Class for parsing and reading files in MSR format. More...

#include <ms_mascotresfile_msr.hpp>

Inheritance diagram for ms_mascotresfile_msr:

Collaboration diagram for ms_mascotresfile_msr:

[legend]

Public Types
enum	FLAGS { RESFILE_NOFLAG = 0x00000000 , RESFILE_USE_CACHE = 0x00000001 , RESFILE_CACHE_IGNORE_ACC_DUPES = 0x00000002 , RESFILE_USE_PARENT_PARAMS = 0x00000004 , RESFILE_CACHE_IGNORE_DATE_CHANGE = 0x00000008 }
	Flags for opening the results file. More...

enum	KA_TASK { KA_CREATEINDEX_CI = 0 , KA_READFILE_RF = 1 , KA_ASSIGNPROTEINS_AP = 2 , KA_GROUPPROTEINS_GP = 3 , KA_UNASSIGNEDLIST_UL = 4 , KA_QUANTITATION = 5 , KA_CREATECACHE_CC = 6 , KA_THRESHFORFDR_FDR = 7 , KA_LAST = 8 }
	Processing some results files is computationally intensive. These are the tasks that can be performed. More...

enum	PERCOLATOR_FILE_NAMES { PERCOLATOR_INPUT_FILE = 0 , PERCOLATOR_OUTPUT_TARGET = 1 , PERCOLATOR_OUTPUT_DECOY = 2 }
	Offsets into a vector of Percolator filenames. More...

enum	RESFILE_TYPE { RESFILE_DAT28 = 0 , RESFILE_MSR = 1 , RESFILE_UNKNOWN = 2 }
	Supported results file formats. More...

enum	XML_SCHEMA { XML_SCHEMA_QUANTITATION = 0 , XML_SCHEMA_UNIMOD = 1 , XML_SCHEMA_DIRECTORY = 2 , XML_SCHEMA_CROSSLINKING = 3 , XML_SCHEMA_LAST = 4 }
	The results file contains embedded files in XML format and these need to be validated against a schema. More...

Public Member Functions
	ms_mascotresfile_msr (const char szFileName, const int keepAliveInterval=0, const char keepAliveText="<!-- %d seconds -->\n", const unsigned int flags=RESFILE_NOFLAG, const char cacheDirectory="../data/cache/%Y/%m", const char XMLschemaDirectory=0, ms_progress_info *progressMonitor=0)
	Constructor to open a Mascot results file in MSR format.

bool	anyCrosslinkedMatches (const bool isDecoy=false) const override
	Returns true if there are any Crosslinked matches.

bool	anyErrorTolerantMatches (const bool isDecoy=false) const override
	Returns true if there are any Error Tolerant matches.

bool	anyFastaMatches (const bool isDecoy=false) const override
	Returns true if there are any FASTA matches.

bool	anyMSMS () const override
	Returns true if any of the queries in the search contain ions data.

bool	anyPMF () const override
	Returns true if any of the queries in the search just contain a single peptide mass.

bool	anySpectralLibraryMatches (const bool isDecoy=false) const override
	Returns true if there are any Spectral library matches.

bool	anySQ () const override
	Returns true if any of the queries in the search contain `seq` or `comp` commands.

bool	anyTag () const override
	Returns true if any of the queries in the search contain `tag` or `etag` commands.

void	appendErrors (const ms_errors &src)
	Copies all errors from another instance and appends them at the end of own list.

int	appendResfile (const char filename, int flags=RESFILE_USE_PARENT_PARAMS, const char cacheDirectory=0) override
	Multiple results files can be summed together and treated as 'one'.

void	clearAllErrors ()
	Remove all errors from the current list of errors.

void	copyFrom (const ms_errors *right)
	Use this member to make a copy of another instance.

std::string	get_ms_mascotresults_params (const ms_mascotoptions &opts, ms_mascotresults_params &params) const
	Return default flags and parameters for creating an ms_peptidesummary or ms_proteinsummary object.

std::string	get_ms_mascotresults_params (const ms_mascotoptions &opts, unsigned int gpFlags, double gpMinProbability, int gpMaxHitsToReport, double gpIgnoreIonsScoreBelow, unsigned int gpMinPepLenInPepSummary, bool gpUsePeptideSummary, unsigned int *gpFlags2) const
	[Deprecated] Return default flags and parameters for creating an ms_peptidesummary or ms_proteinsummary object.

std::string	getCacheDirectory (bool processed=true) const override
	Returns the directory being used for cache files (if any).

std::string	getCacheFileName () const override
	Returns the filename of the cache file.

bool	getCrosslinkingMethod (ms_crosslinking_method *method) const
	Return the crosslinking method object from the embedded crosslinking file.

