Molecule utility factory. More...

#include <MoleculeUtil.hh>

Data Structures
class	AtomLabelData

class	BondLabelData

Public Types
typedef std::map< std::string, std::string >	AromaticSwapMap

typedef std::map< std::string, AtomLabelData >	AtomDataMap

typedef std::map< std::string, BondLabelData >	BondDataMap

typedef unsigned char	OneByte
	typedef to represent one byte of information More...

Public Member Functions
	MoleculeUtil ()
	Default construction. More...

virtual	~MoleculeUtil ()
	Default destruction. More...

Static Public Member Functions
static void	compressGroups (ggl::chem::Molecule &mol, const GroupMap &groups)

static void	compressHnodes (Molecule &mol)

static std::string	convertCML (const Molecule &mol)

static std::ostream &	convertCML (const Molecule &mol, std::ostream &stream)

static void	copy (const Molecule &mol, Molecule &toFill)

static void	copy (const sgm::Graph_Interface &mol, Molecule &toFill)

static bool	decodeConsistencyStatus (const size_t consistencyCode, std::ostream &errorStream)

static void	fillProtons (Molecule &mol)

static const std::string *const	getAromaticPendant (const std::string &label)

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

static const AtomDataMap &	getAtomData (void)

static const AtomLabelData *const	getAtomData (const std::string &label)

static const BondDataMap &	getBondData (void)

static const BondLabelData *const	getBondData (const std::string &label)

static int	getCharge (const std::string &label)

static int	getClass (const std::string &label)

static std::string	getComplexAtomLabel (const std::string &atom, const size_t protons=0, const int charge=0, const int classID=0, const bool explicitChargeValue=false)

static std::string	getGroupLabel (const std::string &nodeLabel)

static size_t	getProtons (const std::string &label)

static size_t	getProtonsToAdd (const std::string &atomLabel, const int atomCharge, const size_t bondValenceSum, const size_t bondNum, const size_t bondNumAromatic, const size_t bondNumProton)

static void	insertGroups (ggl::chem::Molecule &mol, const GroupMap &groups) throw (std::runtime_error)

static size_t	isConsistent (const Molecule &mol)

static bool	isGroupLabel (const std::string &nodeLabel)

static bool	isValidAtomLabel (const std::string &atomLabel)

static bool	isValidBondLabel (const std::string &bondLabel)

static void	removeProtons (Molecule &mol)

Static Public Attributes
static const std::string	AtomLabelWildcard

static const size_t	C_AtomComplexWithH

static const size_t	C_AtomLabelInvalid

static const size_t	C_AtomLabelWildcard

static const size_t	C_AtomValence

static const size_t	C_BondLabelInvalid

static const size_t	C_BondLoop

static const size_t	C_Consistent
	consistency code : everything fine More...

static const size_t	C_NonConnected

Static Protected Member Functions
static bool	checkAtomComplexWithH (const Molecule &mol)

static bool	checkAtomLabel (const Molecule &mol)

static bool	checkAtomLabelWildcard (const Molecule &mol)

static bool	checkAtomValence (const Molecule &mol)

static bool	checkBondLabel (const Molecule &mol)

static bool	checkBondLoop (const Molecule &mol)

static bool	checkNonConnected (const Molecule &mol)

Static Protected Attributes
static AromaticSwapMap	aromaticSwapMap
	maps aromatic labels onto their non-aromatic form and vice versa More...

static AtomDataMap	atomData
	the stored atom label to data mapping More...

static BondDataMap	bondData
	the stored bond label to data mapping More...

static const std::string	DIGIT
	holds all digits for string parsing More...

static const std::string	WHITESPACE
	holds all white space characters for string parsing More...

Detailed Description

    Utility class that contains certain data and members needed for
    Molecule evaluation and handling.

Author: Martin Mann (c) 2009 http://www.bioinf.uni-freiburg.de/~mmann/

Definition at line 54 of file MoleculeUtil.hh.

Member Typedef Documentation

typedef std::map< std::string, std::string > ggl::chem::MoleculeUtil::AromaticSwapMap

Mapping of aromatic labels to their non-aromatic form and vice versa, to enable a relabeling of aromatic rings.

Definition at line 164 of file MoleculeUtil.hh.

typedef std::map< std::string, AtomLabelData > ggl::chem::MoleculeUtil::AtomDataMap

Mapping of atom labels (in SMILES notation but without brackets) to the corresponding atom information like valence etc.

Definition at line 159 of file MoleculeUtil.hh.

typedef std::map< std::string, BondLabelData > ggl::chem::MoleculeUtil::BondDataMap

Mapping of bond labels (in SMILES notation) to the corresponding bond information like valence etc.

