Package rdkit :: Package Chem :: Module rdmolops
[hide private]
[frames] | no frames]

Module rdmolops

Module containing RDKit functionality for manipulating molecules.

Classes [hide private]
  SanitizeFlags
Functions [hide private]
 
AddHs(...)
AddHs( (Mol)mol [, (bool)explicitOnly=False [, (bool)addCoords=False]]) -> Mol : Adds hydrogens to the graph of a molecule.
 
AddRecursiveQuery(...)
AddRecursiveQuery( (Mol)mol, (Mol)query, (int)atomIdx [, (bool)preserveExistingQuery=True]) -> None : Adds a recursive query to an atom
 
AssignAtomChiralTagsFromStructure(...)
AssignAtomChiralTagsFromStructure( (Mol)mol [, (int)confId=-1 [, (bool)replaceExistingTags=True]]) -> None : Sets the chiral tags on a molecule's atoms based on a 3D conformation.
 
AssignRadicals(...)
AssignRadicals( (Mol)mol) -> None : Assigns radical counts to atoms
 
AssignStereochemistry(...)
AssignStereochemistry( (Mol)mol [, (bool)cleanIt=False [, (bool)force=False [, (bool)flagPossibleStereoCenters=False]]]) -> None : Does the CIP stereochemistry assignment for the molecule's atoms (R/S) and double bond (Z/E).
 
Cleanup(...)
Cleanup( (Mol)mol) -> None : cleans up certain common bad functionalities in the molecule
 
CombineMols(...)
CombineMols( (Mol)mol1, (Mol)mol2 [, (Point3D)offset=<rdkit.Geometry.rdGeometry.Point3D object at 0x7f5b4cae0d10>]) -> Mol : Combine the atoms from two molecules to produce a third
 
DeleteSubstructs(...)
DeleteSubstructs( (Mol)mol, (Mol)query [, (bool)onlyFrags=False]) -> Mol : Removes atoms matching a substructure query from a molecule
 
FastFindRings(...)
FastFindRings( (Mol)arg1) -> None : Does a non-SSSR ring finding for a molecule.
 
FindAllPathsOfLengthN(...)
FindAllPathsOfLengthN( (Mol)mol, (int)length [, (bool)useBonds=True [, (bool)useHs=False [, (int)rootedAtAtom=-1]]]) -> _listSt6vectorIiSaIiEE : Finds all paths of a particular length in a molecule
 
FindAllSubgraphsOfLengthMToN(...)
FindAllSubgraphsOfLengthMToN( (Mol)mol, (int)min, (int)max [, (bool)useHs=False [, (int)rootedAtAtom=-1]]) -> object : Finds all subgraphs of a particular length in a molecule See documentation for FindAllSubgraphsOfLengthN for definitions
 
FindAllSubgraphsOfLengthN(...)
FindAllSubgraphsOfLengthN( (Mol)mol, (int)length [, (bool)useHs=False [, (int)rootedAtAtom=-1]]) -> _listSt6vectorIiSaIiEE : Finds all subgraphs of a particular length in a molecule
 
FindAtomEnvironmentOfRadiusN(...)
FindAtomEnvironmentOfRadiusN( (Mol)mol, (int)radius, (int)rootedAtAtom [, (bool)useHs=False]) -> _vecti : Finds the bonds within a certain radius of an atom in a molecule
 
FindUniqueSubgraphsOfLengthN(...)
FindUniqueSubgraphsOfLengthN( (Mol)mol, (int)length [, (bool)useHs=False [, (bool)useBO=True [, (int)rootedAtAtom=-1]]]) -> _listSt6vectorIiSaIiEE : Finds unique subgraphs of a particular length in a molecule
 
FragmentOnBRICSBonds(...)
FragmentOnBRICSBonds( (Mol)mol) -> Mol : Return a new molecule with all BRICS bonds broken
 
FragmentOnBonds(...)
FragmentOnBonds( (Mol)mol, (AtomPairsParameters)bondIndices [, (bool)addDummies=True [, (AtomPairsParameters)dummyLabels=None [, (AtomPairsParameters)bondTypes=None]]]) -> Mol : Return a new molecule with all specified bonds broken
 
FragmentOnSomeBonds(...)
FragmentOnSomeBonds( (Mol)mol, (AtomPairsParameters)bondIndices [, (int)numToBreak=1 [, (bool)addDummies=True [, (AtomPairsParameters)dummyLabels=None [, (AtomPairsParameters)bondTypes=None]]]]) -> tuple : fragment on some bonds
 
Get3DDistanceMatrix(...)
Get3DDistanceMatrix( (Mol)mol [, (int)confId=-1 [, (bool)useAtomWts=False [, (bool)force=False [, (str)prefix='']]]]) -> object : Returns the molecule's 3D distance matrix.
 
GetAdjacencyMatrix(...)
GetAdjacencyMatrix( (Mol)mol [, (bool)useBO=False [, (int)emptyVal=0 [, (bool)force=False [, (str)prefix='']]]]) -> object : Returns the molecule's adjacency matrix.
 
GetDistanceMatrix(...)
GetDistanceMatrix( (Mol)mol [, (bool)useBO=False [, (bool)useAtomWts=False [, (bool)force=False [, (str)prefix='']]]]) -> object : Returns the molecule's topological distance matrix.
 
GetFormalCharge(...)
GetFormalCharge( (Mol)arg1) -> int : Returns the formal charge for the molecule.
 
GetMolFrags(...)
GetMolFrags( (Mol)mol [, (bool)asMols=False [, (bool)sanitizeFrags=True]]) -> tuple : Finds the disconnected fragments from a molecule.
 
GetSSSR(...)
GetSSSR( (Mol)arg1) -> int : Get the smallest set of simple rings for a molecule.
 
GetSymmSSSR(...)
GetSymmSSSR( (Mol)arg1) -> _vectSt6vectorIiSaIiEE : Get a symmetrized SSSR for a molecule.
 