DATABASE_TYPE	getDatabaseType (const int idx) const override
	Return database type if available.

int	getDate () const override
	Returns the date and time of the search in seconds since midnight January 1st 1970.

ms_mascotoptions::DECOY_ALGORITHM	getDecoyTypeForDB (const int idx=1) const override
	Returns the decoy algorithm type for a given database.

bool	getEnzyme (ms_enzymefile efile, const char enzymeFileName=0) const override
	Returns an object that represents the embedded enzyme file as a reduced `enzymes` file.

const ms_errs *	getErrorHandler () const
	Retrive the error object using this function to get access to all errors and error parameters.

int	getErrorNumber (const int num=-1) const
	Return a specific error number - or ms_errs::ERR_NO_ERROR.

std::string	getErrorString (const int num) const
	Return a specific error as a string.

int	getExecTime () const override
	Returns the time taken for the search.

std::string	getFastaPath (int idx=1) const override
	Returns the path to the FASTA file used.

std::string	getFastaVer (int idx=1) const override
	Returns the FASTA file version.

std::string	getFileName (const int id=1) const override
	Returns the name of the results file passed into the constructor.

double	getFirstPassThreshold () const override
	Return the threshold value for the first pass of an automated error tolerant search.

void	getHeaderKeyValues (std::vector< std::string > &keys, std::vector< std::string > &values) const override
	Return all the header key-value pairs.

virtual std::string	getHeaderValue (const std::string &key) const override
	Return the header value for the given key.

ms_inputquery	getInputQuery (const int queryNum) const override
	Return the ms_inputquery object for the query given as argument.

int	getJobNumber (const int resfileID=1) const override
	Return the job number for this file - obtained from the file name.

void	getKeepAlive (KA_TASK &kaTask, int &kaPercentage, std::string &kaAccession, int &kaHit, int &kaQuery, std::string &kaText) const
	Return the progress indicators used by the keepAlive functions.

int	getLastError () const
	Return the last error number - or ms_erros::ERR_NO_ERROR.

std::string	getLastErrorString () const
	Return the last error number - or an empty string.

int	getLibraryMods (std::vector< std::string > &modNames, std::vector< double > &modDeltas) const override
	Return all the library mod names and deltas.

std::string	getMascotVer () const override
	Returns the version of Mascot used to perform the search.

bool	getMasses (ms_masses *masses) const
	Returns an ms_masses object from the mass values in the results file.

void	getMassesKeyValues (std::vector< std::string > &keys, std::vector< double > &values) const override
	Return all the residue and modification masses as key-value pairs.

virtual double	getMassValue (const std::string &key) const override
	Return the residue or modification mass for the given key.

const ms_modification *	getMonoLinkModification (const int modNum, const int monoLink) const
	Returns an ms_modification object that represents a monolink variable modification.

std::string	getMSParserVersion () const
	Returns the version number of the Mascot Parser library.

int	getMultiFileQueryNumber (const int localQuery, const int fileId) const override
	Return the multi-file query number from the local query number in an appended file.

int	getNumberOfErrors () const
	Return the number of errors since the last call to clearAllErrors.

int	getNumberOfResfiles () const override
	Multiple results files can be summed together and treated as 'one'.

int	getNumEtSeqsSearched (const int idx=0) const override
	Returns the number of sequences searched in the second pass of an integrated error tolerant search.

int	getNumLibraryEntries (const int idx=0) const override
	Returns the number of entries in the spectral library searched.

int	getNumQueries (const int resfileID=0) const override
	Returns the number of queries (peptide masses or ms-ms spectra).

double	getNumResidues (const int idx=0) const override
	Returns the number of residues in the FASTA file(s) searched.

int	getNumSeqs (const int idx=0) const override
	Returns the number of sequences in the FASTA file(s) searched.

int	getNumSeqsAfterTax (const int idx=0) const override
	Returns the number of sequences that passed the taxonomy filter in the FASTA file(s) searched.

int	getObservedCharge (const int query, const bool decoy=false) const override
	The 'charge' returned will be 0 for Mr, otherwise it will be 1, -1, 2, -2, 3, -3 etc. and -100 for an error.

double	getObservedIntensity (const int query) const override
	Returns the experimental intensity for the peptide.

double	getObservedMass (const int query) const override
	Returns the experimental mass value as entered by the user.

double	getObservedMrValue (const int query, const bool decoy=false) const override
	Returns the experimental mass value (as a relative mass) as entered by the user.

std::vector< std::string >	getPercolatorFileNames () const
	Retrieve the filenames use for percolator input and output.

ms_progress_info *	getProgressInfo (bool forPeptideSummary=false) const
	If a matrix_science::ms_progress_info object is passed to the constructor, this is returned here.

