Molecule to SMILES writer. More...

#include <SMILESwriter.hh>

Data Structures
class	NodeData

Public Member Functions
	SMILESwriter ()

Static Public Member Functions
static std::string	getSMILES (const Molecule &m, const bool ignoreProtons=true, const bool allowWildcard=false)

static std::string	getSMILES (const Molecule &m, const GroupMap &groups, const bool ignoreProtons, const bool allowWildcard=false)

Protected Types
typedef boost::graph_traits < Molecule > ::adjacency_iterator	MA_Iterator_t

typedef boost::property_map < Molecule, PropEdgeLabel > ::const_type	ME_Property_Map_t

typedef boost::graph_traits < Molecule >::edge_descriptor	MEdge_t

typedef boost::property_map < Molecule, PropNodeIndex > ::const_type	MV_Index_Map_t

typedef boost::graph_traits < Molecule >::vertex_iterator	MV_Iterator_t

typedef std::map< MVertex_t, NodeData >	MV_NodeData_Map

typedef boost::property_map < Molecule, PropNodeLabel > ::const_type	MV_Property_Map_t

typedef std::map< MVertex_t, bool >	MV_Visited_Map_t
	utility map type for DFS traversal of the Molecule graph More...

typedef boost::graph_traits < Molecule > ::vertex_descriptor	MVertex_t

Static Protected Member Functions
static std::string	build_dfs (MVertex_t v, MVertex_t p, const Molecule graph, std::vector< int > ranks, MV_Visited_Map_t &visit, const MV_NodeData_Map &nodeData, const MV_Index_Map_t &idx, const MV_Property_Map_t &vname, const ME_Property_Map_t &ename, const bool ignoreProtons)

static std::vector< int >	canonize (const Molecule graph, const MV_Visited_Map_t &visit, const MV_Index_Map_t &idx, const MV_Property_Map_t &vname, const ME_Property_Map_t &ename, MV_NodeData_Map &nodeData, const GroupMap const groups, const bool allowWildcard)

static std::string	getLabel (const std::string &label)

static std::string	getLabel (const std::string &label, const NodeData &nodeData, const bool ignoreProtons)

static std::string	getSMILES (const Molecule &m, const GroupMap *const groups, const bool ignoreProtons, const bool allowWildcard)

static std::set< std::string >	initOrganicSubset ()

static bool	isWithBracketsInSMILES (const std::string &atom)

static int	prime (int number)

static std::string	second_pass (std::string smiles)

Static Protected Attributes
static std::set< std::string >	organic_subset

static const int	primes []

static const int	primesLength

Detailed Description

    Utility class to generate a canonical SMILES string from a molecule
    graph representation. It expects atom (node) and edge (bond) label
    following the Daylight's SMILES description. See 
    ggl::chem::SMILES_grammar for further details.

    It implements the algorithm suggested by Weininger (1989)

    @article{ Weininger_1989,
     title={SMILES. 2. Algorithm for generation of unique SMILES notation},
     author={Weininger, D and Weininger, A and Weininger, J L},
     journal={Journal of Chemical Information and Modeling},
     volume={29},
     number={2},
     pages={97--101},
     year={1989},
     publisher={American Chemical Society},
     url={http://dx.doi.org/10.1021/ci00062a008}
    }

    NOTE : THIS WRITER IS INCOMPLETE, I.E. NOT ALL TYPES OF MOLECULE ATOMS
    AND BONDS ARE HANDLED BY THIS WRITER !!!

    Supported atom labels are defined by MoleculeUtil::getAtomData().

    Supported bond labels are defined by MoleculeUtil::getBondData().

Author: Alexander Ullrich (c) 2008; Martin Mann (c) 2008 http://www.bioinf.uni-freiburg.de/~mmann/

Definition at line 46 of file SMILESwriter.hh.

Member Typedef Documentation

typedef boost::graph_traits<Molecule>::adjacency_iterator ggl::chem::SMILESwriter::MA_Iterator_t

protected

Definition at line 55 of file SMILESwriter.hh.

typedef boost::property_map<Molecule, PropEdgeLabel>::const_type ggl::chem::SMILESwriter::ME_Property_Map_t

protected

Definition at line 60 of file SMILESwriter.hh.

typedef boost::graph_traits<Molecule>::edge_descriptor ggl::chem::SMILESwriter::MEdge_t

protected

Definition at line 52 of file SMILESwriter.hh.

typedef boost::property_map<Molecule, PropNodeIndex>::const_type ggl::chem::SMILESwriter::MV_Index_Map_t

protected

Definition at line 58 of file SMILESwriter.hh.

typedef boost::graph_traits<Molecule>::vertex_iterator ggl::chem::SMILESwriter::MV_Iterator_t

protected

Definition at line 54 of file SMILESwriter.hh.

typedef std::map<MVertex_t, NodeData> ggl::chem::SMILESwriter::MV_NodeData_Map

protected

Definition at line 106 of file SMILESwriter.hh.

typedef boost::property_map<Molecule, PropNodeLabel>::const_type ggl::chem::SMILESwriter::MV_Property_Map_t

protected

Definition at line 59 of file SMILESwriter.hh.

typedef std::map<MVertex_t, bool> ggl::chem::SMILESwriter::MV_Visited_Map_t

protected

Definition at line 63 of file SMILESwriter.hh.

typedef boost::graph_traits<Molecule>::vertex_descriptor ggl::chem::SMILESwriter::MVertex_t

protected

Definition at line 51 of file SMILESwriter.hh.