Kekulize(...)
Kekulize( (Mol)mol [, (bool)clearAromaticFlags=False]) -> None : Kekulizes the molecule
 
LayeredFingerprint(...)
LayeredFingerprint( (Mol)mol [, (int)layerFlags=4294967295 [, (int)minPath=1 [, (int)maxPath=7 [, (int)fpSize=2048 [, (list)atomCounts=[] [, (ExplicitBitVect)setOnlyBits=None [, (bool)branchedPaths=True [, (AtomPairsParameters)fromAtoms=0]]]]]]]]) -> ExplicitBitVect : Returns a layered fingerprint for a molecule
 
MergeQueryHs(...)
MergeQueryHs( (Mol)mol) -> Mol : merges hydrogens into their neighboring atoms as queries
 
MolAddRecursiveQueries(...)
MolAddRecursiveQueries( (Mol)mol, (dict)queries, (str)propName) -> None : Adds named recursive queries to atoms
 
MurckoDecompose(...)
MurckoDecompose( (Mol)mol) -> Mol : Do a Murcko decomposition and return the scaffold
 
ParseMolQueryDefFile(...)
ParseMolQueryDefFile( (AtomPairsParameters)fileobj [, (bool)standardize=True [, (str)delimiter='\t' [, (str)comment='//' [, (int)nameColumn=0 [, (int)smartsColumn=1]]]]]) -> dict : reads query definitions from a simply formatted file
 
PathToSubmol(...)
PathToSubmol( (Mol)mol, (AtomPairsParameters)path [, (bool)useQuery=False [, (AtomPairsParameters)atomMap=None]]) -> Mol :
 
PatternFingerprint(...)
PatternFingerprint( (Mol)mol [, (int)fpSize=2048 [, (list)atomCounts=[] [, (ExplicitBitVect)setOnlyBits=None]]]) -> ExplicitBitVect : A fingerprint using SMARTS patterns
 
RDKFingerprint(...)
RDKFingerprint( (Mol)mol [, (int)minPath=1 [, (int)maxPath=7 [, (int)fpSize=2048 [, (int)nBitsPerHash=2 [, (bool)useHs=True [, (float)tgtDensity=0.0 [, (int)minSize=128 [, (bool)branchedPaths=True [, (bool)useBondOrder=True [, (AtomPairsParameters)atomInvariants=0 [, (AtomPairsParameters)fromAtoms=0 [, (AtomPairsParameters)atomBits=None]]]]]]]]]]]]) -> ExplicitBitVect : Returns an RDKit topological fingerprint for a molecule
 
RemoveHs(...)
RemoveHs( (Mol)mol [, (bool)implicitOnly=False]) -> Mol : Removes any hydrogens from the graph of a molecule.
 
RemoveStereochemistry(...)
RemoveStereochemistry( (Mol)mol) -> None : Removes all stereochemistry info from the molecule.
 
RenumberAtoms(...)
RenumberAtoms( (Mol)mol, (AtomPairsParameters)newOrder) -> Mol : Returns a copy of a molecule with renumbered atoms
 
ReplaceCore(...)
ReplaceCore( (Mol)mol, (Mol)coreQuery [, (bool)replaceDummies=True [, (bool)labelByIndex=False [, (bool)requireDummyMatch=False]]]) -> Mol : Removes the core of a molecule and labels the sidechains with dummy atoms.
 
ReplaceSidechains(...)
ReplaceSidechains( (Mol)mol, (Mol)coreQuery) -> Mol : Replaces sidechains in a molecule with dummy atoms for their attachment points.
 
ReplaceSubstructs(...)
ReplaceSubstructs( (Mol)mol, (Mol)query, (Mol)replacement [, (bool)replaceAll=False [, (int)replacementConnectionPoint=0]]) -> object : Replaces atoms matching a substructure query in a molecule
 
SanitizeMol(...)
SanitizeMol( (Mol)mol [, (int)sanitizeOps=rdkit.Chem.rdmolops.SanitizeFlags.SANITIZE_ALL [, (bool)catchErrors=False]]) -> SanitizeFlags : Kekulize, check valencies, set aromaticity, conjugation and hybridization
 
SetAromaticity(...)
SetAromaticity( (Mol)mol) -> None : does aromaticity perception
 
SetConjugation(...)
SetConjugation( (Mol)mol) -> None : finds conjugated bonds
 
SetHybridization(...)
SetHybridization( (Mol)mol) -> None : Assigns hybridization states to atoms
 
SplitMolByPDBChainId(...)
SplitMolByPDBChainId( (Mol)mol [, (AtomPairsParameters)whiteList=None [, (bool)negateList=False]]) -> dict : Splits a molecule into pieces based on PDB chain information.
 
SplitMolByPDBResidues(...)
SplitMolByPDBResidues( (Mol)mol [, (AtomPairsParameters)whiteList=None [, (bool)negateList=False]]) -> dict : Splits a molecule into pieces based on PDB residue information.
 
WedgeMolBonds(...)
WedgeMolBonds( (Mol)arg1, (Conformer)arg2) -> None : Set the wedging on single bonds in a molecule.
Variables [hide private]
  LayeredFingerprint_substructLayers = 7
  _LayeredFingerprint_version = '0.7.0'
  _RDKFingerprint_version = '2.0.0'
  __package__ = None
hash(x)
Function Details [hide private]

AddHs(...)

 

AddHs( (Mol)mol [, (bool)explicitOnly=False [, (bool)addCoords=False]]) -> Mol :
    Adds hydrogens to the graph of a molecule.
    
      ARGUMENTS:
    
        - mol: the molecule to be modified
    
        - explicitOnly: (optional) if this toggle is set, only explicit Hs will
          be added to the molecule.  Default value is 0 (add implicit and explicit Hs).
    
        - addCoords: (optional) if this toggle is set, The Hs will have 3D coordinates
          set.  Default value is 0 (no 3D coords).
    
      RETURNS: a new molecule with added Hs
    
      NOTES:
    
        - The original molecule is *not* modified.
    
