RDKit
Open-source cheminformatics and machine learning.
Namespaces | Classes | Typedefs | Enumerations | Functions | Variables
RDKit::MolStandardize Namespace Reference

Namespaces

namespace  defaults
 
namespace  TautomerScoringFunctions
 

Classes

class  AcidBaseCatalogEntry
 
class  AcidBaseCatalogParams
 
class  AllowedAtomsValidation
 
struct  ChargeCorrection
 
struct  CleanupParameters
 
class  DisallowedAtomsValidation
 
class  FragmentCatalogEntry
 
class  FragmentCatalogParams
 
class  FragmentRemover
 
class  FragmentValidation
 The FragmentValidation class logs if certain fragments are present. More...
 
class  IsotopeValidation
 The IsotopeValidation class logs if molecule contains isotopes. More...
 
class  LargestFragmentChooser
 
class  MetalDisconnector
 
class  MolVSValidation
 The MolVSValidation class can be used to perform all MolVSValidions. More...
 
class  MolVSValidations
 MolVS Validations. More...
 
class  NeutralValidation
 The NeutralValidation class logs if not an overall neutral system. More...
 
class  NoAtomValidation
 
class  Normalizer
 The Normalizer class for applying Normalization transforms. More...
 
class  RDKitValidation
 
class  Reionizer
 
class  Tautomer
 
class  TautomerCatalogEntry
 
class  TautomerCatalogParams
 
class  TautomerEnumerator
 
class  TautomerEnumeratorCallback
 
class  TautomerEnumeratorResult
 Contains results of tautomer enumeration. More...
 
class  TautomerTransform
 
class  TransformCatalogEntry
 
class  TransformCatalogParams
 
class  Uncharger
 The Uncharger class for neutralizing ionized acids and bases. More...
 
class  ValidationErrorInfo
 
class  ValidationMethod
 

Typedefs

typedef RDCatalog::HierarchCatalog< AcidBaseCatalogEntry, AcidBaseCatalogParams, int > AcidBaseCatalog
 
typedef RDCatalog::HierarchCatalog< FragmentCatalogEntry, FragmentCatalogParams, int > FragmentCatalog
 
typedef RDCatalog::HierarchCatalog< TransformCatalogEntry, TransformCatalogParams, int > TransformCatalog
 
typedef std::pair< std::string, ROMOL_SPTR > SmilesMolPair
 
typedef RDCatalog::HierarchCatalog< TautomerCatalogEntry, TautomerCatalogParams, int > TautomerCatalog
 
typedef std::map< std::string, Tautomer > SmilesTautomerMap
 
typedef std::pair< std::string, Tautomer > SmilesTautomerPair
 
using TautomerTransformDefs = std::vector< std::tuple< std::string, std::string, std::string, std::string > >
 

Enumerations

enum class  TautomerEnumeratorStatus { Completed = 0 , MaxTautomersReached , MaxTransformsReached , Canceled }
 

Functions

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::pair< ROMOL_SPTR, ROMOL_SPTR > > readPairs (std::string fileName)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::pair< ROMOL_SPTR, ROMOL_SPTR > > readPairs (std::istream &inStream, int nToRead=-1)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::pair< ROMOL_SPTR, ROMOL_SPTR > > readPairs (const std::vector< std::tuple< std::string, std::string, std::string > > &data)
 
Reionizer * reionizerFromParams (const CleanupParameters &params)
 
FragmentRemover * fragmentRemoverFromParams (const CleanupParameters &params, bool leave_last=true, bool skip_if_all_match=false)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::shared_ptr< ROMol > > readFuncGroups (std::string fileName)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::shared_ptr< ROMol > > readFuncGroups (std::istream &inStream, int nToRead=-1)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::shared_ptr< ROMol > > readFuncGroups (const std::vector< std::pair< std::string, std::string > > &data)
 
RDKIT_MOLSTANDARDIZE_EXPORT void updateCleanupParamsFromJSON (CleanupParameters &params, const std::string &json)
 
RDKIT_MOLSTANDARDIZE_EXPORT RWMol * cleanup (const RWMol *mol, const CleanupParameters &params=defaultCleanupParameters)
 
RWMol * cleanup (const RWMol &mol, const CleanupParameters &params=defaultCleanupParameters)
 This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. More...
 
