MzTabFile Class Reference

File adapter for MzTab files. More...

#include <OpenMS/FORMAT/MzTabFile.h>

Collaboration diagram for MzTabFile:

Public Types
typedef std::map< std::pair< String, String >, std::vector< PeptideHit > >	MapAccPepType

Public Member Functions
	MzTabFile ()
	Default constructor. More...
	~MzTabFile ()
	Destructor. More...
void	store (const String &filename, const MzTab &mz_tab) const
void	store (const String &filename, const std::vector< ProteinIdentification > &protein_identifications, const std::vector< PeptideIdentification > &peptide_identifications, bool first_run_inference_only, bool export_empty_pep_ids=false, const String &title="ID export from OpenMS")
void	store (const String &filename, const ConsensusMap &cmap, const bool first_run_inference_only, const bool export_unidentified_features, const bool export_unassigned_ids, const bool export_subfeatures, const bool export_empty_pep_ids=false) const
void	storeProteinReliabilityColumn (bool store)
void	storePeptideReliabilityColumn (bool store)
void	storePSMReliabilityColumn (bool store)
void	storeSmallMoleculeReliabilityColumn (bool store)
void	storeProteinUriColumn (bool store)
void	storePeptideUriColumn (bool store)
void	storePSMUriColumn (bool store)
void	storeSmallMoleculeUriColumn (bool store)
void	storeProteinGoTerms (bool store)
void	load (const String &filename, MzTab &mz_tab)

Protected Member Functions
void	generateMzTabMetaDataSection_ (const MzTabMetaData &map, StringList &sl) const
String	generateMzTabProteinHeader_ (const MzTabProteinSectionRow &reference_row, const Size n_best_search_engine_scores, const std::vector< String > &optional_columns, const MzTabMetaData &meta, size_t &n_columns) const
String	generateMzTabSectionRow_ (const MzTabProteinSectionRow &row, const std::vector< String > &optional_columns, const MzTabMetaData &meta, size_t &n_columns) const
String	generateMzTabPeptideHeader_ (Size search_ms_runs, Size n_best_search_engine_scores, Size n_search_engine_score, Size assays, Size study_variables, const std::vector< String > &optional_columns, size_t &n_columns) const
String	generateMzTabSectionRow_ (const MzTabPeptideSectionRow &row, const std::vector< String > &optional_columns, const MzTabMetaData &meta, size_t &n_columns) const
String	generateMzTabPSMHeader_ (Size n_search_engine_scores, const std::vector< String > &optional_columns, size_t &n_columns) const
String	generateMzTabSectionRow_ (const MzTabPSMSectionRow &row, const std::vector< String > &optional_columns, const MzTabMetaData &meta, size_t &n_columns) const
String	generateMzTabSmallMoleculeHeader_ (Size search_ms_runs, Size n_best_search_engine_scores, Size n_search_engine_score, Size assays, Size study_variables, const std::vector< String > &optional_columns, size_t &n_columns) const
String	generateMzTabSectionRow_ (const MzTabSmallMoleculeSectionRow &row, const std::vector< String > &optional_columns, const MzTabMetaData &meta, size_t &n_columns) const
String	generateMzTabNucleicAcidHeader_ (Size search_ms_runs, Size n_best_search_engine_scores, Size n_search_engine_scores, const std::vector< String > &optional_columns, size_t &n_columns) const
String	generateMzTabSectionRow_ (const MzTabNucleicAcidSectionRow &row, const std::vector< String > &optional_columns, const MzTabMetaData &meta, size_t &n_columns) const
String	generateMzTabOligonucleotideHeader_ (Size search_ms_runs, Size n_best_search_engine_scores, Size n_search_engine_score, const std::vector< String > &optional_columns, size_t &n_columns) const
String	generateMzTabSectionRow_ (const MzTabOligonucleotideSectionRow &row, const std::vector< String > &optional_columns, const MzTabMetaData &meta, size_t &n_columns) const
String	generateMzTabOSMHeader_ (Size n_search_engine_scores, const std::vector< String > &optional_columns, size_t &n_columns) const
String	generateMzTabSectionRow_ (const MzTabOSMSectionRow &row, const std::vector< String > &optional_columns, const MzTabMetaData &meta, size_t &n_columns) const
template<typename SectionRow >
void	generateMzTabSection_ (const std::vector< SectionRow > &rows, const std::vector< String > &optional_columns, const MzTabMetaData &meta, StringList &output, size_t n_header_columns) const
	Generate an mzTab section comprising multiple rows of the same type and perform sanity check. More...