int64_t	getQmatch (const int query, const ms_peptide::PSM_TYPE pepType) const override
	Return the number of peptide masses within precursor tolerance of this query.

double	getQplughole (const int query, const ms_peptide::PSM_TYPE pepType) const override
	Return the threshold score for homologous peptide match (MIS only).

bool	getQuantitation (ms_quant_configfile *qfile) const override
	Returns an object that represents the embedded quantitation file as a reduced `quantitation.xml` file.

bool	getQuantitationMethod (ms_quant_method *qmethod) const
	Return the quantitation method object from the embedded quantitation file.

int	getReferenceDatabaseNumberOfSL (const int idx) const override
	Return the database number of the reference database of a spectral library.

std::string	getRepeatSearchString (const int query, const bool fullQuery=false) const override
	To perform a repeat search need to build up appropriate string.

const ms_mascotresfile_msr *	getResfile (int id) const override
	Returns a pointer to the ms_mascotresfile_msr object created by calling appendResfile.

virtual std::string	getSearchParameter (const std::string &key) const override
	Return the search parameter the given key.

void	getSearchParametersKeyValues (std::vector< std::string > &keys, std::vector< std::string > &values) const override
	Return all the search parameters as key-value pairs.

std::vector< int >	getSLDatabaseNumbersOfReference (const int idx) const override
	Return the database numbers of the spectral libraries whose reference database is at the given index.

virtual std::string	getSLExecCommand (int idx=1) const override
	Returns the library search command line and parameters (sl_exec_command).

double	getSLFragmentTolerance (int idx=1) const override
	Returns the effective spectral library fragment tolerance.

std::string	getSLFragmentToleranceUnit (int idx=1) const override
	Returns the unit of the effective spectral library fragment tolerance.

bool	getSrcQueryAndFileIdForMultiFile (const int q, int &gsqNewQuery, int &gsqFileId) const override
	Return the query number and file ID in the source results file.

bool	getTaxonomy (ms_taxonomyfile *tfile) const override
	Returns an object that represents the embedded taxonomy file as a reduced `taxonomy` file.

bool	getUnimod (ms_umod_configfile *ufile, bool useSchemaFromResfile=false) const override
	Returns an object that represents the embedded unimod file as a reduced `unimod_2.xml` file.

bool	getUnimodXL (ms_umod_configfile *ufile, bool useSchemaFromResfile=false) const override
	Returns an object that represents the embedded unimod_xl file as a reduced `unimod_xl.xml` file.

std::string	getUniqueTaskID () const override
	Returns the unique task ID used by Mascot Daemon.

std::string	getXMLschemaFilePath (XML_SCHEMA XMLschema) const
	Gets the XML schema to be used by functions using quantitation or unimod.

bool	hasEnzyme () const override
	Return true if the results file contains information about the enzyme used.

bool	hasQuantitation () const override
	Return true if the results file contains quantitation data.

bool	hasRT () const override
	Return true if the results file contains retention time data.

bool	isDatabaseTypeAvailable () const override
	Check whether database types are available.

bool	isErrorTolerant () const override
	Returns true if the search was an error tolerant search.

bool	isMSMS () const override
	Returns true if the search was an MSMS search (`SEARCH=MIS`).

bool	isPMF () const override
	Returns true if the search was a PMF search (`SEARCH=PMF`).

bool	isSQ () const override
	Returns true if the search was a sequence query search (`SEARCH=SQ`).

bool	isValid () const
	Call this function to determine if there have been any errors.

bool	outputKeepAlive () const
	Outputs the "keep-alive" string during time-consuming operations.

ms_searchparams &	params () const
	Returns a reference to the search parameters class.

void	resetKeepAlive (const int keepAliveInterval, const char *keepAliveText, const bool propagateToAppended=true, const bool resetStartTime=false)
	Replace the existing keepAlive values with new values.

void	setPercolatorFeatures (const char percolatorFeatures, const char additionalFeatures, const bool useRetentionTimes)
	Set Percolator features before creating an ms_peptidesummary with Percolator scoring (deprecated).

void	setPercolatorFeatures (const ms_mascotoptions &options, const char *additionalFeatures, const std::vector< std::string > &adapterParameters=std::vector< std::string >())
	Set Percolator features before creating an ms_peptidesummary with Percolator scoring.

bool	setXMLschemaFilePath (XML_SCHEMA XMLschema, const char *path)
	Sets the XML schema to be used by functions using quantitation or unimod.

bool	versionGreaterOrEqual (int major, int minor, int revision) const
	Compare the value returned by getMascotVer() with the passed version number.

