schrodinger.application.steps.filters module

Filter steps that take input Mols and only outputs Mols that meet certain criteria.

class schrodinger.application.steps.filters.InMemoryUniqueRandomSampleFilter(*args, **kwargs)

Bases: schrodinger.stepper.stepper.Chain

class Settings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.models.parameters.CompoundParam

n: int

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
seed: int

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
nChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

nReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

seedChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

seedReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

buildChain()

This method must be implemented by subclasses to build the chain. The chain is built by modifying self.steps. The chain’s composition may be dependent on self.settings.

class schrodinger.application.steps.filters.InMemoryUniqueSmilesFilter(*args, **kwargs)

Bases: schrodinger.application.steps.basesteps.MolReduceStep

Only allow molecules through whose canonical SMILES was not previously encountered.

reduceFunction(mols)

The main computation for this step. This function should take in a iterable of inputs and return an iterable of outputs.

Example:

def reduceFunction(self, words):
    # Find all unique words
    seen_words = set()
    for word in words:
        if word not in seen_words:
            seen_words.add(word)
            yield word
class schrodinger.application.steps.filters.InMemoryRandomSampleFilter(*args, **kwargs)

Bases: schrodinger.application.steps.basesteps.MolReduceStep

A filter that takes a random subsample of molecules. The sample size can be set through the step’s settings n.

Implementation of Algorithm R, but without knowing the size of sequence to sample from. See https://en.wikipedia.org/wiki/Reservoir_sampling

class Settings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.models.parameters.CompoundParam

n: int

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
seed: int

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
nChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

nReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

seedChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

seedReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

validateSettings()

Check whether the step settings are valid and return a list of SettingsError and SettingsWarning to report any invalid settings. Default implementation checks that all stepper files are set to valid file paths.

Return type

list[TaskError or TaskWarning]

reduceFunction(mols)

The main computation for this step. This function should take in a iterable of inputs and return an iterable of outputs.

Example:

def reduceFunction(self, words):
    # Find all unique words
    seen_words = set()
    for word in words:
        if word not in seen_words:
            seen_words.add(word)
            yield word
class schrodinger.application.steps.filters.MaeUniqueSmilesFilter(*args, **kwargs)

Bases: schrodinger.application.steps.basesteps.MaeMapStep

Filter structures based on unique seen SMILES.

setUp()

Hook for adding any type of work that needs to happen before any outputs are created.

mapFunction(st)
class schrodinger.application.steps.filters.SmartsFilter(*args, **kwargs)

Bases: schrodinger.application.steps.basesteps.MolMapStep

Only allow molecules that have a SMARTS substructure defined in settings.

class Settings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.models.parameters.CompoundParam

core_smarts: str

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
core_smartsChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

core_smartsReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

validateSettings()

Check whether the step settings are valid and return a list of SettingsError and SettingsWarning to report any invalid settings. Default implementation checks that all stepper files are set to valid file paths.

Return type

list[TaskError or TaskWarning]

setUp()

Hook for adding any type of work that needs to happen before any outputs are created.

mapFunction(mol)
class schrodinger.application.steps.filters.ChiralCenterCountFilter(*args, **kwargs)

Bases: schrodinger.application.steps.basesteps.MolMapStep

Only allow molecules through that have the number of chiral centers that falls in the ranged determined by settings’ min_value and max_value, with the borders included.

class Settings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.models.parameters.CompoundParam

min_value: int

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
max_value: int

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
max_valueChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

max_valueReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

min_valueChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

min_valueReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

validateSettings()

Check whether the step settings are valid and return a list of SettingsError and SettingsWarning to report any invalid settings. Default implementation checks that all stepper files are set to valid file paths.

Return type

list[TaskError or TaskWarning]

mapFunction(mol)
class schrodinger.application.steps.filters.ProductFilterMixin

Bases: object

A mixin that only allows molecules through whose SMARTS substructure count passes all product filters defined in the settings.

If the settings has cflt_file defined, it will be considered to be the path from which to create the smarts_filter to use.

