XML DOM handler for MzIdentMLFile. More...

#include <OpenMS/FORMAT/HANDLERS/MzIdentMLDOMHandler.h>

Collaboration diagram for MzIdentMLDOMHandler:

Classes
struct	AnalysisSoftware
	Struct to hold the used analysis software for that file. More...

struct	DatabaseInput
	Struct to hold the information from the DatabaseInput xml tag. More...

struct	DBSequence
	Struct to hold the information from the DBSequence xml tag. More...

struct	ModificationParam
	Struct to hold the information from the ModificationParam xml tag. More...

struct	PeptideEvidence
	Struct to hold the PeptideEvidence information. More...

struct	SpectrumIdentification
	Struct to hold the information from the SpectrumIdentification xml tag. More...

struct	SpectrumIdentificationProtocol
	Struct to hold the information from the SpectrumIdentificationProtocol xml tag. More...

Constructors and destructor
const ProgressLogger &	logger_
	Progress logger. More...

ControlledVocabulary	cv_
	Controlled vocabulary (psi-ms from OpenMS/share/OpenMS/CV/psi-ms.obo) More...

ControlledVocabulary	unimod_
	Controlled vocabulary for modifications (unimod from OpenMS/share/OpenMS/CV/unimod.obo) More...

std::vector< ProteinIdentification > *	pro_id_
	Internal +w Identification Item for proteins. More...

std::vector< PeptideIdentification > *	pep_id_
	Internal +w Identification Item for peptides. More...

const std::vector< ProteinIdentification > *	cpro_id_
	Internal -w Identification Item for proteins. More...

const std::vector< PeptideIdentification > *	cpep_id_
	Internal -w Identification Item for peptides. More...

const String	schema_version_
	Internal version keeping. More...

	MzIdentMLDOMHandler (const std::vector< ProteinIdentification > &pro_id, const std::vector< PeptideIdentification > &pep_id, const String &version, const ProgressLogger &logger)
	Constructor for a write-only handler for internal identification structures. More...

	MzIdentMLDOMHandler (std::vector< ProteinIdentification > &pro_id, std::vector< PeptideIdentification > &pep_id, const String &version, const ProgressLogger &logger)
	Constructor for a read-only handler for internal identification structures. More...

virtual	~MzIdentMLDOMHandler ()
	Destructor. More...

void	readMzIdentMLFile (const std::string &mzid_file)
	Provides the functionality of reading a mzid with a handler object. More...

void	writeMzIdentMLFile (const std::string &mzid_file)
	Provides the functionality to write a mzid with a handler object. More...

ControlledVocabulary::CVTerm	getChildWithName_ (const String &parent_accession, const String &name) const
	Looks up a child CV term of `parent_accession` with the name `name`. If no such term is found, an empty term is returned. More...

Helper functions to build the internal id structures from the DOM tree
std::pair< CVTermList, std::map< String, DataValue > >	parseParamGroup_ (xercesc::DOMNodeList *paramGroup)

CVTerm	parseCvParam_ (xercesc::DOMElement *param)

std::pair< String, DataValue >	parseUserParam_ (xercesc::DOMElement *param)

void	parseAnalysisSoftwareList_ (xercesc::DOMNodeList *analysisSoftwareElements)

void	parseDBSequenceElements_ (xercesc::DOMNodeList *dbSequenceElements)

void	parsePeptideElements_ (xercesc::DOMNodeList *peptideElements)

AASequence	parsePeptideSiblings_ (xercesc::DOMElement *peptide)

void	parsePeptideEvidenceElements_ (xercesc::DOMNodeList *peptideEvidenceElements)

void	parseSpectrumIdentificationElements_ (xercesc::DOMNodeList *spectrumIdentificationElements)

void	parseSpectrumIdentificationProtocolElements_ (xercesc::DOMNodeList *spectrumIdentificationProtocolElements)

void	parseInputElements_ (xercesc::DOMNodeList *inputElements)

void	parseSpectrumIdentificationListElements_ (xercesc::DOMNodeList *spectrumIdentificationListElements)

void	parseSpectrumIdentificationItemSetXLMS (std::set< String >::const_iterator set_it, std::multimap< String, int > xl_val_map, xercesc::DOMElement *element_res, String spectrumID)

