Used to load and store PepXML files. More...

#include <OpenMS/FORMAT/PepXMLFile.h>

Inheritance diagram for PepXMLFile:

Classes
struct	AminoAcidModification

Public Member Functions
	PepXMLFile ()
	Constructor. More...

virtual	~PepXMLFile ()
	Destructor. More...

void	load (const String &filename, std::vector< ProteinIdentification > &proteins, std::vector< PeptideIdentification > &peptides, const String &experiment_name, const SpectrumMetaDataLookup &lookup)
	Loads peptide sequences with modifications out of a PepXML file. More...

void	load (const String &filename, std::vector< ProteinIdentification > &proteins, std::vector< PeptideIdentification > &peptides, const String &experiment_name="")
	load function with empty defaults for some parameters (see above) More...

void	store (const String &filename, std::vector< ProteinIdentification > &protein_ids, std::vector< PeptideIdentification > &peptide_ids, const String &mz_file="", const String &mz_name="", bool peptideprophet_analyzed=false)
	Stores idXML as PepXML file. More...

void	keepNativeSpectrumName (bool keep)
	Whether we should keep the native spectrum name of the pepXML. More...

Public Member Functions inherited from XMLFile
	XMLFile ()
	Default constructor. More...

	XMLFile (const String &schema_location, const String &version)
	Constructor that sets the schema location. More...

virtual	~XMLFile ()
	Destructor. More...

bool	isValid (const String &filename, std::ostream &os)
	Checks if a file validates against the XML schema. More...

const String &	getVersion () const
	return the version of the schema More...

Protected Member Functions
virtual void	endElement (const XMLCh const, const XMLCh const, const XMLCh *const qname)
	Docu in base class. More...

virtual void	startElement (const XMLCh const, const XMLCh const, const XMLCh *const qname, const xercesc::Attributes &attributes)
	Docu in base class. More...

Protected Member Functions inherited from XMLHandler
bool	equal_ (const XMLCh a, const XMLCh b) const
	Returns if two Xerces strings are equal. More...

void	writeUserParam_ (const String &tag_name, std::ostream &os, const MetaInfoInterface &meta, UInt indent) const
	Writes the content of MetaInfoInterface to the file. More...

Int	asInt_ (const String &in)
	Conversion of a String to an integer value. More...

Int	asInt_ (const XMLCh *in)
	Conversion of a Xerces string to an integer value. More...

UInt	asUInt_ (const String &in)
	Conversion of a String to an unsigned integer value. More...

double	asDouble_ (const String &in)
	Conversion of a String to a double value. More...

float	asFloat_ (const String &in)
	Conversion of a String to a float value. More...

bool	asBool_ (const String &in)
	Conversion of a string to a boolean value. More...

DateTime	asDateTime_ (String date_string)
	Conversion of a xs:datetime string to a DateTime value. More...

char *	attributeAsString_ (const xercesc::Attributes &a, const char *name) const
	Converts an attribute to a String. More...

Int	attributeAsInt_ (const xercesc::Attributes &a, const char *name) const
	Converts an attribute to a Int. More...

double	attributeAsDouble_ (const xercesc::Attributes &a, const char *name) const
	Converts an attribute to a double. More...

DoubleList	attributeAsDoubleList_ (const xercesc::Attributes &a, const char *name) const
	Converts an attribute to a DoubleList. More...

IntList	attributeAsIntList_ (const xercesc::Attributes &a, const char *name) const
	Converts an attribute to an IntList. More...

StringList	attributeAsStringList_ (const xercesc::Attributes &a, const char *name) const
	Converts an attribute to an StringList. More...

bool	optionalAttributeAsString_ (String &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the String value if the attribute is present. More...

bool	optionalAttributeAsInt_ (Int &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the Int value if the attribute is present. More...

bool	optionalAttributeAsUInt_ (UInt &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the UInt value if the attribute is present. More...

bool	optionalAttributeAsDouble_ (double &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the double value if the attribute is present. More...

bool	optionalAttributeAsDoubleList_ (DoubleList &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the DoubleList value if the attribute is present. More...

bool	optionalAttributeAsStringList_ (StringList &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the StringList value if the attribute is present. More...

bool	optionalAttributeAsIntList_ (IntList &value, const xercesc::Attributes &a, const char *name) const
	Assigns the attribute content to the IntList value if the attribute is present. More...

char *	attributeAsString_ (const xercesc::Attributes &a, const XMLCh *name) const
	Converts an attribute to a String. More...