RDKIT_MOLSTANDARDIZE_EXPORT RWMol * normalize (const RWMol *mol, const CleanupParameters &params=defaultCleanupParameters)
 Works the same as Normalizer().normalize(mol) More...
 
RDKIT_MOLSTANDARDIZE_EXPORT RWMol * reionize (const RWMol *mol, const CleanupParameters &params=defaultCleanupParameters)
 Works the same as Reionizer().reionize(mol) More...
 
RDKIT_MOLSTANDARDIZE_EXPORT RWMol * removeFragments (const RWMol *mol, const CleanupParameters &params=defaultCleanupParameters)
 Works the same as FragmentRemover().remove(mol) More...
 
RDKIT_MOLSTANDARDIZE_EXPORT RWMol * canonicalTautomer (const RWMol *mol, const CleanupParameters &params=defaultCleanupParameters)
 Works the same as TautomerEnumerator().canonicalize(mol) More...
 
RDKIT_MOLSTANDARDIZE_EXPORT RWMol * tautomerParent (const RWMol &mol, const CleanupParameters &params=defaultCleanupParameters, bool skipStandardize=false)
 
RDKIT_MOLSTANDARDIZE_EXPORT RWMol * fragmentParent (const RWMol &mol, const CleanupParameters &params=defaultCleanupParameters, bool skip_standardize=false)
 
RDKIT_MOLSTANDARDIZE_EXPORT RWMol * stereoParent (const RWMol &mol, const CleanupParameters &params=defaultCleanupParameters, bool skip_standardize=false)
 calls removeStereochemistry() on the given molecule More...
 
RDKIT_MOLSTANDARDIZE_EXPORT RWMol * isotopeParent (const RWMol &mol, const CleanupParameters &params=defaultCleanupParameters, bool skip_standardize=false)
 removes all isotopes specifications from the given molecule More...
 
RDKIT_MOLSTANDARDIZE_EXPORT RWMol * chargeParent (const RWMol &mol, const CleanupParameters &params=defaultCleanupParameters, bool skip_standardize=false)
 
RDKIT_MOLSTANDARDIZE_EXPORT RWMol * superParent (const RWMol &mol, const CleanupParameters &params=defaultCleanupParameters, bool skip_standardize=false)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::string standardizeSmiles (const std::string &smiles)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::string > enumerateTautomerSmiles (const std::string &smiles, const CleanupParameters &params=defaultCleanupParameters)
 TODO. More...
 
Normalizer * normalizerFromParams (const CleanupParameters &params)
 
TautomerEnumerator * tautomerEnumeratorFromParams (const CleanupParameters &params)
 
TautomerEnumerator * getV1TautomerEnumerator ()
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< Bond::BondType > stringToBondType (std::string bond_str)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< int > stringToCharge (std::string charge_str)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< TautomerTransform > readTautomers (std::string fileName)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< TautomerTransform > readTautomers (std::istream &inStream, int nToRead=-1)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< TautomerTransform > readTautomers (const std::vector< std::tuple< std::string, std::string, std::string, std::string > > &data)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::shared_ptr< ChemicalReaction > > readTransformations (std::string fileName)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::shared_ptr< ChemicalReaction > > readTransformations (std::istream &inStream, int nToRead=-1)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::shared_ptr< ChemicalReaction > > readTransformations (const std::vector< std::pair< std::string, std::string > > &data)
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< ValidationErrorInfo > validateSmiles (const std::string &smiles)
 A convenience function for quickly validating a single SMILES string. More...
 