void	parseSpectrumIdentificationItemElement_ (xercesc::DOMElement *spectrumIdentificationItemElement, PeptideIdentification &spectrum_identification, String &spectrumIdentificationList_ref)

void	parseProteinDetectionHypothesisElement_ (xercesc::DOMElement *proteinDetectionHypothesisElement, ProteinIdentification &protein_identification)

void	parseProteinAmbiguityGroupElement_ (xercesc::DOMElement *proteinAmbiguityGroupElement, ProteinIdentification &protein_identification)

void	parseProteinDetectionListElements_ (xercesc::DOMNodeList *proteinDetectionListElements)

static ProteinIdentification::SearchParameters	findSearchParameters_ (std::pair< CVTermList, std::map< String, DataValue > > as_params)

Helper functions to build a DOM tree from the internal id structures
XMLCh *	xml_root_tag_ptr_

XMLCh *	xml_cvparam_tag_ptr_

XMLCh *	xml_name_attr_ptr_

xercesc::XercesDOMParser	mzid_parser_

String	search_engine_

String	search_engine_version_

std::map< String, AnalysisSoftware >	as_map_
	mapping AnalysisSoftware id -> AnalysisSoftware More...

std::map< String, String >	sr_map_
	mapping sourcefile id -> sourcefile location More...

std::map< String, String >	sd_map_
	mapping spectradata id -> spectradata location More...

std::map< String, DatabaseInput >	db_map_
	mapping database id -> DatabaseInput More...

std::map< String, SpectrumIdentification >	si_map_
	mapping SpectrumIdentification id -> SpectrumIdentification (id refs) More...

std::map< String, size_t >	si_pro_map_
	mapping SpectrumIdentificationList id -> index to ProteinIdentification in pro_id_ More...

std::map< String, SpectrumIdentificationProtocol >	sp_map_
	mapping SpectrumIdentificationProtocol id -> SpectrumIdentificationProtocol More...

std::map< String, AASequence >	pep_map_
	mapping Peptide id -> Sequence More...

std::map< String, PeptideEvidence >	pe_ev_map_
	mapping PeptideEvidence id -> PeptideEvidence More...

std::map< String, String >	pv_db_map_
	mapping PeptideEvidence id -> DBSequence id More...

std::multimap< String, String >	p_pv_map_
	mapping Peptide id -> PeptideEvidence id, multiple PeptideEvidences can have equivalent Peptides. More...

std::map< String, DBSequence >	db_sq_map_
	mapping DBSequence id -> Sequence More...

std::list< std::list< String > >	hit_pev_
	writing help only More...

bool	xl_ms_search_
	is true when reading a file containing Cross-Linking MS search results More...

std::map< String, String >	xl_id_donor_map_
	mapping Peptide id -> cross-link donor value More...

std::map< String, String >	xl_id_acceptor_map_
	mapping peptide id of acceptor peptide -> cross-link acceptor value More...

std::map< String, SignedSize >	xl_donor_pos_map_
	mapping donor value -> cross-link modification location More...

std::map< String, SignedSize >	xl_acceptor_pos_map_
	mapping acceptor value -> cross-link modification location More...

std::map< String, double >	xl_mass_map_
	mapping Peptide id -> cross-link mass More...

std::map< String, String >	xl_mod_map_
	mapping peptide id -> cross-linking reagent name More...

void	buildCvList_ (xercesc::DOMElement *cvElements)

void	buildAnalysisSoftwareList_ (xercesc::DOMElement *analysisSoftwareElements)

void	buildSequenceCollection_ (xercesc::DOMElement *sequenceCollectionElements)

void	buildAnalysisCollection_ (xercesc::DOMElement *analysisCollectionElements)

void	buildAnalysisProtocolCollection_ (xercesc::DOMElement *protocolElements)

void	buildInputDataCollection_ (xercesc::DOMElement *inputElements)

void	buildEnclosedCV_ (xercesc::DOMElement *parentElement, String encel, String acc, String name, String cvref)

void	buildAnalysisDataCollection_ (xercesc::DOMElement *analysisElements)

	MzIdentMLDOMHandler ()

	MzIdentMLDOMHandler (const MzIdentMLDOMHandler &rhs)

MzIdentMLDOMHandler &	operator= (const MzIdentMLDOMHandler &rhs)

Detailed Description

XML DOM handler for MzIdentMLFile.