Since the filter.SmartsFilter can checkStructure with either Mol or Structure objects the behavior is completely determined by the class that it is a mixin for, i.e., either an MolMapStep or MaeMapStep.

class Settings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.models.parameters.CompoundParam

Variables
  • smarts_filter – the smarts filter or None

  • cflt_file – if defined the source to

cflt_file: schrodinger.stepper.stepper.StepperFile

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
cflt_fileChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

cflt_fileReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

validateSettings()
setUp()
mapFunction(molecule)
class schrodinger.application.steps.filters.ProductFilter(*args, **kwargs)

Bases: schrodinger.application.steps.filters.ProductFilterMixin, schrodinger.application.steps.basesteps.MolMapStep

See ProductFilterMixin

class schrodinger.application.steps.filters.MaeProductFilter(*args, **kwargs)

Bases: schrodinger.application.steps.filters.ProductFilterMixin, schrodinger.application.steps.basesteps.MaeMapStep

See ProductFilterMixin

class schrodinger.application.steps.filters.PropertyFilter(*args, **kwargs)

Bases: schrodinger.application.steps.basesteps.MolMapStep

Only allows molecules through whose properties pass all property filters defined in the settings.

If the settings has filter_file defined, it will be considered to be the path from which to create the filters to be used.

If the filter filename has the .json extension, it will be interpreted as a JSON filter file of the kind used by a few panels, including PathFinder; that filter format is implemented by schrodinger.ui.qt.filter_dialog_dir.filter_core.

A file without the .json extension is considered to be regular text with the format of the filter file is that of what pathfinder and canvas filter uses, e.g., lines like:

r_rdkit_TPSA > 30.0 < 150.0
i_rdkit_NumRotatableBonds < 10
i_rdkit_NumChiralCenters == 1
r_rdkit_MolWt > 150.0 < 575.0
class Settings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.models.parameters.CompoundParam

filter_file: schrodinger.stepper.stepper.StepperFile

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
filter_fileChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

filter_fileReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

validateSettings()

Check whether the step settings are valid and return a list of SettingsError and SettingsWarning to report any invalid settings. Default implementation checks that all stepper files are set to valid file paths.

Return type

list[TaskError or TaskWarning]

setUp()

Hook for adding any type of work that needs to happen before any outputs are created.

mapFunction(mol)
class schrodinger.application.steps.filters.PropertyRangeSettings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.models.parameters.CompoundParam

The property_ranges dict should have, as keys, the property key and, as values, the range, [min, max] of values allowed for that property where the ends are included in what is considered to be acceptable.

Override _appendPropertyNameIssues to validate the property name, i.e., a key in the property_ranges dict.

property_ranges: Dict[str, List[float]]

A Param to represent dictionaries. Values of this param will have a mutated signal that will be emitted whenever any mutation method is called.

The constructor optionally takes a value_class keyword argument to specify what type of class the values will be. This information will be used for jsonifying the dictionary if specified. (Note that non-string keys are not currently supported for jsonification. This may change in the future. See PANEL-13029).

validate(step)

Validate the settings on behalf of a step.

Parameters

step – stepper._BaseStep

Return type

list[TaskError or TaskWarning]

property_rangesChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

property_rangesReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

class schrodinger.application.steps.filters.ProfileSettings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.application.steps.filters.PropertyRangeSettings

The property_ranges should be a dict where the key is the property name (a string that exists in filtering.DESCRIPTORS_DICT). The value should be the range of values allowed for that property where the ends are included in what is considered to be acceptable.

property_ranges: Dict[str, List[float]]

A Param to represent dictionaries. Values of this param will have a mutated signal that will be emitted whenever any mutation method is called.

The constructor optionally takes a value_class keyword argument to specify what type of class the values will be. This information will be used for jsonifying the dictionary if specified. (Note that non-string keys are not currently supported for jsonification. This may change in the future. See PANEL-13029).

property_rangesChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

property_rangesReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

class schrodinger.application.steps.filters.ProfileFilter(*args, **kwargs)

Bases: schrodinger.application.steps.basesteps.MolMapStep

A product filter where the property profile is defined by the settings.

The complexity_max is a dictionary with the property name as key and the value above which the complexity is incremented. If the total complexity exceeds max_complexity the molecule is rejected.