Variables

RDKIT_MOLSTANDARDIZE_EXPORT const CleanupParameters defaultCleanupParameters
 
RDKIT_MOLSTANDARDIZE_EXPORT std::vector< ChargeCorrection > CHARGE_CORRECTIONS
 

Typedef Documentation

◆ AcidBaseCatalog

typedef RDCatalog::HierarchCatalog<AcidBaseCatalogEntry, AcidBaseCatalogParams, int> RDKit::MolStandardize::AcidBaseCatalog

Definition at line 36 of file Charge.h.

◆ FragmentCatalog

typedef RDCatalog::HierarchCatalog<FragmentCatalogEntry, FragmentCatalogParams, int> RDKit::MolStandardize::FragmentCatalog

Definition at line 29 of file Fragment.h.

◆ SmilesMolPair

typedef std::pair<std::string, ROMOL_SPTR> RDKit::MolStandardize::SmilesMolPair

Definition at line 35 of file Normalize.h.

◆ SmilesTautomerMap

typedef std::map<std::string, Tautomer> RDKit::MolStandardize::SmilesTautomerMap

Definition at line 74 of file MolStandardize/Tautomer.h.

◆ SmilesTautomerPair

typedef std::pair<std::string, Tautomer> RDKit::MolStandardize::SmilesTautomerPair

Definition at line 75 of file MolStandardize/Tautomer.h.

◆ TautomerCatalog

typedef RDCatalog::HierarchCatalog<TautomerCatalogEntry, TautomerCatalogParams, int> RDKit::MolStandardize::TautomerCatalog

Definition at line 33 of file MolStandardize/Tautomer.h.

◆ TautomerTransformDefs

using RDKit::MolStandardize::TautomerTransformDefs = typedef std::vector<std::tuple<std::string, std::string, std::string, std::string> >

Definition at line 27 of file TautomerCatalogParams.h.

◆ TransformCatalog

typedef RDCatalog::HierarchCatalog<TransformCatalogEntry, TransformCatalogParams, int> RDKit::MolStandardize::TransformCatalog

Definition at line 34 of file Normalize.h.

Enumeration Type Documentation

◆ TautomerEnumeratorStatus

enum class RDKit::MolStandardize::TautomerEnumeratorStatus
strong
Enumerator
Completed 
MaxTautomersReached 
MaxTransformsReached 
Canceled 

Definition at line 47 of file MolStandardize/Tautomer.h.

Function Documentation

◆ canonicalTautomer()

RDKIT_MOLSTANDARDIZE_EXPORT RWMol * RDKit::MolStandardize::canonicalTautomer ( const RWMol *  mol,
const CleanupParameters &  params = defaultCleanupParameters 
)

Works the same as TautomerEnumerator().canonicalize(mol)

◆ chargeParent()

RDKIT_MOLSTANDARDIZE_EXPORT RWMol * RDKit::MolStandardize::chargeParent ( const RWMol &  mol,
const CleanupParameters &  params = defaultCleanupParameters,
bool  skip_standardize = false 
)

Returns the charge parent of a given molecule. The charge parent is the uncharged version of the fragment parent.

◆ cleanup() [1/2]

RWMol * RDKit::MolStandardize::cleanup ( const RWMol &  mol,
const CleanupParameters &  params = defaultCleanupParameters 
)
inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Definition at line 101 of file MolStandardize.h.

References cleanup().

◆ cleanup() [2/2]

RDKIT_MOLSTANDARDIZE_EXPORT RWMol * RDKit::MolStandardize::cleanup ( const RWMol *  mol,
const CleanupParameters &  params = defaultCleanupParameters 
)

The cleanup function is equivalent to the molvs.Standardizer().standardize(mol) function. It calls the same steps, namely: RemoveHs, RDKit SanitizeMol, MetalDisconnector, Normalizer, Reionizer, RDKit AssignStereochemistry.

Referenced by cleanup().

◆ enumerateTautomerSmiles()

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::string > RDKit::MolStandardize::enumerateTautomerSmiles ( const std::string &  smiles,
const CleanupParameters &  params = defaultCleanupParameters 
)

TODO.