In read-mode, this class will parse an MzIdentML XML file and append the input identifications to the provided PeptideIdentifications and ProteinIdentifications.

Note: Do not use this class. It is only needed in MzIdentMLFile.; DOM and STREAM handler for MzIdentML have the same interface for legacy id structures.; Only upon destruction of this class it can be guaranteed that all data has been appended to the appropriate containers. Do not try to access the data before that.

Class Documentation

◆ OpenMS::Internal::MzIdentMLDOMHandler::AnalysisSoftware

struct OpenMS::Internal::MzIdentMLDOMHandler::AnalysisSoftware

Struct to hold the used analysis software for that file.

Collaboration diagram for MzIdentMLDOMHandler::AnalysisSoftware:

[legend]

Class Members
String	name
String	version

◆ OpenMS::Internal::MzIdentMLDOMHandler::DatabaseInput

struct OpenMS::Internal::MzIdentMLDOMHandler::DatabaseInput

Struct to hold the information from the DatabaseInput xml tag.

Collaboration diagram for MzIdentMLDOMHandler::DatabaseInput:

[legend]

Class Members
DateTime	date
String	location
String	name
String	version

◆ OpenMS::Internal::MzIdentMLDOMHandler::DBSequence

struct OpenMS::Internal::MzIdentMLDOMHandler::DBSequence

Struct to hold the information from the DBSequence xml tag.

Collaboration diagram for MzIdentMLDOMHandler::DBSequence:

[legend]

Class Members
String	accession
CVTermList	cvs
String	database_ref
String	sequence

◆ OpenMS::Internal::MzIdentMLDOMHandler::ModificationParam

struct OpenMS::Internal::MzIdentMLDOMHandler::ModificationParam

Struct to hold the information from the ModificationParam xml tag.

Collaboration diagram for MzIdentMLDOMHandler::ModificationParam:

[legend]

Class Members
String	fixed_mod
long double	mass_delta
CVTermList	modification_param_cvs
String	residues
CVTermList	specificities

◆ OpenMS::Internal::MzIdentMLDOMHandler::PeptideEvidence

struct OpenMS::Internal::MzIdentMLDOMHandler::PeptideEvidence

Struct to hold the PeptideEvidence information.

Collaboration diagram for MzIdentMLDOMHandler::PeptideEvidence:

[legend]

Class Members
bool	idec
char	post
char	pre
int	start
int	stop

◆ OpenMS::Internal::MzIdentMLDOMHandler::SpectrumIdentification

struct OpenMS::Internal::MzIdentMLDOMHandler::SpectrumIdentification

Struct to hold the information from the SpectrumIdentification xml tag.

Collaboration diagram for MzIdentMLDOMHandler::SpectrumIdentification:

[legend]

Class Members
String	search_database_ref
String	spectra_data_ref
String	spectrum_identification_list_ref
String	spectrum_identification_protocol_ref

◆ OpenMS::Internal::MzIdentMLDOMHandler::SpectrumIdentificationProtocol

struct OpenMS::Internal::MzIdentMLDOMHandler::SpectrumIdentificationProtocol

Struct to hold the information from the SpectrumIdentificationProtocol xml tag.

Collaboration diagram for MzIdentMLDOMHandler::SpectrumIdentificationProtocol:

[legend]

Class Members
String	enzyme
long double	fragment_tolerance
CVTermList	modification_parameter
CVTermList	parameter_cvs
map< String, DataValue >	parameter_ups
long double	precursor_tolerance
CVTerm	searchtype
CVTermList	threshold_cvs
map< String, DataValue >	threshold_ups

Constructor & Destructor Documentation

◆ MzIdentMLDOMHandler() [1/4]

MzIdentMLDOMHandler	(	const std::vector< ProteinIdentification > &	pro_id,
		const std::vector< PeptideIdentification > &	pep_id,
		const String &	version,
		const ProgressLogger &	logger
	)

Constructor for a write-only handler for internal identification structures.

◆ MzIdentMLDOMHandler() [2/4]

MzIdentMLDOMHandler	(	std::vector< ProteinIdentification > &	pro_id,
		std::vector< PeptideIdentification > &	pep_id,
		const String &	version,
		const ProgressLogger &	logger
	)

Constructor for a read-only handler for internal identification structures.