Definition at line 191 of file MoleculeUtil.hh.

typedef unsigned char ggl::chem::MoleculeUtil::OneByte

Definition at line 59 of file MoleculeUtil.hh.

Constructor & Destructor Documentation

ggl::chem::MoleculeUtil::MoleculeUtil ( )

virtual ggl::chem::MoleculeUtil::~MoleculeUtil ( )

virtual

Member Function Documentation

static bool ggl::chem::MoleculeUtil::checkAtomComplexWithH ( const Molecule & mol )

staticprotected

Checks if any complex node label contains implicit H atoms. This is currently not supported by the library

Parameters

mol	the molecule to check

Returns: true iff no atom label equals AtomLabelWildcard; false otherwise

static bool ggl::chem::MoleculeUtil::checkAtomLabel ( const Molecule & mol )

staticprotected

Checks if all node label of the given molecule are supported by the current SMILESwriter.

Parameters

mol	the molecule to check

Returns: true iff all node label are ok, false otherwise

static bool ggl::chem::MoleculeUtil::checkAtomLabelWildcard ( const Molecule & mol )

staticprotected

Checks if any node label is equal to AtomLabelWildcard. Since this is currently not supported the check returns false if any occurence is found.

Parameters

mol	the molecule to check

Returns: true iff no atom label equals AtomLabelWildcard; false otherwise

static bool ggl::chem::MoleculeUtil::checkAtomValence ( const Molecule & mol )

staticprotected

Checks if any atom shows an inconsistent electron distribution, ie. [valence+charge != bondValenceSum+aromAdd] where aromAdd == 1 if the atom is part of an aromatic ring and 0 otherwise.

Parameters

mol	the molecule to check

Returns: true iff no atom shows inconsistent electron distribution false otherwise

static bool ggl::chem::MoleculeUtil::checkBondLabel ( const Molecule & mol )

staticprotected

Checks if all bond label of the given molecule are supported by the current SMILESwriter.

Parameters

mol	the molecule to check

Returns: true iff all bond labels are ok; false otherwise

static bool ggl::chem::MoleculeUtil::checkBondLoop ( const Molecule & mol )

staticprotected

Checks if an atom forms a bond with itself, i.e. a ring bond.

Parameters

mol	the molecule to check

Returns: true iff all bond labels are ok; false otherwise

static bool ggl::chem::MoleculeUtil::checkNonConnected ( const Molecule & mol )

staticprotected

Checks if the molecule shows more than one connected component.

Parameters

mol	the molecule to check

Returns: true iff only the molecule is connected; false otherwise

static void ggl::chem::MoleculeUtil::compressGroups	(	ggl::chem::Molecule &	mol,
		const GroupMap &	groups
	)

static

Iteratively identifies groups within the molecule and replaces them by the according group label. The replacement is done in decreasing group size, ie. first the largest groups are compressed.

Parameters

mol	the molecule to alter
groups	the list of known groups to be introduced if found

static void ggl::chem::MoleculeUtil::compressHnodes ( Molecule & mol )

static

Compresses all explicitly represented "H" atoms into the adjacent atom label.

Note: only protons with atom node label "H" are compressed. Nodes e.g. including class information like "H:1" are maintained and not removed.

Parameters

mol	the molecule graph to compress

static std::string ggl::chem::MoleculeUtil::convertCML ( const Molecule & mol )

static

Converts a given molecule in Chemical Markup Language (CML) format.

See http://cml.sourceforge.net/ for further details on the format.

Parameters

mol	the molecule to represent

Returns: the CML string representation of the molecule

static std::ostream& ggl::chem::MoleculeUtil::convertCML	(	const Molecule &	mol,
		std::ostream &	stream
	)

static

Converts a given molecule in Chemical Markup Language (CML) format.

See http://cml.sourceforge.net/ for further details on the format.

Parameters

mol	the molecule to represent
stream	the out stream to add the CML representation to

Returns: the altered stream filled with the CML string representation of the molecule

static void ggl::chem::MoleculeUtil::copy	(	const Molecule &	mol,
		Molecule &	toFill
	)

static

Copies a given molecule into another molecule object which is overwritten.

Parameters

mol	the molecule graph to copy
toFill	the molecule graph to make a copy of mol

static void ggl::chem::MoleculeUtil::copy	(	const sgm::Graph_Interface &	mol,
		Molecule &	toFill
	)

static

Copies a given molecule into another molecule object which is overwritten.