        - Much of the code assumes that Hs are not included in the molecular
          topology, so be *very* careful with the molecule that comes back from
          this function.
    
    

    C++ signature :
        RDKit::ROMol* AddHs(RDKit::ROMol [,bool=False [,bool=False]])

AddRecursiveQuery(...)

 

AddRecursiveQuery( (Mol)mol, (Mol)query, (int)atomIdx [, (bool)preserveExistingQuery=True]) -> None :
    Adds a recursive query to an atom
    
      ARGUMENTS:
    
        - mol: the molecule to be modified
    
        - query: the molecule to be used as the recursive query (this will be copied)
    
        - atomIdx: the atom to modify
    
        - preserveExistingQuery: (optional) if this is set, existing query information on the atom will be preserved
    
      RETURNS: None
    
    

    C++ signature :
        void AddRecursiveQuery(RDKit::ROMol {lvalue},RDKit::ROMol,unsigned int [,bool=True])

AssignAtomChiralTagsFromStructure(...)

 

AssignAtomChiralTagsFromStructure( (Mol)mol [, (int)confId=-1 [, (bool)replaceExistingTags=True]]) -> None :
    Sets the chiral tags on a molecule's atoms based on 
      a 3D conformation.
    
      ARGUMENTS:
    
        - mol: the molecule to use
        - confId: the conformer id to use, -1 for the default 
        - replaceExistingTags: if True, existing stereochemistry information will be cleared 
                               before running the calculation. 
    
    

    C++ signature :
        void AssignAtomChiralTagsFromStructure(RDKit::ROMol {lvalue} [,int=-1 [,bool=True]])

AssignRadicals(...)

 

AssignRadicals( (Mol)mol) -> None :
    Assigns radical counts to atoms
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
      NOTES:
    
        - The molecule is modified in place.
    
    

    C++ signature :
        void AssignRadicals(RDKit::ROMol {lvalue})

AssignStereochemistry(...)

 

AssignStereochemistry( (Mol)mol [, (bool)cleanIt=False [, (bool)force=False [, (bool)flagPossibleStereoCenters=False]]]) -> None :
    Does the CIP stereochemistry assignment 
      for the molecule's atoms (R/S) and double bond (Z/E).
      Chiral atoms will have a property '_CIPCode' indicating
      their chiral code.
    
      ARGUMENTS:
    
        - mol: the molecule to use
        - cleanIt: (optional) if provided, atoms with a chiral specifier that aren't
          actually chiral (e.g. atoms with duplicate substituents or only 2 substituents,
          etc.) will have their chiral code set to CHI_UNSPECIFIED
        - force: (optional) causes the calculation to be repeated, even if it has already
          been done
        - flagPossibleStereoCenters (optional)   set the _ChiralityPossible property on
          atoms that are possible stereocenters
    
    

    C++ signature :
        void AssignStereochemistry(RDKit::ROMol {lvalue} [,bool=False [,bool=False [,bool=False]]])

Cleanup(...)

 

Cleanup( (Mol)mol) -> None :
    cleans up certain common bad functionalities in the molecule
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
      NOTES:
    
        - The molecule is modified in place.
    
    

    C++ signature :
        void Cleanup(RDKit::ROMol {lvalue})

CombineMols(...)

 

CombineMols( (Mol)mol1, (Mol)mol2 [, (Point3D)offset=<rdkit.Geometry.rdGeometry.Point3D object at 0x7f5b4cae0d10>]) -> Mol :
    Combine the atoms from two molecules to produce a third

    C++ signature :
        RDKit::ROMol* CombineMols(RDKit::ROMol,RDKit::ROMol [,RDGeom::Point3D=<rdkit.Geometry.rdGeometry.Point3D object at 0x7f5b4cae0d10>])

DeleteSubstructs(...)

 

DeleteSubstructs( (Mol)mol, (Mol)query [, (bool)onlyFrags=False]) -> Mol :
    Removes atoms matching a substructure query from a molecule
    
      ARGUMENTS:
    
        - mol: the molecule to be modified
    
        - query: the molecule to be used as a substructure query
    
        - onlyFrags: (optional) if this toggle is set, atoms will only be removed if
          the entire fragment in which they are found is matched by the query.
          See below for examples.
          Default value is 0 (remove the atoms whether or not the entire fragment matches)
    
      RETURNS: a new molecule with the substructure removed
    
      NOTES:
    
        - The original molecule is *not* modified.
    
      EXAMPLES:
    
       The following examples substitute SMILES/SMARTS strings for molecules, you'd have
       to actually use molecules:
    
        - DeleteSubstructs('CCOC','OC') -> 'CC'
    
        - DeleteSubstructs('CCOC','OC',1) -> 'CCOC'
    
        - DeleteSubstructs('CCOCCl.Cl','Cl',1) -> 'CCOCCl'
    
        - DeleteSubstructs('CCOCCl.Cl','Cl') -> 'CCOC'
    
    

    C++ signature :
        RDKit::ROMol* DeleteSubstructs(RDKit::ROMol,RDKit::ROMol [,bool=False])

FastFindRings(...)

 

FastFindRings( (Mol)arg1) -> None :
    Does a non-SSSR ring finding for a molecule.
    
      ARGUMENTS:
    
        - mol: the molecule to use.
    
      RETURNS: Nothing
    
    

    C++ signature :
        void FastFindRings(RDKit::ROMol)

FindAllPathsOfLengthN(...)

 

FindAllPathsOfLengthN( (Mol)mol, (int)length [, (bool)useBonds=True [, (bool)useHs=False [, (int)rootedAtAtom=-1]]]) -> _listSt6vectorIiSaIiEE :
    Finds all paths of a particular length in a molecule
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
        - length: an integer with the target length for the paths.
    
        - useBonds: (optional) toggles the use of bond indices in the paths.
          Otherwise atom indices are used.  *Note* this behavior is different
          from that for subgraphs.
          Defaults to 1.
    