◆ ~MzIdentMLDOMHandler()

virtual ~MzIdentMLDOMHandler ( )

virtual

Destructor.

◆ MzIdentMLDOMHandler() [3/4]

MzIdentMLDOMHandler ( )

private

◆ MzIdentMLDOMHandler() [4/4]

MzIdentMLDOMHandler ( const MzIdentMLDOMHandler & rhs )

private

Member Function Documentation

◆ buildAnalysisCollection_()

void buildAnalysisCollection_ ( xercesc::DOMElement * analysisCollectionElements )

protected

◆ buildAnalysisDataCollection_()

void buildAnalysisDataCollection_ ( xercesc::DOMElement * analysisElements )

protected

◆ buildAnalysisProtocolCollection_()

void buildAnalysisProtocolCollection_ ( xercesc::DOMElement * protocolElements )

protected

◆ buildAnalysisSoftwareList_()

void buildAnalysisSoftwareList_ ( xercesc::DOMElement * analysisSoftwareElements )

protected

◆ buildCvList_()

void buildCvList_ ( xercesc::DOMElement * cvElements )

protected

◆ buildEnclosedCV_()

void buildEnclosedCV_	(	xercesc::DOMElement *	parentElement,
		String	encel,
		String	acc,
		String	name,
		String	cvref
	)

protected

◆ buildInputDataCollection_()

void buildInputDataCollection_ ( xercesc::DOMElement * inputElements )

protected

◆ buildSequenceCollection_()

void buildSequenceCollection_ ( xercesc::DOMElement * sequenceCollectionElements )

protected

◆ findSearchParameters_()

static ProteinIdentification::SearchParameters findSearchParameters_ ( std::pair< CVTermList, std::map< String, DataValue > > as_params )

staticprotected

◆ getChildWithName_()

ControlledVocabulary::CVTerm getChildWithName_	(	const String &	parent_accession,
		const String &	name
	)		const

protected

Looks up a child CV term of parent_accession with the name name. If no such term is found, an empty term is returned.

◆ operator=()

MzIdentMLDOMHandler& operator= ( const MzIdentMLDOMHandler & rhs )

private

◆ parseAnalysisSoftwareList_()

void parseAnalysisSoftwareList_ ( xercesc::DOMNodeList * analysisSoftwareElements )

protected

◆ parseCvParam_()

CVTerm parseCvParam_ ( xercesc::DOMElement * param )

protected

◆ parseDBSequenceElements_()

void parseDBSequenceElements_ ( xercesc::DOMNodeList * dbSequenceElements )

protected

◆ parseInputElements_()

void parseInputElements_ ( xercesc::DOMNodeList * inputElements )

protected

◆ parseParamGroup_()

std::pair<CVTermList, std::map<String, DataValue> > parseParamGroup_ ( xercesc::DOMNodeList * paramGroup )

protected

◆ parsePeptideElements_()

void parsePeptideElements_ ( xercesc::DOMNodeList * peptideElements )

protected

◆ parsePeptideEvidenceElements_()

void parsePeptideEvidenceElements_ ( xercesc::DOMNodeList * peptideEvidenceElements )

protected

◆ parsePeptideSiblings_()

AASequence parsePeptideSiblings_ ( xercesc::DOMElement * peptide )

protected

◆ parseProteinAmbiguityGroupElement_()

void parseProteinAmbiguityGroupElement_	(	xercesc::DOMElement *	proteinAmbiguityGroupElement,
		ProteinIdentification &	protein_identification
	)

protected

◆ parseProteinDetectionHypothesisElement_()

void parseProteinDetectionHypothesisElement_	(	xercesc::DOMElement *	proteinDetectionHypothesisElement,
		ProteinIdentification &	protein_identification
	)

protected

◆ parseProteinDetectionListElements_()

void parseProteinDetectionListElements_ ( xercesc::DOMNodeList * proteinDetectionListElements )

protected

◆ parseSpectrumIdentificationElements_()

void parseSpectrumIdentificationElements_ ( xercesc::DOMNodeList * spectrumIdentificationElements )

protected

◆ parseSpectrumIdentificationItemElement_()

void parseSpectrumIdentificationItemElement_	(	xercesc::DOMElement *	spectrumIdentificationItemElement,
		PeptideIdentification &	spectrum_identification,
		String &	spectrumIdentificationList_ref
	)