Note, no sanity checks of node/edge labels, degrees, etc. are done!

Parameters

mol	the molecule graph to copy
toFill	the molecule graph to make a copy of mol

static bool ggl::chem::MoleculeUtil::decodeConsistencyStatus	(	const size_t	consistencyCode,
		std::ostream &	errorStream
	)

static

Writes a description of the consistency status or errors, encoded in a consistency code produced by isConsistent*(...), to a given outstream. The function returns whether or not an error occured.

Parameters

consistencyCode	the error code to parse, produced by a call to isConsistent*(...)
errorStream	the output stream to write the error description to

Returns: true if no error is encoded; false otherwise

static void ggl::chem::MoleculeUtil::fillProtons ( Molecule & mol )

static

Adds explicit "H" atoms according to the valence of atom nodes and protons within complex atom labels.

TODO: NOTE, this implementation is still experimental and is not necessarily correct!

Parameters

mol	the molecule graph to fill

static const std::string* const ggl::chem::MoleculeUtil::getAromaticPendant ( const std::string & label )

static

Access to the aromatic/non-aromatic pendant of an atom or edge label if it exists.

Parameters

label the label of interest

Returns: a pointer to the pendant label or NULL if none exists

static std::string ggl::chem::MoleculeUtil::getAtom ( const std::string & label )

static

Access to atom name within a given atom label.

Parameters

label the atom label to derive the information from

Returns: the name of the atom

static const AtomDataMap& ggl::chem::MoleculeUtil::getAtomData ( void )

static

Access to the currently supported atom labels and the corresponding atom information, e.g. valence etc.

Returns: the atom2data mapping

static const AtomLabelData* const ggl::chem::MoleculeUtil::getAtomData ( const std::string & label )

static

Access to atom information for the given atom label, if existing.

Parameters

label the atom label to derive the information from

Returns: the atom2data entry or NULL if none available

static const BondDataMap& ggl::chem::MoleculeUtil::getBondData ( void )

static

Access to the currently supported bond labels and the corresponding bond information, e.g. valence etc.

Returns: the bond2data mapping

static const BondLabelData* const ggl::chem::MoleculeUtil::getBondData ( const std::string & label )

static

Access to bond information for the given bond label, if existing.

Parameters

label the bond label to derive the information from

Returns: the bond2data entry or NULL if none available

static int ggl::chem::MoleculeUtil::getCharge ( const std::string & label )

static

Access to the charge within a given atom label, if existing.

Parameters

label the atom label to derive the information from

Returns: the charge information in the label

static int ggl::chem::MoleculeUtil::getClass ( const std::string & label )

static

Access to the class information within a given atom label, if existing.

Parameters

label the atom label to derive the information from

Returns: the class information in the label, or 0 if not present

static std::string ggl::chem::MoleculeUtil::getComplexAtomLabel	(	const std::string &	atom,
		const size_t	protons = `0`,
		const int	charge = `0`,
		const int	classID = `0`,
		const bool	explicitChargeValue = `false`
	)

static

Produces a complex atom label with the given information.

Parameters

atom	the atom label
protons	the number of protons attached to the atom; a value of 0 is ignored
charge	the charge of the atom; a value of 0 is ignored
classID	the classID; a value of 0 is ignored
explicitChargeValue	if true, a charge value of 1 is represented by "+1" rather than just "+"

Returns: the according complex atom label

static std::string ggl::chem::MoleculeUtil::getGroupLabel ( const std::string & nodeLabel )

static

Extracts the group identifier from the (complex) node label.

Parameters

nodeLabel the node label that contains a group label

Returns: the group label or an empty string if no group label is present

static size_t ggl::chem::MoleculeUtil::getProtons ( const std::string & label )

static

Access to number of protons within a given atom label, if existing.

Parameters

label the atom label to derive the information from

Returns: the number of additional protons in the label

static size_t ggl::chem::MoleculeUtil::getProtonsToAdd	(	const std::string &	atomLabel,
		const int	atomCharge,
		const size_t	bondValenceSum,
		const size_t	bondNum,
		const size_t	bondNumAromatic,
		const size_t	bondNumProton
	)

static

Computes the number of missing hydrogens to be added to this atom.

static void ggl::chem::MoleculeUtil::insertGroups	(	ggl::chem::Molecule &	mol,
		const GroupMap &	groups
	)		throw (std::runtime_error)

static

Replaces all nodes with group labels with the according molecule component if present in groups. If the group label is unknown, an exception is raised.

NOTE: The node replacement is NOT recursive to avoid infinite replacement chains.