        - rootedAtAtom: (optional) if nonzero, only paths from the specified
          atom will be returned.
    
      RETURNS: a tuple of tuples with IDs for the bonds.
    
      NOTES: 
    
       - Difference between _subgraphs_ and _paths_ :: 
    
           Subgraphs are potentially branched, whereas paths (in our 
           terminology at least) cannot be.  So, the following graph: 
    
                C--0--C--1--C--3--C
                      |
                      2
                      |
                      C
    
           has 3 _subgraphs_ of length 3: (0,1,2),(0,1,3),(2,1,3)
           but only 2 _paths_ of length 3: (0,1,3),(2,1,3)
    
    

    C++ signature :
        std::list<std::vector<int, std::allocator<int> >, std::allocator<std::vector<int, std::allocator<int> > > > FindAllPathsOfLengthN(RDKit::ROMol,unsigned int [,bool=True [,bool=False [,int=-1]]])

FindAllSubgraphsOfLengthMToN(...)

 

FindAllSubgraphsOfLengthMToN( (Mol)mol, (int)min, (int)max [, (bool)useHs=False [, (int)rootedAtAtom=-1]]) -> object :
    Finds all subgraphs of a particular length in a molecule
      See documentation for FindAllSubgraphsOfLengthN for definitions
    
    

    C++ signature :
        boost::python::api::object FindAllSubgraphsOfLengthMToN(RDKit::ROMol,unsigned int,unsigned int [,bool=False [,int=-1]])

FindAllSubgraphsOfLengthN(...)

 

FindAllSubgraphsOfLengthN( (Mol)mol, (int)length [, (bool)useHs=False [, (int)rootedAtAtom=-1]]) -> _listSt6vectorIiSaIiEE :
    Finds all subgraphs of a particular length in a molecule
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
        - length: an integer with the target number of bonds for the subgraphs.
    
        - useHs: (optional) toggles whether or not bonds to Hs that are part of the graph
          should be included in the results.
          Defaults to 0.
    
        - rootedAtAtom: (optional) if nonzero, only subgraphs from the specified
          atom will be returned.
    
      RETURNS: a tuple of 2-tuples with bond IDs
    
      NOTES: 
    
       - Difference between _subgraphs_ and _paths_ :: 
    
           Subgraphs are potentially branched, whereas paths (in our 
           terminology at least) cannot be.  So, the following graph: 
    
                C--0--C--1--C--3--C
                      |
                      2
                      |
                      C
      has 3 _subgraphs_ of length 3: (0,1,2),(0,1,3),(2,1,3)
      but only 2 _paths_ of length 3: (0,1,3),(2,1,3)
    
    

    C++ signature :
        std::list<std::vector<int, std::allocator<int> >, std::allocator<std::vector<int, std::allocator<int> > > > FindAllSubgraphsOfLengthN(RDKit::ROMol,unsigned int [,bool=False [,int=-1]])

FindAtomEnvironmentOfRadiusN(...)

 

FindAtomEnvironmentOfRadiusN( (Mol)mol, (int)radius, (int)rootedAtAtom [, (bool)useHs=False]) -> _vecti :
    Finds the bonds within a certain radius of an atom in a molecule
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
        - radius: an integer with the target radius for the environment.
    
        - rootedAtAtom: the atom to consider
    
        - useHs: (optional) toggles whether or not bonds to Hs that are part of the graph
          should be included in the results.
          Defaults to 0.
    
      RETURNS: a vector of bond IDs
    
    
    

    C++ signature :
        std::vector<int, std::allocator<int> > FindAtomEnvironmentOfRadiusN(RDKit::ROMol,unsigned int,unsigned int [,bool=False])

FindUniqueSubgraphsOfLengthN(...)

 

FindUniqueSubgraphsOfLengthN( (Mol)mol, (int)length [, (bool)useHs=False [, (bool)useBO=True [, (int)rootedAtAtom=-1]]]) -> _listSt6vectorIiSaIiEE :
    Finds unique subgraphs of a particular length in a molecule
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
        - length: an integer with the target number of bonds for the subgraphs.
    
        - useHs: (optional) toggles whether or not bonds to Hs that are part of the graph
          should be included in the results.
          Defaults to 0.
    
        - useBO: (optional) Toggles use of bond orders in distinguishing one subgraph from
          another.
          Defaults to 1.
    
        - rootedAtAtom: (optional) if nonzero, only subgraphs from the specified
          atom will be returned.
    
      RETURNS: a tuple of tuples with bond IDs
    
    
    

    C++ signature :
        std::list<std::vector<int, std::allocator<int> >, std::allocator<std::vector<int, std::allocator<int> > > > FindUniqueSubgraphsOfLengthN(RDKit::ROMol,unsigned int [,bool=False [,bool=True [,int=-1]]])

FragmentOnBRICSBonds(...)

 

FragmentOnBRICSBonds( (Mol)mol) -> Mol :
    Return a new molecule with all BRICS bonds broken

    C++ signature :
        RDKit::ROMol* FragmentOnBRICSBonds(RDKit::ROMol)

FragmentOnBonds(...)

 

FragmentOnBonds( (Mol)mol, (AtomPairsParameters)bondIndices [, (bool)addDummies=True [, (AtomPairsParameters)dummyLabels=None [, (AtomPairsParameters)bondTypes=None]]]) -> Mol :
    Return a new molecule with all specified bonds broken
    
      ARGUMENTS:
    
          - mol            - the molecule to be modified
          - bondIndices    - indices of the bonds to be broken
          - addDummies  - toggles addition of dummy atoms to indicate where 
              bonds were broken
          - dummyLabels - used to provide the labels to be used for the dummies.
              the first element in each pair is the label for the dummy
              that replaces the bond's beginAtom, the second is for the 
              dummy that replaces the bond's endAtom. If not provided, the
              dummies are labeled with atom indices.
          - bondTypes - used to provide the bond type to use between the
              fragments and the dummy atoms. If not provided, defaults to single. 
    