Int	attributeAsInt_ (const xercesc::Attributes &a, const XMLCh *name) const
	Converts an attribute to a Int. More...

double	attributeAsDouble_ (const xercesc::Attributes &a, const XMLCh *name) const
	Converts an attribute to a double. More...

DoubleList	attributeAsDoubleList_ (const xercesc::Attributes &a, const XMLCh *name) const
	Converts an attribute to a DoubleList. More...

IntList	attributeAsIntList_ (const xercesc::Attributes &a, const XMLCh *name) const
	Converts an attribute to a IntList. More...

StringList	attributeAsStringList_ (const xercesc::Attributes &a, const XMLCh *name) const
	Converts an attribute to a StringList. More...

bool	optionalAttributeAsString_ (String &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the String value if the attribute is present. More...

bool	optionalAttributeAsInt_ (Int &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the Int value if the attribute is present. More...

bool	optionalAttributeAsUInt_ (UInt &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the UInt value if the attribute is present. More...

bool	optionalAttributeAsDouble_ (double &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the double value if the attribute is present. More...

bool	optionalAttributeAsDoubleList_ (DoubleList &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the DoubleList value if the attribute is present. More...

bool	optionalAttributeAsIntList_ (IntList &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the IntList value if the attribute is present. More...

bool	optionalAttributeAsStringList_ (StringList &value, const xercesc::Attributes &a, const XMLCh *name) const
	Assigns the attribute content to the StringList value if the attribute is present. More...

SignedSize	cvStringToEnum_ (const Size section, const String &term, const char *message, const SignedSize result_on_error=0)

	XMLHandler (const String &filename, const String &version)
	Default constructor. More...

virtual	~XMLHandler ()
	Destructor. More...

void	reset ()
	Release internal memory used for parsing (call. More...

void	fatalError (ActionMode mode, const String &msg, UInt line=0, UInt column=0) const
	Fatal error handler. Throws a ParseError exception. More...

void	error (ActionMode mode, const String &msg, UInt line=0, UInt column=0) const
	Error handler for recoverable errors. More...

void	warning (ActionMode mode, const String &msg, UInt line=0, UInt column=0) const
	Warning handler. More...

virtual void	characters (const XMLCh *const chars, const XMLSize_t length)
	Parsing method for character data. More...

virtual void	writeTo (std::ostream &)
	Writes the contents to a stream. More...

String	errorString ()
	Returns the last error description. More...

void	fatalError (const xercesc::SAXParseException &exception)

void	error (const xercesc::SAXParseException &exception)

void	warning (const xercesc::SAXParseException &exception)

Protected Member Functions inherited from XMLFile
void	parse_ (const String &filename, XMLHandler *handler)
	Parses the XML file given by `filename` using the handler given by `handler`. More...

void	save_ (const String &filename, XMLHandler *handler) const
	Stores the contents of the XML handler given by `handler` in the file given by `filename`. More...

void	enforceEncoding_ (const String &encoding)

	XMLFile ()
	Default constructor. More...

	XMLFile (const String &schema_location, const String &version)
	Constructor that sets the schema location. More...

virtual	~XMLFile ()
	Destructor. More...

bool	isValid (const String &filename, std::ostream &os)
	Checks if a file validates against the XML schema. More...

const String &	getVersion () const
	return the version of the schema More...

Private Member Functions
void	makeScanMap_ ()
	Fill `scan_map_`. More...

void	readRTMZCharge_ (const xercesc::Attributes &attributes)
	Read RT, m/z, charge information from attributes of "spectrum_query". More...

void	matchModification_ (const double mass, const String &origin, String &modification_description)
	find modification name given a modified AA mass More...

Private Attributes
std::vector< ProteinIdentification > *	proteins_
	Pointer to the list of identified proteins. More...

std::vector< PeptideIdentification > *	peptides_
	Pointer to the list of identified peptides. More...

const SpectrumMetaDataLookup *	lookup_
	Pointer to wrapper for looking up spectrum meta data. More...