Parameters

mol	the molecule to alter
groups	the list of known groups

std::runtime_error in case a group label is unknown

static size_t ggl::chem::MoleculeUtil::isConsistent ( const Molecule & mol )

static

Checks if a given ggl::chem::Molecule graph is consistent. If not, according error codes are returned.

Parameters

mol	the molecule graph to check

Returns: if consistent C_Consistent is returned. Otherwise a product of the according C_* values.

static bool ggl::chem::MoleculeUtil::isGroupLabel ( const std::string & nodeLabel )

static

Checks whether or not a given atom node label is a group label.

Parameters

nodeLabel the node label of interest

Returns: true if the given node label is a group label; false otherwise

static bool ggl::chem::MoleculeUtil::isValidAtomLabel ( const std::string & atomLabel )

static

Checks if the given atom (node) label is SMILES conform and currently supported, e.g. by the SMILESwriter class.

Parameters

atomLabel the label to check

Returns: true if the atom label is ok, false otherwise

static bool ggl::chem::MoleculeUtil::isValidBondLabel ( const std::string & bondLabel )

static

Checks if the given bond (edge) label is SMILES conform and currently supported, e.g. by the SMILESwriter class.

Parameters

bondLabel the label to check

Returns: true if the bond label is ok, false otherwise

static void ggl::chem::MoleculeUtil::removeProtons ( Molecule & mol )

static

Removes all represented "H" atoms that can be inferred from atom valence, charge and adjacent bond information. All other proton information that cannot be inferred is collapsed into accoring complex atom labels.

Thus, in the end, the molecule won't show adjacent protons if any.

Single protons or HH molecules are preserved as that.

Parameters

mol	the molecule graph to be stripped

Field Documentation

AromaticSwapMap ggl::chem::MoleculeUtil::aromaticSwapMap

staticprotected

Definition at line 569 of file MoleculeUtil.hh.

AtomDataMap ggl::chem::MoleculeUtil::atomData

staticprotected

Definition at line 566 of file MoleculeUtil.hh.

const std::string ggl::chem::MoleculeUtil::AtomLabelWildcard

static

the wildcard character for atom labels valid in molecule descriptions

Definition at line 63 of file MoleculeUtil.hh.

BondDataMap ggl::chem::MoleculeUtil::bondData

staticprotected

Definition at line 572 of file MoleculeUtil.hh.

const size_t ggl::chem::MoleculeUtil::C_AtomComplexWithH

static

consistency code : at least one atom label is complex and contains implicit H atoms, this is currently not supported

Definition at line 209 of file MoleculeUtil.hh.

const size_t ggl::chem::MoleculeUtil::C_AtomLabelInvalid

static

consistency code : at least one atom label is not SMILES conform or currently not supported within the library

Definition at line 200 of file MoleculeUtil.hh.

const size_t ggl::chem::MoleculeUtil::C_AtomLabelWildcard

static

consistency code : at least one atom label is a wildcard which is currently not supported within the library

Definition at line 206 of file MoleculeUtil.hh.

const size_t ggl::chem::MoleculeUtil::C_AtomValence

static

consistency code : at least one atom shows an inconsistent electron distribution, ie. valence+charge != protonCount

Definition at line 212 of file MoleculeUtil.hh.

const size_t ggl::chem::MoleculeUtil::C_BondLabelInvalid

static

consistency code : at least one bond label is not SMILES conform or currently not supported within the library

Definition at line 203 of file MoleculeUtil.hh.

const size_t ggl::chem::MoleculeUtil::C_BondLoop

static

consistency code : at least one bond connects the same atom, i.e. forms a loop

Definition at line 215 of file MoleculeUtil.hh.

const size_t ggl::chem::MoleculeUtil::C_Consistent

static

Definition at line 197 of file MoleculeUtil.hh.

const size_t ggl::chem::MoleculeUtil::C_NonConnected

static

consistency code : the molecule graph is not connected, i.e. contains at least two connected components

Definition at line 218 of file MoleculeUtil.hh.

const std::string ggl::chem::MoleculeUtil::DIGIT

staticprotected

Definition at line 561 of file MoleculeUtil.hh.

const std::string ggl::chem::MoleculeUtil::WHITESPACE

staticprotected

Definition at line 563 of file MoleculeUtil.hh.

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

src/ggl/chem/MoleculeUtil.hh

Data Structures

Public Types

Public Member Functions

Static Public Member Functions

Static Public Attributes

Static Protected Member Functions

Static Protected Attributes

Detailed Description

Member Typedef Documentation

Constructor & Destructor Documentation

Member Function Documentation

Field Documentation