      RETURNS:
          a new Mol with the modifications
    

    C++ signature :
        RDKit::ROMol* FragmentOnBonds(RDKit::ROMol,boost::python::api::object [,bool=True [,boost::python::api::object=None [,boost::python::api::object=None]]])

FragmentOnSomeBonds(...)

 

FragmentOnSomeBonds( (Mol)mol, (AtomPairsParameters)bondIndices [, (int)numToBreak=1 [, (bool)addDummies=True [, (AtomPairsParameters)dummyLabels=None [, (AtomPairsParameters)bondTypes=None]]]]) -> tuple :
    fragment on some bonds

    C++ signature :
        boost::python::tuple FragmentOnSomeBonds(RDKit::ROMol,boost::python::api::object [,unsigned int=1 [,bool=True [,boost::python::api::object=None [,boost::python::api::object=None]]]])

Get3DDistanceMatrix(...)

 

Get3DDistanceMatrix( (Mol)mol [, (int)confId=-1 [, (bool)useAtomWts=False [, (bool)force=False [, (str)prefix='']]]]) -> object :
    Returns the molecule's 3D distance matrix.
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
        - confId: (optional) chooses the conformer Id to use
          Default value is -1.
    
        - useAtomWts: (optional) toggles using atom weights for the diagonal elements of the
          matrix (to return a "Balaban" distance matrix).
          Default value is 0.
    
        - force: (optional) forces the calculation to proceed, even if there is a cached value.
          Default value is 0.
    
        - prefix: (optional, internal use) sets the prefix used in the property cache
          Default value is .
    
      RETURNS: a Numeric array of floats with the distance matrix
    
    

    C++ signature :
        _object* Get3DDistanceMatrix(RDKit::ROMol {lvalue} [,int=-1 [,bool=False [,bool=False [,char const*='']]]])

GetAdjacencyMatrix(...)

 

GetAdjacencyMatrix( (Mol)mol [, (bool)useBO=False [, (int)emptyVal=0 [, (bool)force=False [, (str)prefix='']]]]) -> object :
    Returns the molecule's adjacency matrix.
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
        - useBO: (optional) toggles use of bond orders in calculating the matrix.
          Default value is 0.
    
        - emptyVal: (optional) sets the elements of the matrix between non-adjacent atoms
          Default value is 0.
    
        - force: (optional) forces the calculation to proceed, even if there is a cached value.
          Default value is 0.
    
        - prefix: (optional, internal use) sets the prefix used in the property cache
          Default value is .
    
      RETURNS: a Numeric array of floats containing the adjacency matrix
    
    

    C++ signature :
        _object* GetAdjacencyMatrix(RDKit::ROMol {lvalue} [,bool=False [,int=0 [,bool=False [,char const*='']]]])

GetDistanceMatrix(...)

 

GetDistanceMatrix( (Mol)mol [, (bool)useBO=False [, (bool)useAtomWts=False [, (bool)force=False [, (str)prefix='']]]]) -> object :
    Returns the molecule's topological distance matrix.
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
        - useBO: (optional) toggles use of bond orders in calculating the distance matrix.
          Default value is 0.
    
        - useAtomWts: (optional) toggles using atom weights for the diagonal elements of the
          matrix (to return a "Balaban" distance matrix).
          Default value is 0.
    
        - force: (optional) forces the calculation to proceed, even if there is a cached value.
          Default value is 0.
    
        - prefix: (optional, internal use) sets the prefix used in the property cache
          Default value is .
    
      RETURNS: a Numeric array of floats with the distance matrix
    
    

    C++ signature :
        _object* GetDistanceMatrix(RDKit::ROMol {lvalue} [,bool=False [,bool=False [,bool=False [,char const*='']]]])

GetFormalCharge(...)

 

GetFormalCharge( (Mol)arg1) -> int :
    Returns the formal charge for the molecule.
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
    

    C++ signature :
        int GetFormalCharge(RDKit::ROMol)

GetMolFrags(...)

 

GetMolFrags( (Mol)mol [, (bool)asMols=False [, (bool)sanitizeFrags=True]]) -> tuple :
    Finds the disconnected fragments from a molecule.
    
      For example, for the molecule 'CC(=O)[O-].[NH3+]C' GetMolFrags() returns
      ((0, 1, 2, 3), (4, 5))
    
      ARGUMENTS:
    
        - mol: the molecule to use
        - asMols: (optional) if this is provided and true, the fragments
          will be returned as molecules instead of atom ids.
        - sanitizeFrags: (optional) if this is provided and true, the fragments
          molecules will be sanitized before returning them.
    
      RETURNS: a tuple of tuples with IDs for the atoms in each fragment
               or a tuple of molecules.
    
    

    C++ signature :
        boost::python::tuple GetMolFrags(RDKit::ROMol [,bool=False [,bool=True]])

GetSSSR(...)

 

GetSSSR( (Mol)arg1) -> int :
    Get the smallest set of simple rings for a molecule.
    
      ARGUMENTS:
    
        - mol: the molecule to use.
    
      RETURNS: a sequence of sequences containing the rings found as atom ids
             The length of this will be equal to NumBonds-NumAtoms+1 for single-fragment molecules.
    
    

    C++ signature :
        int GetSSSR(RDKit::ROMol {lvalue})

GetSymmSSSR(...)

 

GetSymmSSSR( (Mol)arg1) -> _vectSt6vectorIiSaIiEE :
    Get a symmetrized SSSR for a molecule.
    
      The symmetrized SSSR is at least as large as the SSSR for a molecule.
      In certain highly-symmetric cases (e.g. cubane), the symmetrized SSSR can be
      a bit larger (i.e. the number of symmetrized rings is >= NumBonds-NumAtoms+1).
    
      ARGUMENTS:
    
        - mol: the molecule to use.
    
      RETURNS: a sequence of sequences containing the rings found as atom ids
    
    

    C++ signature :
        std::vector<std::vector<int, std::allocator<int> >, std::allocator<std::vector<int, std::allocator<int> > > > GetSymmSSSR(RDKit::ROMol {lvalue})

Kekulize(...)