◆ fragmentParent()

RDKIT_MOLSTANDARDIZE_EXPORT RWMol * RDKit::MolStandardize::fragmentParent ( const RWMol &  mol,
const CleanupParameters &  params = defaultCleanupParameters,
bool  skip_standardize = false 
)

Returns the fragment parent of a given molecule. The fragment parent is the largest organic covalent unit in the molecule.

◆ fragmentRemoverFromParams()

FragmentRemover * RDKit::MolStandardize::fragmentRemoverFromParams ( const CleanupParameters &  params,
bool  leave_last = true,
bool  skip_if_all_match = false 
)
inline

Definition at line 61 of file Fragment.h.

References RDKit::MolStandardize::CleanupParameters::fragmentData, and RDKit::MolStandardize::CleanupParameters::fragmentFile.

◆ getV1TautomerEnumerator()

TautomerEnumerator * RDKit::MolStandardize::getV1TautomerEnumerator ( )
inline

Definition at line 419 of file MolStandardize/Tautomer.h.

References RDKit::MolStandardize::defaults::defaultTautomerTransformsv1.

◆ isotopeParent()

RDKIT_MOLSTANDARDIZE_EXPORT RWMol * RDKit::MolStandardize::isotopeParent ( const RWMol &  mol,
const CleanupParameters &  params = defaultCleanupParameters,
bool  skip_standardize = false 
)

removes all isotopes specifications from the given molecule

◆ normalize()

RDKIT_MOLSTANDARDIZE_EXPORT RWMol * RDKit::MolStandardize::normalize ( const RWMol *  mol,
const CleanupParameters &  params = defaultCleanupParameters 
)

Works the same as Normalizer().normalize(mol)

◆ normalizerFromParams()

Normalizer * RDKit::MolStandardize::normalizerFromParams ( const CleanupParameters &  params)
inline

Definition at line 93 of file Normalize.h.

References RDKit::MolStandardize::CleanupParameters::maxRestarts, RDKit::MolStandardize::CleanupParameters::normalizationData, and RDKit::MolStandardize::CleanupParameters::normalizations.

◆ readFuncGroups() [1/3]

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::shared_ptr< ROMol > > RDKit::MolStandardize::readFuncGroups ( const std::vector< std::pair< std::string, std::string > > &  data)

◆ readFuncGroups() [2/3]

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::shared_ptr< ROMol > > RDKit::MolStandardize::readFuncGroups ( std::istream &  inStream,
int  nToRead = -1 
)

◆ readFuncGroups() [3/3]

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::shared_ptr< ROMol > > RDKit::MolStandardize::readFuncGroups ( std::string  fileName)

◆ readPairs() [1/3]

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::pair< ROMOL_SPTR, ROMOL_SPTR > > RDKit::MolStandardize::readPairs ( const std::vector< std::tuple< std::string, std::string, std::string > > &  data)

◆ readPairs() [2/3]

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::pair< ROMOL_SPTR, ROMOL_SPTR > > RDKit::MolStandardize::readPairs ( std::istream &  inStream,
int  nToRead = -1 
)

◆ readPairs() [3/3]

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::pair< ROMOL_SPTR, ROMOL_SPTR > > RDKit::MolStandardize::readPairs ( std::string  fileName)

◆ readTautomers() [1/3]

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< TautomerTransform > RDKit::MolStandardize::readTautomers ( const std::vector< std::tuple< std::string, std::string, std::string, std::string > > &  data)

◆ readTautomers() [2/3]

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< TautomerTransform > RDKit::MolStandardize::readTautomers ( std::istream &  inStream,
int  nToRead = -1 
)

◆ readTautomers() [3/3]

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< TautomerTransform > RDKit::MolStandardize::readTautomers ( std::string  fileName)

◆ readTransformations() [1/3]

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::shared_ptr< ChemicalReaction > > RDKit::MolStandardize::readTransformations ( const std::vector< std::pair< std::string, std::string > > &  data)

◆ readTransformations() [2/3]

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::shared_ptr< ChemicalReaction > > RDKit::MolStandardize::readTransformations ( std::istream &  inStream,
int  nToRead = -1 
)