Constructor & Destructor Documentation

ggl::chem::SMILESwriter::SMILESwriter ( )

Member Function Documentation

static std::string ggl::chem::SMILESwriter::build_dfs	(	MVertex_t	v,
		MVertex_t	p,
		const Molecule *	graph,
		std::vector< int > *	ranks,
		MV_Visited_Map_t &	visit,
		const MV_NodeData_Map &	nodeData,
		const MV_Index_Map_t &	idx,
		const MV_Property_Map_t &	vname,
		const ME_Property_Map_t &	ename,
		const bool	ignoreProtons
	)

staticprotected

static std::vector<int> ggl::chem::SMILESwriter::canonize	(	const Molecule *	graph,
		const MV_Visited_Map_t &	visit,
		const MV_Index_Map_t &	idx,
		const MV_Property_Map_t &	vname,
		const ME_Property_Map_t &	ename,
		MV_NodeData_Map &	nodeData,
		const GroupMap *const	groups,
		const bool	allowWildcard
	)

staticprotected

static std::string ggl::chem::SMILESwriter::getLabel ( const std::string & label )

staticprotected

Produces a SMILES conform label of the given atom label, ie. enclosing brackets are added if needed.

Parameters

label the atom label to check

Returns: the SMILES conform atom label

static std::string ggl::chem::SMILESwriter::getLabel	(	const std::string &	label,
		const NodeData &	nodeData,
		const bool	ignoreProtons
	)

staticprotected

Produces a SMILES conform label of the given atom label, ie. enclosing brackets are added if needed. Furthermore, protons can be removed from the SMILES if their number can be deduced from atom and bond valence.

Parameters

label	the atom label to check
nodeData	the atom information for this atom
ignoreProtons	whether or not protons should be removed from the atom label if possible

Returns: the SMILES conform atom label

static std::string ggl::chem::SMILESwriter::getSMILES	(	const Molecule &	m,
		const bool	ignoreProtons = `true`,
		const bool	allowWildcard = `false`
	)

static

Generates a canonical SMILES string of the given graph representation of a molecule.

NOTE: THE FUNCTIONALITY IS INCOMPLETE, i.e. not all atom and bond types are possible! See class description!

Parameters

m	the molecule graph to parse
ignoreProtons	if true and m is no HH molecule, all protons that can be inferred from atom and bond valence are ignored when producing the SMILES string; otherwise protons are compressed into the adjacent non-proton atom label
allowWildcard	whether or not the wildcard is a valid atom label within SMILES. NOTE: this will result in non-standard SMILES since the wildcard label is a non-standard extension within the GGL!

Returns: a canonical SMILES string representing the given molecule

Exceptions

std::runtime_error if unsupported atom or bond labels are encountered

static std::string ggl::chem::SMILESwriter::getSMILES	(	const Molecule &	m,
		const GroupMap &	groups,
		const bool	ignoreProtons,
		const bool	allowWildcard = `false`
	)

static

Generates a canonical SMILES string of the given graph representation of a molecule.

Before this is done, all known groups are compressed into their according group labels using MoleculeUtil::compressGroups(..).

NOTE: THE FUNCTIONALITY IS INCOMPLETE, i.e. not all atom and bond types are possible! See class description!

Parameters

m	the molecule graph to parse
groups	a container that holds group IDs where each matching node represents the according subgraph
ignoreProtons	if true and m is no HH molecule, all protons that can be inferred from atom and bond valence are ignored when producing the SMILES string; otherwise protons are compressed into the adjacent non-proton atom label
allowWildcard	whether or not the wildcard is a valid atom label within SMILES. NOTE: this will result in non-standard SMILES since the wildcard label is a non-standard extension within the GGL!

Returns: a canonical SMILES string representing the given molecule

static std::string ggl::chem::SMILESwriter::getSMILES	(	const Molecule &	m,
		const GroupMap *const	groups,
		const bool	ignoreProtons,
		const bool	allowWildcard
	)

staticprotected

Generates a canonical SMILES string of the given graph representation of a molecule.

NOTE: THE FUNCTIONALITY IS INCOMPLETE, i.e. not all atom and bond types are possible! See class description!

Parameters

m	the molecule graph to parse
groups	a container that holds group IDs where each matching node represents the according subgraph; can be NULL if no groups are to be considered
ignoreProtons	if true and m is no HH molecule, all protons that can be inferred from atom and bond valence are ignored when producing the SMILES string; otherwise protons are compressed into the adjacent non-proton atom label
allowWildcard	whether or not the wildcard is a valid atom label within SMILES. NOTE: this will result in non-standard SMILES since the wildcard label is a non-standard extension within the GGL!

Returns: a canonical SMILES string representing the given molecule

static std::set<std::string> ggl::chem::SMILESwriter::initOrganicSubset ( )

staticprotected

static bool ggl::chem::SMILESwriter::isWithBracketsInSMILES ( const std::string & atom )

staticprotected

Checks whether or not an atom identifier has to be enclosed in brackets within the SMILES notation or not.

Parameters

atom	the atom label without enclosing brackets

Returns: true, if the atom label has to be enclosed with brackets; false otherwise.

static int ggl::chem::SMILESwriter::prime ( int number )

staticprotected

static std::string ggl::chem::SMILESwriter::second_pass ( std::string smiles )

staticprotected

Field Documentation

std::set<std::string> ggl::chem::SMILESwriter::organic_subset

staticprotected

Definition at line 108 of file SMILESwriter.hh.

const int ggl::chem::SMILESwriter::primes[]

staticprotected

Definition at line 201 of file SMILESwriter.hh.

const int ggl::chem::SMILESwriter::primesLength

staticprotected

Definition at line 204 of file SMILESwriter.hh.

The documentation for this class was generated from the following file:

src/ggl/chem/SMILESwriter.hh

Data Structures

Public Member Functions

Static Public Member Functions

Protected Types

Static Protected Member Functions

Static Protected Attributes

Detailed Description

Member Typedef Documentation

Constructor & Destructor Documentation

Member Function Documentation

Field Documentation