source]¶

Bases: object

Manage a complex.

BURIED_VOLUME_VDW_SCALE = 1.17¶

CONTOURS_DIR = 'contours'¶

__init__(st, logger=None, nonmetallic_centers=())[source]¶

Create an instance.

Parameters

st (schrodinger.structure.Structure) – the structure
logger (logging.Logger or None) – output logger or None if there isn’t one
nonmetallic_centers (tuple) – Tuple of nonmetallic elements to also consider when looking for center atom

setMetalAtom()[source]¶: Set the metal atom.

setLigands()[source]¶: Set the ligands.

getBondAngle()[source]¶

Return the bond angle in degrees.

Return type: float
Returns: the bond angle in degrees

getVDWSurfaceArea()[source]¶

Return the VDW surface area in Angstrom^2.

Return type: float
Returns: the VDW surface area in Angstrom^2

getVDWVolume(vdw_scale=1, buffer_len=2)[source]¶

Return the VDW volume in Angstrom^3.

Parameters

vdw_scale (float) – the VDW scale
buffer_len (float) – a shape buffer lengths in Angstrom

Return type

float

Returns

the VDW volume in Angstrom^3

getBuriedVolumeStructure(only_largest_ligands=False)[source]¶

Return a copy of the structure without the metal atom. If only_largest_ligands is True, it will only contain the largest ligand or multiple copies thereof if it is symmetric.

Parameters: only_largest_ligands (bool) – Whether small ligands should be deleted
Return type: schrodinger.structure.Structure
Returns: the structure containing some or all ligands

getBuriedVDWVolumePct(struct, vdw_scale=1.17)[source]¶

Return the buried VDW volume percent.

Parameters

struct (structure.Structure) – The structure to get buried volume for
vdw_scale (float) – the VDW scale

Return type

float

Returns

the buried VDW volume percent

getFreeVolumeVector()[source]¶

Return a unit vector pointing from the metal atom of the complex in the direction of free volume.

Return type: numpy.array
Returns: the free volume unit vector

getRotatedComplex()[source]¶

Return a copy of the complex that is rotated so that the free volume vector points along the positive z-axis.

Return type: structure.Structure
Returns: A rotated copy of the input structure

exportBuriedVolumeContour(sphere_radius=3.5, vdw_scale=1.17, num_bins=30, seed=1234)[source]¶

Export the buried volume contour for the complex

Parameters

sphere_radius (float) – The radius for the sphere to sample points in
vdw_scale (float) – The VdW scale factor to apply to VdW radii when checking to see if a point is “inside” an atom
num_bins (int) – The number of bins in x and y direction to put the points in
seed (int) – Seed for random number generation

Return type

str, str

Returns

The paths to contour png and csv files

plotContour(points)[source]¶

Plot a contour for the passed points. matplotlib uses triangulation to create a grid for the contour.

Parameters: points (numpy.array) – The x, y, z values of points

getVectorizedDescriptors(jaguar_out_file)[source]¶

Return vectorized descriptors which are instance specific descriptors that are vectorized, for example depending on the molecule’s geometric orientation, atom indexing, etc.

Parameters: jaguar_out_file (str or None) – the name of a Jaguar *.out file from which descriptors will be extracted or None if there isn’t one
Return type: dict
Returns: (label, data) pairs

getDescriptors(no_organometallic=False)[source]¶

Return descriptors.

Parameters: no_organometallic (bool) – Whether organometallic descriptors should be skipped
Return type: dict
Returns: (label, data) pairs

schrodinger.application.matsci.mlearn.features.get_unique_titles(sts)[source]¶

Return a list of unique titles for the given structures.

Parameters: sts (list) – contains schrodinger.structure.Structure
Return type: list
Returns: the unique titles

class schrodinger.application.matsci.mlearn.features.ComplexFeatures(jaguar=False, jaguar_keywords={'basis': 'LACVP**', 'dftname': 'B3LYP', 'iuhf': '1'}, tpp=1, ligfilter=False, no_organometallic=False, nonmetallic_centers=(), canvas=False, moldescriptors=False, include_vectorized=False, save_files=False, logger=None)[source]¶

Bases: schrodinger.application.matsci.mlearn.base.BaseFeaturizer

Class to generate features for metal complexes.

__init__(jaguar=False, jaguar_keywords={'basis': 'LACVP**', 'dftname': 'B3LYP', 'iuhf': '1'}, tpp=1, ligfilter=False, no_organometallic=False, nonmetallic_centers=(), canvas=False, moldescriptors=False, include_vectorized=False, save_files=False, logger=None)[source]¶

Create an instance.