String	exp_name_
	Name of the associated experiment (filename of the data file, extension will be removed) More...

String	search_engine_
	Set name of search engine. More...

String	native_spectrum_name_
	Several optional attributes of spectrum_query. More...

String	experiment_label_

String	swath_assay_

String	status_

bool	use_precursor_data_
	Get RT and m/z for peptide ID from precursor scan (should only matter for RT)? More...

std::map< Size, Size >	scan_map_
	Mapping between scan number in the pepXML file and index in the corresponding MSExperiment. More...

Element	hydrogen_
	Hydrogen data (for mass types) More...

bool	analysis_summary_
	Are we currently in an "analysis_summary" element (should be skipped)? More...

bool	keep_native_name_
	Whether we should keep the native spectrum name of the pepXML. More...

bool	search_score_summary_
	Are we currently in an "search_score_summary" element (should be skipped)? More...

bool	search_summary_
	Are we currently in an "search_summary" element (should be skipped)? More...

bool	wrong_experiment_
	Do current entries belong to the experiment of interest (for pepXML files that bundle results from different experiments)? More...

bool	seen_experiment_
	Have we seen the experiment of interest at all? More...

bool	checked_base_name_
	Have we checked the "base_name" attribute in the "msms_run_summary" element? More...

String	current_base_name_
	current base name More...

std::vector< std::vector< ProteinIdentification >::iterator >	current_proteins_
	References to currently active ProteinIdentifications. More...

ProteinIdentification::SearchParameters	params_
	Search parameters of the current identification run. More...

String	enzyme_
	Enzyme name associated with the current identification run. More...

PeptideIdentification	current_peptide_
	PeptideIdentification instance currently being processed. More...

PeptideHit::PepXMLAnalysisResult	current_analysis_result_
	Analysis result instance currently being processed. More...

PeptideHit	peptide_hit_
	PeptideHit instance currently being processed. More...

String	current_sequence_
	Sequence of the current peptide hit. More...

double	rt_
	RT and m/z of current PeptideIdentification. More...

double	mz_

Int	charge_
	Precursor ion charge. More...

UInt	search_id_
	ID of current search result. More...

String	prot_id_
	Identifier linking PeptideIdentifications and ProteinIdentifications. More...

DateTime	date_
	Date the pepXML file was generated. More...

double	hydrogen_mass_
	Mass of a hydrogen atom (monoisotopic/average depending on case) More...

std::vector< std::pair< String, Size > >	current_modifications_
	The modifications of the current peptide hit (position is 1-based) More...

std::vector< AminoAcidModification >	fixed_modifications_
	Fixed aminoacid modifications. More...

std::vector< AminoAcidModification >	variable_modifications_
	Variable aminoacid modifications. More...

Static Private Attributes
static const double	mod_tol_

static const double	xtandem_artificial_mod_tol_

Additional Inherited Members
Protected Types inherited from XMLHandler
enum	ActionMode { LOAD, STORE }
	Action to set the current mode (for error messages) More...

Static Protected Member Functions inherited from XMLHandler
static String	writeXMLEscape (const String &to_escape)
	Escapes a string and returns the escaped string. More...

Protected Attributes inherited from XMLHandler
String	error_message_
	Error message of the last error. More...

String	file_
	File name. More...

String	version_
	Schema version. More...

StringManager	sm_
	Helper class for string conversion. More...

std::vector< String >	open_tags_
	Stack of open XML tags. More...

std::vector< std::vector< String > >	cv_terms_
	Array of CV term lists (one sublist denotes one term and it's children) More...

Protected Attributes inherited from XMLFile
String	schema_location_
	XML schema file location. More...

String	schema_version_
	Version string. More...

String	enforced_encoding_
	Encoding string that replaces the encoding (system dependent or specified in the XML). Disabled if empty. Used as a workaround for XTandem output xml. More...

Detailed Description

Used to load and store PepXML files.

This class is used to load and store documents that implement the schema of PepXML files.

Constructor & Destructor Documentation

◆ PepXMLFile()

PepXMLFile ( )

Constructor.

◆ ~PepXMLFile()

virtual ~PepXMLFile ( )

virtual

Destructor.