Static Protected Member Functions
static void	addOptionalColumnsToSectionRow_ (const std::vector< String > &column_names, const std::vector< MzTabOptionalColumnEntry > &column_entries, StringList &output)
	Helper function for "generateMzTabSectionRow_" functions. More...
static std::pair< int, int >	extractIndexPairsFromBrackets_ (const String &s)
static void	sortPSM_ (std::vector< PeptideIdentification >::iterator begin, std::vector< PeptideIdentification >::iterator end)
static void	keepFirstPSM_ (std::vector< PeptideIdentification >::iterator begin, std::vector< PeptideIdentification >::iterator end)
static void	partitionIntoRuns_ (const std::vector< PeptideIdentification > &pep_ids, const std::vector< ProteinIdentification > &pro_ids, std::map< String, std::vector< PeptideIdentification > > &map_run_to_pepids, std::map< String, std::vector< ProteinIdentification > > &map_run_to_proids)
	Extract protein and peptide identifications for each run. maps are assumed empty. More...
static void	createProteinToPeptideLinks_ (const std::map< String, std::vector< PeptideIdentification > > &map_run_to_pepids, MapAccPepType &map_run_accession_to_pephits)
	create links from protein to peptides More...
static String	extractProteinAccession_ (const PeptideHit &peptide_hit)
	Extracts, if possible a unique protein accession for a peptide hit in mzTab format. Otherwise NA is returned. More...
static String	extractPeptideModifications_ (const PeptideHit &peptide_hit)
	Extracts, modifications and positions of a peptide hit in mzTab format. More...
static String	mapSearchEngineToCvParam_ (const String &openms_search_engine_name)
	Map search engine identifier to CV, param etc. More...
static String	mapSearchEngineScoreToCvParam_ (const String &openms_search_engine_name, double score, String score_type)
static String	extractNumPeptides_ (const String &common_identifier, const String &protein_accession, const MapAccPepType &map_run_accession_to_peptides)
static String	extractNumPeptidesDistinct_ (String common_identifier, String protein_accession, const MapAccPepType &map_run_accession_to_peptides)
static String	extractNumPeptidesUnambiguous_ (String common_identifier, String protein_accession, const MapAccPepType &map_run_accession_to_peptides)
static std::map< String, Size >	extractNumberOfSubSamples_ (const std::map< String, std::vector< ProteinIdentification > > &map_run_to_proids)
static void	writePeptideHeader_ (SVOutStream &output, std::map< String, Size > n_sub_samples)
static void	writeProteinHeader_ (SVOutStream &output, std::map< String, Size > n_sub_samples)
static void	writeProteinData_ (SVOutStream &output, const ProteinIdentification &prot_id, Size run_count, String input_filename, bool has_coverage, const MapAccPepType &map_run_accession_to_peptides, const std::map< String, Size > &map_run_to_num_sub)

Protected Attributes
bool	store_protein_reliability_
bool	store_peptide_reliability_
bool	store_psm_reliability_
bool	store_smallmolecule_reliability_
bool	store_protein_uri_
bool	store_peptide_uri_
bool	store_psm_uri_
bool	store_smallmolecule_uri_
bool	store_protein_goterms_
bool	store_nucleic_acid_reliability_
bool	store_oligonucleotide_reliability_
bool	store_osm_reliability_
bool	store_nucleic_acid_uri_
bool	store_oligonucleotide_uri_
bool	store_osm_uri_
bool	store_nucleic_acid_goterms_

Detailed Description

File adapter for MzTab files.

Member Typedef Documentation

MapAccPepType

typedef std::map<std::pair<String, String>, std::vector<PeptideHit> > MapAccPepType

Constructor & Destructor Documentation

MzTabFile()

MzTabFile

(

)

Default constructor.

~MzTabFile()

~MzTabFile

(

)

Destructor.

Member Function Documentation

addOptionalColumnsToSectionRow_()

static void addOptionalColumnsToSectionRow_ ( const std::vector< String > &  column_names, const std::vector< MzTabOptionalColumnEntry > &  column_entries, StringList &  output  )

staticprotected

Helper function for "generateMzTabSectionRow_" functions.

createProteinToPeptideLinks_()

static void createProteinToPeptideLinks_ ( const std::map< String, std::vector< PeptideIdentification > > &  map_run_to_pepids, MapAccPepType &  map_run_accession_to_pephits  )

staticprotected

create links from protein to peptides

extractIndexPairsFromBrackets_()

static std::pair<int, int> extractIndexPairsFromBrackets_ ( const String &  s )

staticprotected

extractNumberOfSubSamples_()

static std::map<String, Size> extractNumberOfSubSamples_ ( const std::map< String, std::vector< ProteinIdentification > > &  map_run_to_proids )

staticprotected

extractNumPeptides_()

static String extractNumPeptides_ ( const String &  common_identifier, const String &  protein_accession, const MapAccPepType &  map_run_accession_to_peptides  )

staticprotected

extractNumPeptidesDistinct_()

static String extractNumPeptidesDistinct_ ( String  common_identifier, String  protein_accession, const MapAccPepType &  map_run_accession_to_peptides  )

staticprotected

extractNumPeptidesUnambiguous_()

static String extractNumPeptidesUnambiguous_ ( String  common_identifier, String  protein_accession, const MapAccPepType &  map_run_accession_to_peptides  )

staticprotected

extractPeptideModifications_()

static String extractPeptideModifications_ ( const PeptideHit &  peptide_hit )

staticprotected

Extracts, modifications and positions of a peptide hit in mzTab format.