 

Kekulize( (Mol)mol [, (bool)clearAromaticFlags=False]) -> None :
    Kekulizes the molecule
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
        - clearAromaticFlags: (optional) if this toggle is set, all atoms and bonds in the 
          molecule will be marked non-aromatic following the kekulization.
          Default value is 0.
    
      NOTES:
    
        - The molecule is modified in place.
    
    

    C++ signature :
        void Kekulize(RDKit::ROMol {lvalue} [,bool=False])

LayeredFingerprint(...)

 

LayeredFingerprint( (Mol)mol [, (int)layerFlags=4294967295 [, (int)minPath=1 [, (int)maxPath=7 [, (int)fpSize=2048 [, (list)atomCounts=[] [, (ExplicitBitVect)setOnlyBits=None [, (bool)branchedPaths=True [, (AtomPairsParameters)fromAtoms=0]]]]]]]]) -> ExplicitBitVect :
    Returns a layered fingerprint for a molecule
    
      NOTE: This function is experimental. The API or results may change from
        release to release.
    
      Explanation of the algorithm below.
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
        - layerFlags: (optional) which layers to include in the fingerprint
          See below for definitions. Defaults to all.
    
        - minPath: (optional) minimum number of bonds to include in the subgraphs
          Defaults to 1.
    
        - maxPath: (optional) maximum number of bonds to include in the subgraphs
          Defaults to 7.
    
        - fpSize: (optional) number of bits in the fingerprint
          Defaults to 2048.
    
        - atomCounts: (optional) 
            if provided, this should be a list at least as long as the number of atoms
            in the molecule. It will be used to provide the count of the number 
                                  of paths that set bits each atom is involved in.
            NOTE: the list is not zeroed out here.
    
        - setOnlyBits: (optional) 
            if provided, only bits that are set in this bit vector will be set
            in the result. This is essentially the same as doing:
               res &= setOnlyBits
            but also has an impact on the atomCounts (if being used)
    
        - branchedPaths: (optional) if set both branched and unbranched paths will be
          used in the fingerprint.
          Defaults to True.
    
        - fromAtoms: (optional) a sequence of atom indices. If provided, only paths/subgraphs 
          starting from these atoms will be used.
          Defaults to empty.
    
      RETURNS: a DataStructs.ExplicitBitVect with _fpSize_ bits
    
      Layer definitions:
         - 0x01: pure topology
         - 0x02: bond order
         - 0x04: atom types
         - 0x08: presence of rings
         - 0x10: ring sizes
         - 0x20: aromaticity
    
    
    

    C++ signature :
        ExplicitBitVect* LayeredFingerprint(RDKit::ROMol [,unsigned int=4294967295 [,unsigned int=1 [,unsigned int=7 [,unsigned int=2048 [,boost::python::list=[] [,ExplicitBitVect*=None [,bool=True [,boost::python::api::object=0]]]]]]]])

MergeQueryHs(...)

 

MergeQueryHs( (Mol)mol) -> Mol :
    merges hydrogens into their neighboring atoms as queries

    C++ signature :
        RDKit::ROMol* MergeQueryHs(RDKit::ROMol)

MolAddRecursiveQueries(...)

 

MolAddRecursiveQueries( (Mol)mol, (dict)queries, (str)propName) -> None :
    Adds named recursive queries to atoms
    

    C++ signature :
        void MolAddRecursiveQueries(RDKit::ROMol {lvalue},boost::python::dict,std::string)

MurckoDecompose(...)

 

MurckoDecompose( (Mol)mol) -> Mol :
    Do a Murcko decomposition and return the scaffold

    C++ signature :
        RDKit::ROMol* MurckoDecompose(RDKit::ROMol)

ParseMolQueryDefFile(...)

 

ParseMolQueryDefFile( (AtomPairsParameters)fileobj [, (bool)standardize=True [, (str)delimiter='\t' [, (str)comment='//' [, (int)nameColumn=0 [, (int)smartsColumn=1]]]]]) -> dict :
    reads query definitions from a simply formatted file
    

    C++ signature :
        boost::python::dict ParseMolQueryDefFile(boost::python::api::object {lvalue} [,bool=True [,std::string='\t' [,std::string='//' [,unsigned int=0 [,unsigned int=1]]]]])

PathToSubmol(...)

 

PathToSubmol( (Mol)mol, (AtomPairsParameters)path [, (bool)useQuery=False [, (AtomPairsParameters)atomMap=None]]) -> Mol :

    C++ signature :
        RDKit::ROMol* PathToSubmol(RDKit::ROMol,boost::python::api::object {lvalue} [,bool=False [,boost::python::api::object=None]])

PatternFingerprint(...)

 

PatternFingerprint( (Mol)mol [, (int)fpSize=2048 [, (list)atomCounts=[] [, (ExplicitBitVect)setOnlyBits=None]]]) -> ExplicitBitVect :
    A fingerprint using SMARTS patterns 
    
      NOTE: This function is experimental. The API or results may change from
        release to release.
    

    C++ signature :
        ExplicitBitVect* PatternFingerprint(RDKit::ROMol [,unsigned int=2048 [,boost::python::list=[] [,ExplicitBitVect*=None]]])

RDKFingerprint(...)

 

RDKFingerprint( (Mol)mol [, (int)minPath=1 [, (int)maxPath=7 [, (int)fpSize=2048 [, (int)nBitsPerHash=2 [, (bool)useHs=True [, (float)tgtDensity=0.0 [, (int)minSize=128 [, (bool)branchedPaths=True [, (bool)useBondOrder=True [, (AtomPairsParameters)atomInvariants=0 [, (AtomPairsParameters)fromAtoms=0 [, (AtomPairsParameters)atomBits=None]]]]]]]]]]]]) -> ExplicitBitVect :
    Returns an RDKit topological fingerprint for a molecule
    
      Explanation of the algorithm below.
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
        - minPath: (optional) minimum number of bonds to include in the subgraphs
          Defaults to 1.
    