Example in yaml notation:

ProfileFilter:
    property_ranges:
        MolWt: [250, 500]
        FractionCSP3: [0, 1]
        AlogP: [-1, 4]
        NumRotatableBonds: &NumRotatableBonds_range [0, 10]
See

ProfileSettings

class Settings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.application.steps.filters.ProfileSettings

core_complexity: Dict[str, int]

A Param to represent dictionaries. Values of this param will have a mutated signal that will be emitted whenever any mutation method is called.

The constructor optionally takes a value_class keyword argument to specify what type of class the values will be. This information will be used for jsonifying the dictionary if specified. (Note that non-string keys are not currently supported for jsonification. This may change in the future. See PANEL-13029).

max_complexity: int

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
large_ring_cutoff: int

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
validate(step)

Validate the settings on behalf of a step.

Parameters

step – stepper._BaseStep

Return type

list[TaskError or TaskWarning]

core_complexityChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

core_complexityReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

large_ring_cutoffChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

large_ring_cutoffReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

max_complexityChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

max_complexityReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

property_rangesChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

property_rangesReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

validateSettings()

Check whether the step settings are valid and return a list of SettingsError and SettingsWarning to report any invalid settings. Default implementation checks that all stepper files are set to valid file paths.

Return type

list[TaskError or TaskWarning]

setUp()

Hook for adding any type of work that needs to happen before any outputs are created.

mapFunction(mol)
class schrodinger.application.steps.filters.FepFilter(*args, **kwargs)

Bases: schrodinger.application.steps.basesteps.MolMapStep

Only allow molecules through that are amenable to FEP calculations.

A molecule is considered to be amenable if it is an acceptable perturbation with settings.min_edges other molecules in the self.settings.ref_mols.

A perturbation is considered acceptable if the number of heavy atoms in the perturbation from the maximum common substructure (MCS) is less than or equal to settings.max_hac_diff.

The settings contain the following parameters:

  • fep_references_file: the title-less SMILES file with SMILES in the 0th column (the way that Maestro exports them…)

  • ref_mols: the list of references (Chem.Mol objects)

  • min_edges: the minimum number of edges needed

  • max_hac_diff: the maximum number of heavy atoms not part of the MCS

if the fep_references_file is defined, the ref_mols will be ignored.

class Settings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.models.parameters.CompoundParam

fep_references_file: schrodinger.stepper.stepper.StepperFile

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
ref_mols: List[rdkit.Chem.rdchem.Mol]

A Param to represent lists. Values of this param will have a mutated signal that will be emitted whenever any mutation method is called.

The constructor optionally takes a item_class keyword argument to specify what type of class the items in the list will be. This information will be used for jsonifying the list if specified.

min_edges: int

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
max_hac_diff: int

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
fep_references_fileChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

fep_references_fileReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

max_hac_diffChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

max_hac_diffReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

min_edgesChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

min_edgesReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

ref_molsChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

ref_molsReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

validateSettings()

Check whether the step settings are valid and return a list of SettingsError and SettingsWarning to report any invalid settings. Default implementation checks that all stepper files are set to valid file paths.

Return type

list[TaskError or TaskWarning]

setUp()

Hook for adding any type of work that needs to happen before any outputs are created.

mapFunction(mol)
class schrodinger.application.steps.filters.RangeFilter(*args, **kwargs)

Bases: schrodinger.application.steps.basesteps.MolMapStep

A filter that only passes the Mol part of a ScoredMol objects if the score is in the range determined by settings’ min_value and max_value, with borders included.

Input

alias of schrodinger.application.steps.dataclasses.ScoredMol

InputSerializer

alias of schrodinger.application.steps.dataclasses.ScoredMolSerializer

class Settings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.models.parameters.CompoundParam

min_value: float

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
max_value: float

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
max_valueChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

max_valueReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

min_valueChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

min_valueReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

validateSettings()

Check whether the step settings are valid and return a list of SettingsError and SettingsWarning to report any invalid settings. Default implementation checks that all stepper files are set to valid file paths.

Return type

list[TaskError or TaskWarning]

mapFunction(scored_mol)
class schrodinger.application.steps.filters.ScoreFilter(scorer_class=None, **kwargs)

Bases: schrodinger.application.steps.basesteps.MolMolWorkflow

A base class a for step consisting of a self.SCORER_CLASS instance followed by a RangeFilter.