extractProteinAccession_()

static String extractProteinAccession_ ( const PeptideHit &  peptide_hit )

staticprotected

Extracts, if possible a unique protein accession for a peptide hit in mzTab format. Otherwise NA is returned.

generateMzTabMetaDataSection_()

void generateMzTabMetaDataSection_ ( const MzTabMetaData &  map, StringList &  sl  ) const

protected

generateMzTabNucleicAcidHeader_()

String generateMzTabNucleicAcidHeader_ ( Size  search_ms_runs, Size  n_best_search_engine_scores, Size  n_search_engine_scores, const std::vector< String > &  optional_columns, size_t &  n_columns  ) const

protected

generateMzTabOligonucleotideHeader_()

String generateMzTabOligonucleotideHeader_ ( Size  search_ms_runs, Size  n_best_search_engine_scores, Size  n_search_engine_score, const std::vector< String > &  optional_columns, size_t &  n_columns  ) const

protected

generateMzTabOSMHeader_()

String generateMzTabOSMHeader_ ( Size  n_search_engine_scores, const std::vector< String > &  optional_columns, size_t &  n_columns  ) const

protected

generateMzTabPeptideHeader_()

String generateMzTabPeptideHeader_ ( Size  search_ms_runs, Size  n_best_search_engine_scores, Size  n_search_engine_score, Size  assays, Size  study_variables, const std::vector< String > &  optional_columns, size_t &  n_columns  ) const

protected

generateMzTabProteinHeader_()

String generateMzTabProteinHeader_ ( const MzTabProteinSectionRow &  reference_row, const Size  n_best_search_engine_scores, const std::vector< String > &  optional_columns, const MzTabMetaData &  meta, size_t &  n_columns  ) const

protected

Needs a reference row to get the collected optional columns from the MetaValues TODO refactor this behaviour by e.g. storing it in the MzTab object

generateMzTabPSMHeader_()

String generateMzTabPSMHeader_ ( Size  n_search_engine_scores, const std::vector< String > &  optional_columns, size_t &  n_columns  ) const

protected

generateMzTabSection_()

void generateMzTabSection_ ( const std::vector< SectionRow > &  rows, const std::vector< String > &  optional_columns, const MzTabMetaData &  meta, StringList &  output, size_t  n_header_columns  ) const

inlineprotected

Generate an mzTab section comprising multiple rows of the same type and perform sanity check.

generateMzTabSectionRow_() [1/7]

String generateMzTabSectionRow_ ( const MzTabNucleicAcidSectionRow &  row, const std::vector< String > &  optional_columns, const MzTabMetaData &  meta, size_t &  n_columns  ) const

protected

generateMzTabSectionRow_() [2/7]

String generateMzTabSectionRow_ ( const MzTabOligonucleotideSectionRow &  row, const std::vector< String > &  optional_columns, const MzTabMetaData &  meta, size_t &  n_columns  ) const

protected

generateMzTabSectionRow_() [3/7]

String generateMzTabSectionRow_ ( const MzTabOSMSectionRow &  row, const std::vector< String > &  optional_columns, const MzTabMetaData &  meta, size_t &  n_columns  ) const

protected

generateMzTabSectionRow_() [4/7]

String generateMzTabSectionRow_ ( const MzTabPeptideSectionRow &  row, const std::vector< String > &  optional_columns, const MzTabMetaData &  meta, size_t &  n_columns  ) const

protected

generateMzTabSectionRow_() [5/7]

String generateMzTabSectionRow_ ( const MzTabProteinSectionRow &  row, const std::vector< String > &  optional_columns, const MzTabMetaData &  meta, size_t &  n_columns  ) const

protected

generateMzTabSectionRow_() [6/7]

String generateMzTabSectionRow_ ( const MzTabPSMSectionRow &  row, const std::vector< String > &  optional_columns, const MzTabMetaData &  meta, size_t &  n_columns  ) const

protected

generateMzTabSectionRow_() [7/7]

String generateMzTabSectionRow_ ( const MzTabSmallMoleculeSectionRow &  row, const std::vector< String > &  optional_columns, const MzTabMetaData &  meta, size_t &  n_columns  ) const

protected

generateMzTabSmallMoleculeHeader_()