        - maxPath: (optional) maximum number of bonds to include in the subgraphs
          Defaults to 7.
    
        - fpSize: (optional) number of bits in the fingerprint
          Defaults to 2048.
    
        - nBitsPerHash: (optional) number of bits to set per path
          Defaults to 2.
    
        - useHs: (optional) include paths involving Hs in the fingerprint if the molecule
          has explicit Hs.
          Defaults to True.
    
        - tgtDensity: (optional) fold the fingerprint until this minimum density has
          been reached
          Defaults to 0.
    
        - minSize: (optional) the minimum size the fingerprint will be folded to when
          trying to reach tgtDensity
          Defaults to 128.
    
        - branchedPaths: (optional) if set both branched and unbranched paths will be
          used in the fingerprint.
          Defaults to True.
    
        - useBondOrder: (optional) if set both bond orders will be used in the path hashes
          Defaults to True.
    
        - atomInvariants: (optional) a sequence of atom invariants to use in the path hashes
          Defaults to empty.
    
        - fromAtoms: (optional) a sequence of atom indices. If provided, only paths/subgraphs 
          starting from these atoms will be used.
          Defaults to empty.
    
        - atomBits: (optional) an empty list. If provided, the result will contain a list 
          containing the bits each atom sets.
          Defaults to empty.
    
      RETURNS: a DataStructs.ExplicitBitVect with _fpSize_ bits
    
      ALGORITHM:
    
       This algorithm functions by find all subgraphs between minPath and maxPath in
        length.  For each subgraph:
    
         1) A hash is calculated.
    
         2) The hash is used to seed a random-number generator
    
         3) _nBitsPerHash_ random numbers are generated and used to set the corresponding
            bits in the fingerprint
    
    
    

    C++ signature :
        ExplicitBitVect* RDKFingerprint(RDKit::ROMol [,unsigned int=1 [,unsigned int=7 [,unsigned int=2048 [,unsigned int=2 [,bool=True [,double=0.0 [,unsigned int=128 [,bool=True [,bool=True [,boost::python::api::object=0 [,boost::python::api::object=0 [,boost::python::api::object=None]]]]]]]]]]]])

RemoveHs(...)

 

RemoveHs( (Mol)mol [, (bool)implicitOnly=False]) -> Mol :
    Removes any hydrogens from the graph of a molecule.
    
      ARGUMENTS:
    
        - mol: the molecule to be modified
    
        - implicitOnly: (optional) if this toggle is set, only implicit Hs will
          be removed from the graph.  Default value is 0 (remove implicit and explicit Hs).
    
      RETURNS: a new molecule with the Hs removed
    
      NOTES:
    
        - The original molecule is *not* modified.
    
    

    C++ signature :
        RDKit::ROMol* RemoveHs(RDKit::ROMol [,bool=False])

RemoveStereochemistry(...)

 

RemoveStereochemistry( (Mol)mol) -> None :
    Removes all stereochemistry info from the molecule.
    
    

    C++ signature :
        void RemoveStereochemistry(RDKit::ROMol {lvalue})

RenumberAtoms(...)

 

RenumberAtoms( (Mol)mol, (AtomPairsParameters)newOrder) -> Mol :
    Returns a copy of a molecule with renumbered atoms
    
      ARGUMENTS:
    
        - mol: the molecule to be modified
    
        - newOrder: the new ordering the atoms (should be numAtoms long)
             for example: if newOrder is [3,2,0,1], then atom 3 in the original 
             molecule will be atom 0 in the new one
    
    
    

    C++ signature :
        RDKit::ROMol* RenumberAtoms(RDKit::ROMol,boost::python::api::object {lvalue})

ReplaceCore(...)

 

ReplaceCore( (Mol)mol, (Mol)coreQuery [, (bool)replaceDummies=True [, (bool)labelByIndex=False [, (bool)requireDummyMatch=False]]]) -> Mol :
    Removes the core of a molecule and labels the sidechains with dummy atoms.
    
      ARGUMENTS:
    
        - mol: the molecule to be modified
    
        - coreQuery: the molecule to be used as a substructure query for recognizing the core
    
        - replaceDummies: toggles replacement of atoms that match dummies in the query
    
        - labelByIndex: toggles labeling the attachment point dummy atoms with 
                        the index of the core atom they're attached to.
    
        - requireDummyMatch: if the molecule has side chains that attach at points not
                             flagged with a dummy, it will be rejected (None is returned)
    
      RETURNS: a new molecule with the core removed
    
      NOTES:
    
        - The original molecule is *not* modified.
    
      EXAMPLES:
    
       The following examples substitute SMILES/SMARTS strings for molecules, you'd have
       to actually use molecules:
    
        - ReplaceCore('CCC1CCC1','C1CCC1') -> 'CC[1*]'
    
        - ReplaceCore('CCC1CC1','C1CCC1') -> ''
    
        - ReplaceCore('C1CC2C1CCC2','C1CCC1') -> '[1*]C1CCC1[2*]'
    
        - ReplaceCore('C1CNCC1','N') -> '[1*]CCCC[2*]'
    
        - ReplaceCore('C1CCC1CN','C1CCC1[*]',False) -> '[1*]CN'
    
    

    C++ signature :
        RDKit::ROMol* ReplaceCore(RDKit::ROMol,RDKit::ROMol [,bool=True [,bool=False [,bool=False]]])

ReplaceSidechains(...)

 

ReplaceSidechains( (Mol)mol, (Mol)coreQuery) -> Mol :
    Replaces sidechains in a molecule with dummy atoms for their attachment points.
    
      ARGUMENTS:
    
        - mol: the molecule to be modified
    
        - coreQuery: the molecule to be used as a substructure query for recognizing the core
    
      RETURNS: a new molecule with the sidechains removed
    
      NOTES:
    
        - The original molecule is *not* modified.
    