Variables

SCORER_CLASS (ScorerStep) – the class that will compute the value to be filtered

class Settings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.models.parameters.CompoundParam

score_filter: dict

A Param to represent dictionaries. Values of this param will have a mutated signal that will be emitted whenever any mutation method is called.

The constructor optionally takes a value_class keyword argument to specify what type of class the values will be. This information will be used for jsonifying the dictionary if specified. (Note that non-string keys are not currently supported for jsonification. This may change in the future. See PANEL-13029).

score_filterChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

score_filterReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

__init__(scorer_class=None, **kwargs)
SCORER_CLASS

alias of NotImplementedError

buildChain()

This method must be implemented by subclasses to build the chain. The chain is built by modifying self.steps. The chain’s composition may be dependent on self.settings.

class schrodinger.application.steps.filters.ScoreFilterChain(*args, **kwargs)

Bases: schrodinger.application.steps.basesteps.MolMolWorkflow

A base class for chains consisting of ScoreFilter

class Settings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.models.parameters.CompoundParam

score_filters: List[Dict]

A Param to represent lists. Values of this param will have a mutated signal that will be emitted whenever any mutation method is called.

The constructor optionally takes a item_class keyword argument to specify what type of class the items in the list will be. This information will be used for jsonifying the list if specified.

score_filtersChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

score_filtersReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

SCORER_CLASS

alias of NotImplementedError

validateSettings()

Check whether the chain settings are valid and return a list of SettingsError and SettingsWarning to report any invalid settings. Default implementation simply returns problems from all child steps.

Return type

list[TaskError or TaskWarning]

buildChain()

This method must be implemented by subclasses to build the chain. The chain is built by modifying self.steps. The chain’s composition may be dependent on self.settings.

class schrodinger.application.steps.filters.LigandMLScoreFilterChain(*args, **kwargs)

Bases: schrodinger.application.steps.filters.ScoreFilterChain

A variable length chain of LigandMLFilters, allowed to be empty.

The configuration information is a list of LigandMLScorer settings combined with those of a RangeFilter for each ligand ML model to use.

Example yaml file configuration:

LigandMLScoreFilterChain:
  score_filters:
    - ml_file: model1.qzip
      min_value: -3.0
      max_value: 2.0
    - ml_file: model2.qzip
      max_value: 200
SCORER_CLASS

alias of schrodinger.application.steps.scorers.LigandMLScorer

class schrodinger.application.steps.filters.MaxMolWtFilter(*args, **kwargs)

Bases: schrodinger.application.steps.basesteps.MolMapStep

A step that filters Chem.Mol objects by molecular weight.

Note that if no max_mol_wt is set in the settings, this filter will just become an identity step.

class Settings(*args, _param_type=<object object>, **kwargs)

Bases: schrodinger.models.parameters.CompoundParam

max_mol_wt: float

Base class for all Param classes. A Param is a descriptor for storing data, which means that a single Param instance will manage the data values for multiple instances of the class that owns it. Example:

class Coord(CompoundParam):
    x: int
    y: int

An instance of the Coord class can be created normally, and Params can be accessed as normal attributes:

coord = Coord()
coord.x = 4

When a Param value is set, the valueChanged signal is emitted. Params can be serialized and deserialized to and from JSON. Params can also be nested:

class Atom(CompoundParam):
    coord: Coord
    element: str
max_mol_wtChanged

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

max_mol_wtReplaced

pyqtSignal(*types, name: str = …, revision: int = …, arguments: Sequence = …) -> PYQT_SIGNAL

types is normally a sequence of individual types. Each type is either a type object or a string that is the name of a C++ type. Alternatively each type could itself be a sequence of types each describing a different overloaded signal. name is the optional C++ name of the signal. If it is not specified then the name of the class attribute that is bound to the signal is used. revision is the optional revision of the signal that is exported to QML. If it is not specified then 0 is used. arguments is the optional sequence of the names of the signal’s arguments.

validateSettings()
Returns

A settings error if the max mol. weight setting is not properly set, None otherwise.

Return type

List[stepper.SettingsError] or None

mapFunction(mol)