Static Public Member Functions
static std::unique_ptr< ms_mascotresfilebase >	createResfile (const char szFileName, const int keepAliveInterval=0, const char keepAliveText="<!-- %d seconds -->\n", const unsigned int flags=matrix_science::ms_mascotresfilebase::RESFILE_NOFLAG, const char cacheDirectory="../data/cache/%Y/%m", const char XMLschemaDirectory=0, matrix_science::ms_progress_info *progressMonitor=0)
	Return a new ms_mascotresfile_msr or ms_mascotresfile_dat based on the file contents.

static RESFILE_TYPE	resfileType (const std::string &fileName)
	Return the results format of the file provided as an argument.

static bool	staticGetPercolatorFileNames (const char szFileName, const char cacheDirectory, const char percolatorFeatures, const char additionalFeatures, const bool useRetentionTimes, std::vector< std::string > &filenames, std::vector< bool > &exists)
	Returns a list of the Percolator input and output files for the specified data file (deprecated).

static bool	staticGetPercolatorFileNames (const char szFileName, const char cacheDirectory, const ms_mascotoptions &options, const char *additionalFeatures, const std::vector< std::string > &adapterParameters, std::vector< std::string > &filenames, std::vector< bool > &exists)
	Returns a list of the Percolator input and output files for the specified data file.

static bool	willCreateCache (const char szFileName, const ms_mascotoptions &opts, const char applicationName, std::string &resfileCacheFileName, unsigned int &cacheStatus)
	Returns true if a cache file will be created when the ms_mascotresfile_dat constructor is called.

static bool	willCreateCache (const char szFileName, const unsigned int flags, const char cacheDirectory, std::string *cacheFileName)
	Returns true if a cache file will be created when the ms_mascotresfile_dat constructor is called.

Protected Member Functions
bool	getCrosslinking (ms_crosslinking_configfile *crosslinkingFile) const override

std::string	getErrorInfoAsString (const int num) const

bool	setErrorInfoFromString (const std::string &e)

Detailed Description

Class for parsing and reading files in MSR format.

Until Mascot Server 2.8, there was only one Mascot results file format: plain text MIME format file with .dat extension. Mascot Server 3.0 introduced a new file format, Mascot Search Results (MSR), which is an SQLite database. The old .dat format is frozen and now referred to as dat28.

This class reads files in the MSR format.

Member Enumeration Documentation

◆ FLAGS

enum FLAGS

inherited

Flags for opening the results file.

See Using enumerated values and static const ints in Perl, Java, Python and C# and Caching Mascot Results.

Enumerator
RESFILE_NOFLAG	Dat28 format: Read the whole file into memory. MSR format: Use standard SQLite methods to read the file with low memory overhead.
RESFILE_USE_CACHE	Dat28 format: Create the resfile cache if it doesn't already exist. Use the cache rather than reading the whole .dat file into memory. MSR format: this flag is ignored.
RESFILE_CACHE_IGNORE_ACC_DUPES	When creating a cache file, don't check for duplicate accessions in the SEC_PROTEINS and SEC_DECOYPROTEINS sections which can save some time. Strongly recommend that this flag is never used unless performance becomes a real issue and it is known that ms_mascotoptions::getIgnoreDupeAccession was not defined for the relevant database(s) when they were compressed.
RESFILE_USE_PARENT_PARAMS	For use when Combining multiple results files. The flags and parameters are then inherited from the parent search.
RESFILE_CACHE_IGNORE_DATE_CHANGE	Dat28 format: Opening the resfile cache CDB file should ignore the last modified timestamp on the .dat file. MSR format: this flag is ignored.

◆ KA_TASK

enum KA_TASK

inherited

Processing some results files is computationally intensive. These are the tasks that can be performed.

See Using enumerated values and static const ints in Perl, Java, Python and C#.

Used with getKeepAlive(), but also see outputKeepAlive()

Enumerator
KA_CREATEINDEX_CI	Creating a cache file when Using the resfile cache (dat28 format only) in dat28 format.
KA_READFILE_RF	Reading the results file into memory when not using a cache.
KA_ASSIGNPROTEINS_AP	Assigning peptides to proteins to get a list of all possible proteins.
KA_GROUPPROTEINS_GP	Grouping proteins using ms_mascotresults::MSRES_GROUP_PROTEINS or ms_mascotresults::MSRES_CLUSTER_PROTEINS.
KA_UNASSIGNEDLIST_UL	Creating the unassigned list - see ms_mascotresults::createUnassignedList.
KA_QUANTITATION	Calculating quantitation values for reporter and multiplex protocols.
KA_CREATECACHE_CC	Creating a cache file when Using the pepsum cache (MSR and dat28).
KA_THRESHFORFDR_FDR	Calls to ms_mascotresults::getThresholdForFDRAboveHomology can be slow.
KA_LAST	Placeholder that is equal to the number of possible tasks.