      EXAMPLES:
    
       The following examples substitute SMILES/SMARTS strings for molecules, you'd have
       to actually use molecules:
    
        - ReplaceSidechains('CCC1CCC1','C1CCC1') -> '[Xa]C1CCC1'
    
        - ReplaceSidechains('CCC1CC1','C1CCC1') -> ''
    
        - ReplaceSidechains('C1CC2C1CCC2','C1CCC1') -> '[Xa]C1CCC1[Xb]'
    
    

    C++ signature :
        RDKit::ROMol* ReplaceSidechains(RDKit::ROMol,RDKit::ROMol)

ReplaceSubstructs(...)

 

ReplaceSubstructs( (Mol)mol, (Mol)query, (Mol)replacement [, (bool)replaceAll=False [, (int)replacementConnectionPoint=0]]) -> object :
    Replaces atoms matching a substructure query in a molecule
    
      ARGUMENTS:
    
        - mol: the molecule to be modified
    
        - query: the molecule to be used as a substructure query
    
        - replacement: the molecule to be used as the replacement
    
        - replaceAll: (optional) if this toggle is set, all substructures matching
          the query will be replaced in a single result, otherwise each result will
          contain a separate replacement.
          Default value is False (return multiple replacements)
        - replacementConnectionPoint: (optional) index of the atom in the replacement that
          the bond should be made to.
    
      RETURNS: a tuple of new molecules with the substructures replaced removed
    
      NOTES:
    
        - The original molecule is *not* modified.
    
      EXAMPLES:
    
       The following examples substitute SMILES/SMARTS strings for molecules, you'd have
       to actually use molecules:
    
        - ReplaceSubstructs('CCOC','OC','NC') -> ('CCNC',)
    
        - ReplaceSubstructs('COCCOC','OC','NC') -> ('COCCNC','CNCCOC')
    
        - ReplaceSubstructs('COCCOC','OC','NC',True) -> ('CNCCNC',)
    
        - ReplaceSubstructs('COCCOC','OC','CN',True,1) -> ('CNCCNC',)
    
    

    C++ signature :
        _object* ReplaceSubstructs(RDKit::ROMol,RDKit::ROMol,RDKit::ROMol [,bool=False [,unsigned int=0]])

SanitizeMol(...)

 

SanitizeMol( (Mol)mol [, (int)sanitizeOps=rdkit.Chem.rdmolops.SanitizeFlags.SANITIZE_ALL [, (bool)catchErrors=False]]) -> SanitizeFlags :
    Kekulize, check valencies, set aromaticity, conjugation and hybridization
    
        - The molecule is modified in place.
    
        - If sanitization fails, an exception will be thrown unless catchErrors is set
    
      ARGUMENTS:
    
        - mol: the molecule to be modified
        - sanitizeOps: (optional) sanitization operations to be carried out
                       these should be constructed by or'ing together the
                       operations in rdkit.Chem.SanitizeFlags
        - catchErrors: (optional) if provided, instead of raising an exception
                       when sanitization fails (the default behavior), the 
                       first operation that failed (as defined in rdkit.Chem.SanitizeFlags)
                       is returned. Zero is returned on success.
    
    

    C++ signature :
        RDKit::MolOps::SanitizeFlags SanitizeMol(RDKit::ROMol {lvalue} [,unsigned int=rdkit.Chem.rdmolops.SanitizeFlags.SANITIZE_ALL [,bool=False]])

SetAromaticity(...)

 

SetAromaticity( (Mol)mol) -> None :
    does aromaticity perception
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
      NOTES:
    
        - The molecule is modified in place.
    
    

    C++ signature :
        void SetAromaticity(RDKit::ROMol {lvalue})

SetConjugation(...)

 

SetConjugation( (Mol)mol) -> None :
    finds conjugated bonds
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
      NOTES:
    
        - The molecule is modified in place.
    
    

    C++ signature :
        void SetConjugation(RDKit::ROMol {lvalue})

SetHybridization(...)

 

SetHybridization( (Mol)mol) -> None :
    Assigns hybridization states to atoms
    
      ARGUMENTS:
    
        - mol: the molecule to use
    
      NOTES:
    
        - The molecule is modified in place.
    
    

    C++ signature :
        void SetHybridization(RDKit::ROMol {lvalue})

SplitMolByPDBChainId(...)

 

SplitMolByPDBChainId( (Mol)mol [, (AtomPairsParameters)whiteList=None [, (bool)negateList=False]]) -> dict :
    Splits a molecule into pieces based on PDB chain information.
    
      ARGUMENTS:
    
        - mol: the molecule to use
        - whiteList: only residues in this list will be returned
        - negateList: if set, negates the white list inclusion logic
    
      RETURNS: a dictionary keyed by chain id with molecules as the values
    
    

    C++ signature :
        boost::python::dict SplitMolByPDBChainId(RDKit::ROMol [,boost::python::api::object=None [,bool=False]])

SplitMolByPDBResidues(...)

 

SplitMolByPDBResidues( (Mol)mol [, (AtomPairsParameters)whiteList=None [, (bool)negateList=False]]) -> dict :
    Splits a molecule into pieces based on PDB residue information.
    
      ARGUMENTS:
    
        - mol: the molecule to use
        - whiteList: only residues in this list will be returned
        - negateList: if set, negates the white list inclusion logic
    
      RETURNS: a dictionary keyed by residue name with molecules as the values
    
    

    C++ signature :
        boost::python::dict SplitMolByPDBResidues(RDKit::ROMol [,boost::python::api::object=None [,bool=False]])

WedgeMolBonds(...)

 

WedgeMolBonds( (Mol)arg1, (Conformer)arg2) -> None :
    Set the wedging on single bonds in a molecule.
        The wedging scheme used is that from Mol files.
     
      ARGUMENTS:
    
        - molecule: the molecule to update
     
    
    

    C++ signature :
        void WedgeMolBonds(RDKit::ROMol {lvalue},RDKit::Conformer const*)