◆ readTransformations() [3/3]

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< std::shared_ptr< ChemicalReaction > > RDKit::MolStandardize::readTransformations ( std::string  fileName)

◆ reionize()

RDKIT_MOLSTANDARDIZE_EXPORT RWMol * RDKit::MolStandardize::reionize ( const RWMol *  mol,
const CleanupParameters &  params = defaultCleanupParameters 
)

Works the same as Reionizer().reionize(mol)

◆ reionizerFromParams()

Reionizer * RDKit::MolStandardize::reionizerFromParams ( const CleanupParameters &  params)
inline

Definition at line 103 of file Charge.h.

References RDKit::MolStandardize::CleanupParameters::acidbaseData, and RDKit::MolStandardize::CleanupParameters::acidbaseFile.

◆ removeFragments()

RDKIT_MOLSTANDARDIZE_EXPORT RWMol * RDKit::MolStandardize::removeFragments ( const RWMol *  mol,
const CleanupParameters &  params = defaultCleanupParameters 
)

Works the same as FragmentRemover().remove(mol)

◆ standardizeSmiles()

RDKIT_MOLSTANDARDIZE_EXPORT std::string RDKit::MolStandardize::standardizeSmiles ( const std::string &  smiles)

Convenience function for quickly standardizing a single SMILES string. Returns a standardized canonical SMILES string given a SMILES string. This is the equivalent of calling cleanup() on each of the molecules

◆ stereoParent()

RDKIT_MOLSTANDARDIZE_EXPORT RWMol * RDKit::MolStandardize::stereoParent ( const RWMol &  mol,
const CleanupParameters &  params = defaultCleanupParameters,
bool  skip_standardize = false 
)

calls removeStereochemistry() on the given molecule

◆ stringToBondType()

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< Bond::BondType > RDKit::MolStandardize::stringToBondType ( std::string  bond_str)

◆ stringToCharge()

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< int > RDKit::MolStandardize::stringToCharge ( std::string  charge_str)

◆ superParent()

RDKIT_MOLSTANDARDIZE_EXPORT RWMol * RDKit::MolStandardize::superParent ( const RWMol &  mol,
const CleanupParameters &  params = defaultCleanupParameters,
bool  skip_standardize = false 
)

Returns the super parent. The super parent is the fragment, charge, isotope, stereo, and tautomer parent of the molecule.

◆ tautomerEnumeratorFromParams()

TautomerEnumerator * RDKit::MolStandardize::tautomerEnumeratorFromParams ( const CleanupParameters &  params)
inline

Definition at line 414 of file MolStandardize/Tautomer.h.

◆ tautomerParent()

RDKIT_MOLSTANDARDIZE_EXPORT RWMol * RDKit::MolStandardize::tautomerParent ( const RWMol &  mol,
const CleanupParameters &  params = defaultCleanupParameters,
bool  skipStandardize = false 
)

Returns the tautomer parent of a given molecule. The fragment parent is the standardized canonical tautomer of the molecule

◆ updateCleanupParamsFromJSON()

RDKIT_MOLSTANDARDIZE_EXPORT void RDKit::MolStandardize::updateCleanupParamsFromJSON ( CleanupParameters &  params,
const std::string &  json 
)

◆ validateSmiles()

RDKIT_MOLSTANDARDIZE_EXPORT std::vector< ValidationErrorInfo > RDKit::MolStandardize::validateSmiles ( const std::string &  smiles)

A convenience function for quickly validating a single SMILES string.

Variable Documentation

◆ CHARGE_CORRECTIONS

RDKIT_MOLSTANDARDIZE_EXPORT std::vector<ChargeCorrection> RDKit::MolStandardize::CHARGE_CORRECTIONS
extern

◆ defaultCleanupParameters

RDKIT_MOLSTANDARDIZE_EXPORT const CleanupParameters RDKit::MolStandardize::defaultCleanupParameters
extern

Definition at line 25 of file Fragment.h.