protected

◆ parseSpectrumIdentificationItemSetXLMS()

void parseSpectrumIdentificationItemSetXLMS	(	std::set< String >::const_iterator	set_it,
		std::multimap< String, int >	xl_val_map,
		xercesc::DOMElement *	element_res,
		String	spectrumID
	)

protected

◆ parseSpectrumIdentificationListElements_()

void parseSpectrumIdentificationListElements_ ( xercesc::DOMNodeList * spectrumIdentificationListElements )

protected

◆ parseSpectrumIdentificationProtocolElements_()

void parseSpectrumIdentificationProtocolElements_ ( xercesc::DOMNodeList * spectrumIdentificationProtocolElements )

protected

◆ parseUserParam_()

std::pair<String, DataValue> parseUserParam_ ( xercesc::DOMElement * param )

protected

◆ readMzIdentMLFile()

void readMzIdentMLFile ( const std::string & mzid_file )

Provides the functionality of reading a mzid with a handler object.

◆ writeMzIdentMLFile()

void writeMzIdentMLFile ( const std::string & mzid_file )

Provides the functionality to write a mzid with a handler object.

Member Data Documentation

◆ as_map_

std::map<String, AnalysisSoftware> as_map_

private

mapping AnalysisSoftware id -> AnalysisSoftware

◆ cpep_id_

const std::vector<PeptideIdentification>* cpep_id_

protected

Internal -w Identification Item for peptides.

◆ cpro_id_

const std::vector<ProteinIdentification>* cpro_id_

protected

Internal -w Identification Item for proteins.

◆ cv_

ControlledVocabulary cv_

protected

Controlled vocabulary (psi-ms from OpenMS/share/OpenMS/CV/psi-ms.obo)

◆ db_map_

std::map<String, DatabaseInput> db_map_

private

mapping database id -> DatabaseInput

◆ db_sq_map_

std::map<String, DBSequence> db_sq_map_

private

mapping DBSequence id -> Sequence

◆ hit_pev_

std::list<std::list<String> > hit_pev_

private

writing help only

◆ logger_

const ProgressLogger& logger_

protected

Progress logger.

◆ mzid_parser_

xercesc::XercesDOMParser mzid_parser_

private

◆ p_pv_map_

std::multimap<String, String> p_pv_map_

private

mapping Peptide id -> PeptideEvidence id, multiple PeptideEvidences can have equivalent Peptides.

◆ pe_ev_map_

std::map<String, PeptideEvidence> pe_ev_map_

private

mapping PeptideEvidence id -> PeptideEvidence

◆ pep_id_

std::vector<PeptideIdentification>* pep_id_

protected

Internal +w Identification Item for peptides.

◆ pep_map_

std::map<String, AASequence> pep_map_

private

mapping Peptide id -> Sequence

◆ pro_id_

std::vector<ProteinIdentification>* pro_id_

protected

Internal +w Identification Item for proteins.

◆ pv_db_map_

std::map<String, String> pv_db_map_

private

mapping PeptideEvidence id -> DBSequence id

◆ schema_version_

const String schema_version_

protected

Internal version keeping.

◆ sd_map_

std::map<String, String> sd_map_

private

mapping spectradata id -> spectradata location

◆ search_engine_

String search_engine_

private

◆ search_engine_version_

String search_engine_version_

private

◆ si_map_

std::map<String, SpectrumIdentification> si_map_

private

mapping SpectrumIdentification id -> SpectrumIdentification (id refs)

◆ si_pro_map_

std::map<String, size_t> si_pro_map_

private

mapping SpectrumIdentificationList id -> index to ProteinIdentification in pro_id_

◆ sp_map_

std::map<String, SpectrumIdentificationProtocol> sp_map_

private

mapping SpectrumIdentificationProtocol id -> SpectrumIdentificationProtocol

◆ sr_map_

std::map<String, String> sr_map_

private

mapping sourcefile id -> sourcefile location

◆ unimod_

ControlledVocabulary unimod_

protected

Controlled vocabulary for modifications (unimod from OpenMS/share/OpenMS/CV/unimod.obo)