◆ PERCOLATOR_FILE_NAMES

enum PERCOLATOR_FILE_NAMES

inherited

Offsets into a vector of Percolator filenames.

See Using enumerated values and static const ints in Perl, Java, Python and C#.

Used with getPercolatorFileNames().

Enumerator
PERCOLATOR_INPUT_FILE	This file is created by ms-createpip.exe and read by Percolator.
PERCOLATOR_OUTPUT_TARGET	From std::out of percolator.exe.
PERCOLATOR_OUTPUT_DECOY	Specified using the -B flag when calling Percolator.

◆ RESFILE_TYPE

enum RESFILE_TYPE

inherited

Supported results file formats.

Enumerator
RESFILE_DAT28	Plain text MIME-format results file produced by Mascot Server 2.0 to 2.8.
RESFILE_MSR	Mascot Search Results (MSR) file introduced in Mascot Server 3.0.
RESFILE_UNKNOWN	Unknown file format.

◆ XML_SCHEMA

enum XML_SCHEMA

inherited

The results file contains embedded files in XML format and these need to be validated against a schema.

This is the list of schema that can be set using setXMLschemaFilePath() and getXMLschemaFilePath()

Enumerator
XML_SCHEMA_QUANTITATION	From the embedded quantation file. Valid aliases are: "http://www.matrixscience.com/xmlns/schema/quantitation_1" and "http://www.matrixscience.com/xmlns/schema/quantitation_2".
XML_SCHEMA_UNIMOD	From the embedded unimod file. Valid alias is: http://www.unimod.org/xmlns/schema/unimod_2.
XML_SCHEMA_DIRECTORY	From the value of XMLschemaDirectory passed into the ms_mascotresfilebase constructor.
XML_SCHEMA_CROSSLINKING	From the embedded crosslinking file. Valid alias is: http://www.matrixscience.com/xmlns/schema/crosslinking_1.
XML_SCHEMA_LAST	Placeholder that is equal to the number of possible schema.

Constructor & Destructor Documentation

◆ ms_mascotresfile_msr()

ms_mascotresfile_msr	(	const char *	szFileName,
		const int	keepAliveInterval = `0`,
		const char *	keepAliveText = `"<!-- %d seconds -->\n"`,
		const unsigned int	flags = `RESFILE_NOFLAG`,
		const char *	cacheDirectory = `"../data/cache/%Y/%m"`,
		const char *	XMLschemaDirectory = `0`,
		ms_progress_info *	progressMonitor = `0`
	)

Constructor to open a Mascot results file in MSR format.

It is always safe to specify just the ms_mascotresfilebase::RESFILE_NOFLAG flag. The Mascot Search Results (MSR) file is an SQLite database, and reading the file has no memory overhead. The ms_mascotresfilebase::RESFILE_USE_CACHE and ms_mascotresfilebase::RESFILE_CACHE_IGNORE_DATE_CHANGE flags are ignored. These are only useful with ms_mascotresfile_dat.

For HTML reports with large result files it is sometimes necessary to output HTML fragments to keep the connection alive. This can be done by specifying the interval at which the text is output (keepAliveInterval) and the text that should be output (keepAliveText). Although ms_mascotresfile_msr does not create a cache file, the outputKeepAlive mechanism is also used by ms_peptidesummary. See ms_mascotresfilebase::outputKeepAlive() for more details.

The functions isValid() or getLastError() should be called after creating the object to determine if the file was valid and loaded properly.

Possible error values:

Parameters

szFileName	is the path to a valid Mascot results file in MSR format
keepAliveInterval	is the interval in seconds between each time the keepAliveText is output to stdout. If a value of zero is specified, then no keep alive text will be output.
keepAliveText	is output every keepAliveInterval seconds while the file is being loaded. See outputKeepAlive() for further details.
flags	are created by bitwise ORing the ms_mascotresfilebase::FLAGS
cacheDirectory	is the location where any cache files are stored. See Specifying cache file directory. If cacheDirectory is null or empty, then ms_peptidesummary will not be able to use caching. Most applications should get this value from ms_mascotoptions::getCacheDirectory().
XMLschemaDirectory	is the location where the xml schema files are located. Some sections of the results file are encoded in XML, and Mascot Parser needs to verify that these are in the correct format using 'xsd' schema files. The required files are supplied with Mascot Parser in the config directory. Either supply the path to that directory, or copy the .xsd files from it to another directory and supply the path to that (only the xsd files from that directory are required). If this parameter is 0 (the default) or empty string (""), then it is assumed that the software is running on the Mascot Server and that the files are located in separate directories under ../html/xmlns/schema as defined in setXMLschemaFilePath(). The constructor does not check that the schema files exist, but subsequent calls to functions such as getUnimod() and getQuantitationMethod() will fail if the schema is not available. The function setXMLschemaFilePath() may be called to override this value passed in the constructor for individual schema files.
progressMonitor	is an optional parameter that can be used to track progress of the creation of this object. It can also be used (from another thread) to cancel the creation of the object by calling ms_progress_info::setBreak. If the passed progressMonitor has a subTask, created by calling ms_progress_info::addSubtask("Creating peptide summary", 100), then that subtask will be used when creating the ms_peptidesummary object. If the subtask doesn't exist, then one is created. Both pointers can be obtained by calling ms_mascotresfilebase::getProgressInfo(). Make sure that the calling function does not delete the object pointed to by this paramater until after the ms_mascotresfile_msr object has been deleted. See: Maintaining object references: two rules of thumb