String generateMzTabSmallMoleculeHeader_ ( Size  search_ms_runs, Size  n_best_search_engine_scores, Size  n_search_engine_score, Size  assays, Size  study_variables, const std::vector< String > &  optional_columns, size_t &  n_columns  ) const

protected

keepFirstPSM_()

static void keepFirstPSM_ ( std::vector< PeptideIdentification >::iterator  begin, std::vector< PeptideIdentification >::iterator  end  )

staticprotected

load()

void load	(	const String &	filename,
		MzTab &	mz_tab
	)

mapSearchEngineScoreToCvParam_()

static String mapSearchEngineScoreToCvParam_ ( const String &  openms_search_engine_name, double  score, String  score_type  )

staticprotected

mapSearchEngineToCvParam_()

static String mapSearchEngineToCvParam_ ( const String &  openms_search_engine_name )

staticprotected

Map search engine identifier to CV, param etc.

partitionIntoRuns_()

static void partitionIntoRuns_ ( const std::vector< PeptideIdentification > &  pep_ids, const std::vector< ProteinIdentification > &  pro_ids, std::map< String, std::vector< PeptideIdentification > > &  map_run_to_pepids, std::map< String, std::vector< ProteinIdentification > > &  map_run_to_proids  )

staticprotected

Extract protein and peptide identifications for each run. maps are assumed empty.

sortPSM_()

static void sortPSM_ ( std::vector< PeptideIdentification >::iterator  begin, std::vector< PeptideIdentification >::iterator  end  )

staticprotected

store() [1/3]

void store	(	const String &	filename,
		const ConsensusMap &	cmap,
		const bool	first_run_inference_only,
		const bool	export_unidentified_features,
		const bool	export_unassigned_ids,
		const bool	export_subfeatures,
		const bool	export_empty_pep_ids = false
	)		const

store() [2/3]

void store	(	const String &	filename,
		const MzTab &	mz_tab
	)		const

Referenced by NucleicAcidSearchEngine::main_().

store() [3/3]

void store	(	const String &	filename,
		const std::vector< ProteinIdentification > &	protein_identifications,
		const std::vector< PeptideIdentification > &	peptide_identifications,
		bool	first_run_inference_only,
		bool	export_empty_pep_ids = false,
		const String &	title = "ID export from OpenMS"
	)

storePeptideReliabilityColumn()

void storePeptideReliabilityColumn

(

bool

store

)

storePeptideUriColumn()

void storePeptideUriColumn

(

bool

store

)

storeProteinGoTerms()

void storeProteinGoTerms

(

bool

store

)

storeProteinReliabilityColumn()

void storeProteinReliabilityColumn

(

bool

store

)

storeProteinUriColumn()

void storeProteinUriColumn

(

bool

store

)

storePSMReliabilityColumn()

void storePSMReliabilityColumn

(

bool

store

)

storePSMUriColumn()

void storePSMUriColumn

(

bool

store

)

storeSmallMoleculeReliabilityColumn()

void storeSmallMoleculeReliabilityColumn

(

bool

store

)

storeSmallMoleculeUriColumn()

void storeSmallMoleculeUriColumn

(

bool

store

)

writePeptideHeader_()

static void writePeptideHeader_ ( SVOutStream &  output, std::map< String, Size >  n_sub_samples  )

staticprotected

writeProteinData_()

static void writeProteinData_ ( SVOutStream &  output, const ProteinIdentification &  prot_id, Size  run_count, String  input_filename, bool  has_coverage, const MapAccPepType &  map_run_accession_to_peptides, const std::map< String, Size > &  map_run_to_num_sub  )

staticprotected

writeProteinHeader_()

static void writeProteinHeader_ ( SVOutStream &  output, std::map< String, Size >  n_sub_samples  )

staticprotected

Member Data Documentation

store_nucleic_acid_goterms_

bool store_nucleic_acid_goterms_

protected

store_nucleic_acid_reliability_

bool store_nucleic_acid_reliability_

protected

store_nucleic_acid_uri_

bool store_nucleic_acid_uri_

protected

store_oligonucleotide_reliability_

bool store_oligonucleotide_reliability_

protected

store_oligonucleotide_uri_

bool store_oligonucleotide_uri_

protected

store_osm_reliability_

bool store_osm_reliability_

protected

store_osm_uri_

bool store_osm_uri_

protected

store_peptide_reliability_

bool store_peptide_reliability_

protected

store_peptide_uri_

bool store_peptide_uri_

protected

store_protein_goterms_

bool store_protein_goterms_

protected

store_protein_reliability_

bool store_protein_reliability_

protected

store_protein_uri_

bool store_protein_uri_

protected

store_psm_reliability_

bool store_psm_reliability_

protected

store_psm_uri_

bool store_psm_uri_

protected

store_smallmolecule_reliability_

bool store_smallmolecule_reliability_

protected

store_smallmolecule_uri_

bool store_smallmolecule_uri_

protected