◆ xl_acceptor_pos_map_

std::map<String, SignedSize> xl_acceptor_pos_map_

private

mapping acceptor value -> cross-link modification location

◆ xl_donor_pos_map_

std::map<String, SignedSize> xl_donor_pos_map_

private

mapping donor value -> cross-link modification location

◆ xl_id_acceptor_map_

std::map<String, String> xl_id_acceptor_map_

private

mapping peptide id of acceptor peptide -> cross-link acceptor value

◆ xl_id_donor_map_

std::map<String, String> xl_id_donor_map_

private

mapping Peptide id -> cross-link donor value

◆ xl_mass_map_

std::map<String, double> xl_mass_map_

private

mapping Peptide id -> cross-link mass

◆ xl_mod_map_

std::map<String, String> xl_mod_map_

private

mapping peptide id -> cross-linking reagent name

◆ xl_ms_search_

bool xl_ms_search_

private

is true when reading a file containing Cross-Linking MS search results

◆ xml_cvparam_tag_ptr_

XMLCh* xml_cvparam_tag_ptr_

private

◆ xml_name_attr_ptr_

XMLCh* xml_name_attr_ptr_

private

◆ xml_root_tag_ptr_

XMLCh* xml_root_tag_ptr_

private

Classes

Constructors and destructor

Helper functions to build the internal id structures from the DOM tree

Helper functions to build a DOM tree from the internal id structures

Detailed Description

Class Documentation

◆ OpenMS::Internal::MzIdentMLDOMHandler::AnalysisSoftware

◆ OpenMS::Internal::MzIdentMLDOMHandler::DatabaseInput

◆ OpenMS::Internal::MzIdentMLDOMHandler::DBSequence

◆ OpenMS::Internal::MzIdentMLDOMHandler::ModificationParam

◆ OpenMS::Internal::MzIdentMLDOMHandler::PeptideEvidence

◆ OpenMS::Internal::MzIdentMLDOMHandler::SpectrumIdentification

◆ OpenMS::Internal::MzIdentMLDOMHandler::SpectrumIdentificationProtocol

Constructor & Destructor Documentation

◆ MzIdentMLDOMHandler() [1/4]

◆ MzIdentMLDOMHandler() [2/4]

◆ ~MzIdentMLDOMHandler()

◆ MzIdentMLDOMHandler() [3/4]

◆ MzIdentMLDOMHandler() [4/4]

Member Function Documentation

◆ buildAnalysisCollection_()

◆ buildAnalysisDataCollection_()

◆ buildAnalysisProtocolCollection_()

◆ buildAnalysisSoftwareList_()

◆ buildCvList_()

◆ buildEnclosedCV_()

◆ buildInputDataCollection_()

◆ buildSequenceCollection_()

◆ findSearchParameters_()

◆ getChildWithName_()

◆ operator=()

◆ parseAnalysisSoftwareList_()

◆ parseCvParam_()

◆ parseDBSequenceElements_()

◆ parseInputElements_()

◆ parseParamGroup_()

◆ parsePeptideElements_()

◆ parsePeptideEvidenceElements_()

◆ parsePeptideSiblings_()

◆ parseProteinAmbiguityGroupElement_()

◆ parseProteinDetectionHypothesisElement_()

◆ parseProteinDetectionListElements_()

◆ parseSpectrumIdentificationElements_()

◆ parseSpectrumIdentificationItemElement_()

◆ parseSpectrumIdentificationItemSetXLMS()

◆ parseSpectrumIdentificationListElements_()

◆ parseSpectrumIdentificationProtocolElements_()

◆ parseUserParam_()

◆ readMzIdentMLFile()

◆ writeMzIdentMLFile()

Member Data Documentation

◆ as_map_

◆ cpep_id_

◆ cpro_id_

◆ cv_

◆ db_map_

◆ db_sq_map_

◆ hit_pev_

◆ logger_

◆ mzid_parser_

◆ p_pv_map_

◆ pe_ev_map_

◆ pep_id_

◆ pep_map_

◆ pro_id_

◆ pv_db_map_

◆ schema_version_

◆ sd_map_

◆ search_engine_

◆ search_engine_version_

◆ si_map_

◆ si_pro_map_

◆ sp_map_

◆ sr_map_

◆ unimod_

◆ xl_acceptor_pos_map_

◆ xl_donor_pos_map_

◆ xl_id_acceptor_map_

◆ xl_id_donor_map_

◆ xl_mass_map_