Member Function Documentation

◆ anyCrosslinkedMatches()

bool anyCrosslinkedMatches ( const bool isDecoy = false ) const

overridevirtual

Returns true if there are any Crosslinked matches.

Returns: true if it has any Crosslinked matches

Implements ms_mascotresfilebase.

◆ anyErrorTolerantMatches()

bool anyErrorTolerantMatches ( const bool isDecoy = false ) const

overridevirtual

Returns true if there are any Error Tolerant matches.

Returns: true if it has any Error Tolerant matches

Implements ms_mascotresfilebase.

◆ anyFastaMatches()

bool anyFastaMatches ( const bool isDecoy = false ) const

overridevirtual

Returns true if there are any FASTA matches.

Returns: true if it has any FASTA matches

Implements ms_mascotresfilebase.

◆ anyMSMS()

bool anyMSMS ( ) const

overridevirtual

Returns true if any of the queries in the search contain ions data.

See also the isMSMS() member, although this function is the preferred one.

Returns: true if any queries contain MS-MS fragment masses

Implements ms_mascotresfilebase.

◆ anyPMF()

bool anyPMF ( ) const

overridevirtual

Returns true if any of the queries in the search just contain a single peptide mass.

See also the isPMF() member, although this function is the preferred one.

Returns: true if any queries contain no MS-MS values

Implements ms_mascotresfilebase.

◆ anySpectralLibraryMatches()

bool anySpectralLibraryMatches ( const bool isDecoy = false ) const

overridevirtual

Returns true if there are any Spectral library matches.

Returns: true if it has any Spectral Library matches

Implements ms_mascotresfilebase.

◆ anySQ()

bool anySQ ( ) const

overridevirtual

Returns true if any of the queries in the search contain seq or comp commands.

See also the isSQ() member, although this function is the preferred one.

Returns: true if any queries contain seq or comp commands

Implements ms_mascotresfilebase.

◆ anyTag()

bool anyTag ( ) const

overridevirtual

Returns true if any of the queries in the search contain tag or etag commands.

See also anySQ(), anyPMF() and anyMSMS()

Returns: true if any queries contain tag or etag commands; true if it has any tag

Implements ms_mascotresfilebase.

◆ appendErrors()

void appendErrors ( const ms_errors & src )

inherited

Copies all errors from another instance and appends them at the end of own list.

Parameters

src	The object to copy the errors across from. See Maintaining object references: two rules of thumb.

◆ appendResfile()

int appendResfile	(	const char *	filename,
		int	flags = `RESFILE_USE_PARENT_PARAMS`,
		const char *	cacheDirectory = `0`
	)

overridevirtual

Multiple results files can be summed together and treated as 'one'.

See Combining multiple results files.

Attempts to load the specifed results file and append to the existing file.

Any warning or error messages in the file are also appended to the existing object. If isValid() for the new file returns false, it is not appended and this function returns 0.

A merged report requires the results to be in the same file format. That is, a dat28 (.dat) can be appended to another dat28 file, and an MSR file (.msr) can be appended to another MSR file, but you cannot append an MSR file to a dat28 file or vice versa.

ms_errs::ERR_INVALID_RESFILE, ms_errs::ERR_READINGFILE or ms_errs::ERR_MSP_MSR_READING_FILE may be set if the file formats are not compatible.

ms_errs::ERR_CANNOT_APPEND_RESFILE_NO_FNAMES and ms_errs::ERR_CANNOT_APPEND_RESFILE will be set if the file cannot be appended because of different parameters, such as a different enzyme.

Parameters

filename	is the path to the results file to append.
flags	are one of the ms_mascotresfilebase::FLAGS. If `RESFILE_USE_PARENT_PARAMS` is specified, then the flags, `keepAlive` and cache directory are copied from the parent object.
cacheDirectory	is the directory for the cache files if `RESFILE_USE_CACHE` has been specified. If `RESFILE_USE_PARENT_PARAMS` is specified and cacheDirectory is null or an empty string, then the cache directory for the parent object is used.