Member Function Documentation

◆ endElement()

virtual void endElement	(	const XMLCh *	const,
		const XMLCh *	const,
		const XMLCh *const	qname
	)

protectedvirtual

Docu in base class.

Reimplemented from XMLHandler.

◆ keepNativeSpectrumName()

void keepNativeSpectrumName ( bool keep )

inline

Whether we should keep the native spectrum name of the pepXML.

Note: This will lead to a "pepxml_spectrum_name" meta value being added to each PeptideIdentification containing the original name of the spectrum in TPP format.

◆ load() [1/2]

void load	(	const String &	filename,
		std::vector< ProteinIdentification > &	proteins,
		std::vector< PeptideIdentification > &	peptides,
		const String &	experiment_name,
		const SpectrumMetaDataLookup &	lookup
	)

Loads peptide sequences with modifications out of a PepXML file.

Parameters

filename	PepXML file to load
proteins	Protein identification output
peptides	Peptide identification output
experiment_name	Experiment file name, which is used to extract the corresponding search results from the PepXML file.
lookup	Helper for looking up retention times (PepXML may contain only scan numbers).

Exceptions

Exception::FileNotFound	is thrown if the file could not be opened
Exception::ParseError	is thrown if an error occurs during parsing

◆ load() [2/2]

void load	(	const String &	filename,
		std::vector< ProteinIdentification > &	proteins,
		std::vector< PeptideIdentification > &	peptides,
		const String &	experiment_name = `""`
	)

load function with empty defaults for some parameters (see above)

Exceptions

Exception::FileNotFound	is thrown if the file could not be opened
Exception::ParseError	is thrown if an error occurs during parsing

◆ makeScanMap_()

void makeScanMap_ ( )

private

Fill scan_map_.

◆ matchModification_()

void matchModification_	(	const double	mass,
		const String &	origin,
		String &	modification_description
	)

private

find modification name given a modified AA mass

Matches a mass of a modified AA to a mod in our modification db For ambiguous mods, the first (arbitrary) is returned If no mod is found an error is issued and the return string is empty

Note: A duplicate of this function is also used in ProtXMLFile

Parameters

mass	Modified AA's mass
origin	AA one letter code
modification_description	[out] Name of the modification, e.g. 'Carboxymethyl (C)'

◆ readRTMZCharge_()

void readRTMZCharge_ ( const xercesc::Attributes & attributes )

private

Read RT, m/z, charge information from attributes of "spectrum_query".

◆ startElement()

virtual void startElement	(	const XMLCh *	const,
		const XMLCh *	const,
		const XMLCh *const	qname,
		const xercesc::Attributes &	attributes
	)

protectedvirtual

Docu in base class.

Reimplemented from XMLHandler.

◆ store()

void store	(	const String &	filename,
		std::vector< ProteinIdentification > &	protein_ids,
		std::vector< PeptideIdentification > &	peptide_ids,
		const String &	mz_file = `""`,
		const String &	mz_name = `""`,
		bool	peptideprophet_analyzed = `false`
	)

Stores idXML as PepXML file.

Exceptions

Exception::UnableToCreateFile is thrown if the file could not be opened for writing

Member Data Documentation

◆ analysis_summary_

bool analysis_summary_

private

Are we currently in an "analysis_summary" element (should be skipped)?

◆ charge_

Int charge_

private

Precursor ion charge.

◆ checked_base_name_

bool checked_base_name_

private

Have we checked the "base_name" attribute in the "msms_run_summary" element?

◆ current_analysis_result_

PeptideHit::PepXMLAnalysisResult current_analysis_result_

private

Analysis result instance currently being processed.

◆ current_base_name_

String current_base_name_

private

current base name

◆ current_modifications_

std::vector<std::pair<String, Size> > current_modifications_

private

The modifications of the current peptide hit (position is 1-based)

◆ current_peptide_

PeptideIdentification current_peptide_

private

PeptideIdentification instance currently being processed.

◆ current_proteins_

std::vector<std::vector<ProteinIdentification>::iterator> current_proteins_

private

References to currently active ProteinIdentifications.

◆ current_sequence_

String current_sequence_

private

Sequence of the current peptide hit.

◆ date_

DateTime date_

private

Date the pepXML file was generated.

◆ enzyme_

String enzyme_

private

Enzyme name associated with the current identification run.