Parameters

jaguar (bool) – specify whether to calculate Jaguar features
jaguar_keywords (OrderedDict) – if Jaguar jobs must be run to calculate the Jaguar features then specify the Jaguar keywords here
tpp (int) – the number of threads for any Jaguar jobs
ligfilter (bool) – specify whether to calculate Ligfilter features
no_organometallic (bool) – Whether organometallic descriptors should be skipped
canvas (bool) – specify whether to calculate Canvas features
moldescriptors (bool or list) – specify whether to calculate Molecular Descriptors features. If it’s a list, it contains command line arguments for moldescriptors
include_vectorized (bool) – whether to include instance specific features that are vectorized, for example depending on the molecule’s geometric orientation, atom indexing, etc.
save_files (bool) – Whether to save subjob files or not
logger (logging.Logger or None) – output logger or None if there isn’t one

runJaguar()[source]¶

Run Jaguar on the given structures.

Return type: list
Returns: contains Jaguar *.out file names

getFeatures(structs, jaguar_out_files=None)[source]¶

Return features dictionary for the given structures

Parameters

structs (list(schrodinger.structure.Structure)) – list of structures to be featurized
jaguar_out_files (list or None) – if Jaguar features should be calculated using existing Jaguar *.out files then specify the files here using the same ordering as used for any given structures

verifyJaguarOutfiles()[source]¶: Run jaguar and get the out-files if the out-files have not been provided

getComplexDescriptors()[source]¶

Create a Complex object for each structure and get their descriptors

Return type: dict
Returns: The descriptors from Complex for each structure

getJaguarDescriptors()[source]¶

Return Jaguar descriptors for all structures. Sets Jaguar atom descriptors on structures.

Return type: dict
Returns: The jaguar descriptors for all structures. Keys are structure titles and values are dictionaries containing descriptors

getUtilityDescriptors()[source]¶

Get the requested utility descriptors for all structures

Return type: dict
Returns: The descriptor utility descriptors for all structures. Keys are structure titles and values are dictionaries containing descriptors

getDescriptorUtilityJob(descriptor_utility)[source]¶

Get the job to run to generate the descriptors using the passed descriptor_utility for all structures

Parameters: descriptor_utility (DescriptorUtility) – The descriptor utility to run to get the descriptors
Return type: jobutils.RobustSubmissionJob
Returns: The job to run to generate the descriptors

processUtilityDescriptorOutputs(jobs_dict)[source]¶

Read the descriptors for all descriptor utilities that were run, and return them

Parameters: jobs_dict (dict) – Dictionary with DescriptorUtility as keys and jobs as values
Return type: dict
Returns: The descriptor utility descriptors for all structures. Keys are structure titles and values are dictionaries containing descriptors

getMolecularDescriptorsJob()[source]¶

Get the job to run to generate molecular descriptors for all structures

Return type: jobutils.RobustSubmissionJob
Returns: The job to run to generate the descriptors

static writeFingerprintFiles(structs)[source]¶

Write fingerprint files for the given structures.

Parameters: structs (list(schrodinger.structure.Structure)) – list of structures to be fingerprinted
Return type: list
Returns: the fingerprint file names

log(msg, **kwargs)[source]¶

Add a message to the log file

Parameters: msg (str) – The message to log

Additional keyword arguments are passed to the textlogger.log_msg function

fit(data, data_y=None)¶

Fit and return self. Anything that evaluates properties related to the passed data should go here. For example, compute physical properties of a stucture and save them as class property, to be used in the transform method.

Parameters

data (numpy array of shape [n_samples, n_features]) – Training set
data_y (numpy array of shape [n_samples]) – Target values

Return type

BaseFeaturizer

Returns

self object with fitted data

fit_transform(X, y=None, **fit_params)¶

Fit to data, then transform it.

Fits transformer to X and y with optional parameters fit_params and returns a transformed version of X.

X : {array-like, sparse matrix, dataframe} of shape (n_samples, n_features)

yndarray of shape (n_samples,), default=None: Target values.
**fit_paramsdict: Additional fit parameters.

X_newndarray array of shape (n_samples, n_features_new): Transformed array.

get_params(deep=True)¶

Get parameters for this estimator.

deepbool, default=True: If True, will return the parameters for this estimator and contained subobjects that are estimators.

paramsmapping of string to any: Parameter names mapped to their values.

set_params(**params)¶

Set the parameters of this estimator.

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

**paramsdict: Estimator parameters.

selfobject: Estimator instance.

transform(data)¶

Get numerical features. Must be implemented by a child class.

Parameters: data (numpy array of shape [n_samples, n_features]) – Training set
Return type: numpy array of shape [n_samples, n_features_new]
Returns: Transformed array

class schrodinger.application.matsci.mlearn.features.CrystalNNFeatures(preset='ops')[source]¶

Bases: object

Calculates CrystalNN structure fingerprints as implemented in pymatgen

OPS_PRESET = 'ops'¶

CN_PRESET = 'cn'¶

__init__(preset='ops')[source]¶

Create a structure featurizer

Parameters: preset (str) – One of OPS_PRESET or CN_PRESET class constants

featurize(struct)[source]¶

Get CrystalNN fingerprints for the passed structure

:param structure.Structure The structure to get features for

Return type: list
Returns: List of CrystalNN fingerprints for the structure