Returns: 0 on error, or the id number of the new file. The id can be used with getNumQueries(), getJobNumber(), getFileName() or getResfile(). The return value from the first successful call to this function will be 2.

Implements ms_mascotresfilebase.

◆ clearAllErrors()

void clearAllErrors ( )

inherited

Remove all errors from the current list of errors.

The list of 'errors' can include fatal errors, warning messages, information messages and different levels of debugging messages.

All messages are accumulated into a list in this object, until clearAllErrors() is called.

See Error Handling.

See also: isValid(), getLastError(), getLastErrorString(), getErrorHandler()

Examples: common_error.cpp, resfile_error.cpp, and resfile_summary.cpp.

◆ copyFrom()

void copyFrom ( const ms_errors * right )

inherited

Use this member to make a copy of another instance.

Parameters

right is the source to initialise from

◆ createResfile()

std::unique_ptr< ms_mascotresfilebase > createResfile	(	const char *	szFileName,
		const int	keepAliveInterval = `0`,
		const char *	keepAliveText = `"<!-- %d seconds -->\n"`,
		const unsigned int	flags = `matrix_science::ms_mascotresfilebase::RESFILE_NOFLAG`,
		const char *	cacheDirectory = `"../data/cache/%Y/%m"`,
		const char *	XMLschemaDirectory = `0`,
		matrix_science::ms_progress_info *	progressMonitor = `0`
	)

staticinherited

Return a new ms_mascotresfile_msr or ms_mascotresfile_dat based on the file contents.

The function 'sniffs' and detects the file contents using ms_mascotresfilebase::resfileType. If it looks like an MSR file, the function returns a new ms_mascotresfile_msr. If it looks like a dat28 (.dat) file, the function returns ms_mascotresfile_dat. Otherwise, a 'nil' object is returned which contains no data and is invalid.

The arguments are the same between the classes, but the details differ a bit. For example, ms_mascotresfile_msr doesn't need caching for fast random access, so it ignores the flags parameter. However, it's always safe to use the same flags regardless of class.

Please see the detailed class documentation:

Parameters

szFileName	is the path to a valid Mascot results file
keepAliveInterval	is the interval in seconds between each time the keepAliveText is output to stdout.
keepAliveText	is output every keepAliveInterval seconds while the file is being loaded. See outputKeepAlive() for further details.
flags	are created by bitwise ORing the ms_mascotresfile_dat::FLAGS.
cacheDirectory	is the location where any cache files are stored.
XMLschemaDirectory	is the location where the xml schema files are located.
progressMonitor	is an optional parameter that can be used to track progress of the creation of this object.

Returns: ms_mascotresfile_msr or ms_mascotresfile_dat object, or a 'nil' object if the file type isn't supported.

◆ get_ms_mascotresults_params() [1/2]

std::string get_ms_mascotresults_params	(	const ms_mascotoptions &	opts,
		ms_mascotresults_params &	resParams
	)		const

inherited

Return default flags and parameters for creating an ms_peptidesummary or ms_proteinsummary object.

A number of optional flags and parameters can be passed to the ms_proteinsummary or ms_peptide summary constructors. For an application or script running on the Mascot server, the default values for some of these parameters should normally be taken from the mascot.dat file. This function sets the values and flags required to pass to the constructor in the passed ms_mascotresults_params object.

Parameters

[in]	opts	contains the options stored in mascot.dat. Call the ms_datfile construction and then ms_datfile::getMascotOptions() to obtain this value.
[out]	resParams	the values and flags required to pass to the peptide or protein summary object are set to this ms_mascotresults_params object, overwriting any values which were already set.

Returns: If the search contains MS-MS data and the number of queries >= ms_mascotoptions::getProteinFamilySwitch, then the returned script name will be ms_mascotoptions::getResultsPerlScript_2, otherwise it will be ms_mascotoptions::getResultsPerlScript.

Examples: resfile_summary.cpp.

◆ get_ms_mascotresults_params() [2/2]

std::string get_ms_mascotresults_params	(	const ms_mascotoptions &	opts,
		unsigned int *	gpFlags,
		double *	gpMinProbability,
		int *	gpMaxHitsToReport,
		double *	gpIgnoreIonsScoreBelow,
		unsigned int *	gpMinPepLenInPepSummary,
		bool *	gpUsePeptideSummary,
		unsigned int *	gpFlags2
	)		const

inherited

[Deprecated] Return default flags and parameters for creating an ms_peptidesummary or ms_proteinsummary object.

Deprecated:: This function is deprecated. All new code should use ms_mascotresfilebase::get_ms_mascotresults_params(const ms_mascotoptions &, ms_mascotresults_params &) instead, as all the parameters are encapsulated in the ms_mascotresults_params class.