◆ exp_name_

String exp_name_

private

Name of the associated experiment (filename of the data file, extension will be removed)

◆ experiment_label_

String experiment_label_

private

◆ fixed_modifications_

std::vector<AminoAcidModification> fixed_modifications_

private

Fixed aminoacid modifications.

◆ hydrogen_

Element hydrogen_

private

Hydrogen data (for mass types)

◆ hydrogen_mass_

double hydrogen_mass_

private

Mass of a hydrogen atom (monoisotopic/average depending on case)

◆ keep_native_name_

bool keep_native_name_

private

Whether we should keep the native spectrum name of the pepXML.

◆ lookup_

const SpectrumMetaDataLookup* lookup_

private

Pointer to wrapper for looking up spectrum meta data.

◆ mod_tol_

const double mod_tol_

staticprivate

◆ mz_

double mz_

private

◆ native_spectrum_name_

String native_spectrum_name_

private

Several optional attributes of spectrum_query.

◆ params_

ProteinIdentification::SearchParameters params_

private

Search parameters of the current identification run.

◆ peptide_hit_

PeptideHit peptide_hit_

private

PeptideHit instance currently being processed.

◆ peptides_

std::vector<PeptideIdentification>* peptides_

private

Pointer to the list of identified peptides.

◆ prot_id_

String prot_id_

private

Identifier linking PeptideIdentifications and ProteinIdentifications.

◆ proteins_

std::vector<ProteinIdentification>* proteins_

private

Pointer to the list of identified proteins.

◆ rt_

double rt_

private

RT and m/z of current PeptideIdentification.

◆ scan_map_

std::map<Size, Size> scan_map_

private

Mapping between scan number in the pepXML file and index in the corresponding MSExperiment.

◆ search_engine_

String search_engine_

private

Set name of search engine.

◆ search_id_

UInt search_id_

private

ID of current search result.

◆ search_score_summary_

bool search_score_summary_

private

Are we currently in an "search_score_summary" element (should be skipped)?

◆ search_summary_

bool search_summary_

private

Are we currently in an "search_summary" element (should be skipped)?

◆ seen_experiment_

bool seen_experiment_

private

Have we seen the experiment of interest at all?

◆ status_

String status_

private

◆ swath_assay_

String swath_assay_

private

◆ use_precursor_data_

bool use_precursor_data_

private

Get RT and m/z for peptide ID from precursor scan (should only matter for RT)?

◆ variable_modifications_

std::vector<AminoAcidModification> variable_modifications_

private

Variable aminoacid modifications.

◆ wrong_experiment_

bool wrong_experiment_

private

Do current entries belong to the experiment of interest (for pepXML files that bundle results from different experiments)?

◆ xtandem_artificial_mod_tol_

const double xtandem_artificial_mod_tol_

staticprivate

Classes

Public Member Functions

Protected Member Functions

Private Member Functions

Private Attributes

Static Private Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ PepXMLFile()

◆ ~PepXMLFile()

Member Function Documentation

◆ endElement()

◆ keepNativeSpectrumName()

◆ load() [1/2]

◆ load() [2/2]

◆ makeScanMap_()

◆ matchModification_()

◆ readRTMZCharge_()

◆ startElement()

◆ store()

Member Data Documentation

◆ analysis_summary_

◆ charge_

◆ checked_base_name_

◆ current_analysis_result_

◆ current_base_name_

◆ current_modifications_

◆ current_peptide_

◆ current_proteins_

◆ current_sequence_

◆ date_

◆ enzyme_

◆ exp_name_

◆ experiment_label_

◆ fixed_modifications_

◆ hydrogen_

◆ hydrogen_mass_

◆ keep_native_name_

◆ lookup_

◆ mod_tol_

◆ mz_

◆ native_spectrum_name_

◆ params_

◆ peptide_hit_

◆ peptides_

◆ prot_id_

◆ proteins_

◆ rt_

◆ scan_map_

◆ search_engine_

◆ search_id_

◆ search_score_summary_

◆ search_summary_

◆ seen_experiment_

◆ status_

◆ swath_assay_

◆ use_precursor_data_

◆ variable_modifications_

◆ wrong_experiment_

◆ xtandem_artificial_mod_tol_