A number of optional flags and parameters can be passed to the ms_proteinsummary or ms_peptide summary constructors. For an application or script running on the Mascot server, the default values for some of these parameters should normally be taken from the mascot.dat file. This function returns the values and flags required to pass to the constructor.

See Multiple return values in Perl, Java, Python and C#.

Parameters

[in]	opts	contains the options stored in mascot.dat. Call the ms_datfile construction and then ms_datfile::getMascotOptions() to obtain this value.
[out]	gpFlags	will return the flags that are to be passed as the second parameter to the ms_proteinsummary or ms_peptidesummary object.
[out]	gpMinProbability	is the third parameter to be passed to the ms_proteinsummary or ms_peptidesummary objects. This return value will nomally be equal to the value returned from ms_mascotoptions::getSigThreshold().
[out]	gpMaxHitsToReport	this return value will normally be the one returned by ms_searchparams::getREPORT().
[out]	gpIgnoreIonsScoreBelow	this return value will be the one returned by ms_mascotoptions::getIgnoreIonsScoreBelow().
[out]	gpMinPepLenInPepSummary	this return value will be the one returned by ms_mascotoptions::getMinPepLenInPepSummary.
[out]	gpUsePeptideSummary	will be false is the file doesn't contain any anyMSMS (as returned by the anyMSMS() function) or any sequence tags (anyTag()). In this case, you should create an ms_proteinsummary. If gpUsePeptideSummary is true, you should create an ms_peptidesummary object.
[out]	gpFlags2	is only required for an ms_peptidesummary. If gpUsePeptideSummary is true, gpFlags2 will have the following bits set. ms_peptidesummary::MSPEPSUM_PERCOLATOR if all of the following apply: the number of queries is >= ms_mascotoptions::getPercolatorMinQueries; the number of sequences searched >= ms_mascotoptions::getPercolatorMinSequences; this is a decoy search; ms_mascotoptions::isPercolator() returns true; ms_peptidesummary::MSPEPSUM_USE_CACHE if the script name that the function will return is in the string specified by ms_mascotoptions::getResultsCache(). ms_peptidesummary::MSPEPSUM_USE_HOMOLOGY_THRESH if the search contains MS-MS data and the number of queries >= ms_mascotoptions::getProteinFamilySwitch. ms_peptidesummary::MSPEPSUM_REMOVE_CHIMERIC_DUPES if the results file comes from Mascot 2.5 or later.

Returns: If the search contains MS-MS data and the number of queries >= ms_mascotoptions::getProteinFamilySwitch, then the returned script name will be ms_mascotoptions::getResultsPerlScript_2, otherwise it will be ms_mascotoptions::getResultsPerlScript.

◆ getCacheDirectory()

std::string getCacheDirectory ( bool processed = true ) const

overridevirtual

Returns the directory being used for cache files (if any).

The cacheDirectory supplied to the constructor ms_mascotresfilebase::ms_mascotresfilebase may contain a number of '%' flags which get substituted by Mascot Parser.

This function returns either an absolute directory or a directory relative to the current working directory, depending on what was supplied and the parameter processed.

See Caching Mascot Results and ms_mascotoptions::getCacheDirectory

Parameters

processed if true (the default), then the returned directory is relative to the current directory and will have any '%' flags replaced with the relevant directory. If processed is false, then the directory returned will be identical to the one passed to the constructor.

Returns: The cache directory.

Implements ms_mascotresfilebase.

◆ getCacheFileName()

std::string getCacheFileName ( ) const

overridevirtual

Returns the filename of the cache file.

Files in .dat (dat28) format need a cache file to avoid issues with random access. MSR files accessed with ms_mascotresfile_msr do not need a cache file, so this method always returns the empty string.

Returns: The empty string.

Implements ms_mascotresfilebase.

◆ getCrosslinking()

bool getCrosslinking ( ms_crosslinking_configfile * crosslinkingFile ) const

overrideprotectedvirtual

The return value indicates that the embedded crosslinking method file exists in the results file. Call ms_crosslinking_configfile::isValid to determine whether the XML part has been parsed successfully.

The contents of the file are validated against a schema by default.

See Object initialising functions in Perl, Java, Python and C#.

See also: getCrosslinkingMethod() which is generally easier to use.

Parameters

crosslinkingFile a pointer to crosslinking file object. This must be a valid pointer to a valid object, which should normally be created using the default constructor: ms_crosslinking_configfile::ms_crosslinking_configfile

Returns: true if embedded file exists and false if it doesn't

Implements ms_mascotresfilebase.

◆ getCrosslinkingMethod()

bool getCrosslinkingMethod ( ms_crosslinking_method * method ) const

inherited

Return the crosslinking method object from the embedded crosslinking file.

This method returns true if all of the following apply:

the embedded crosslinking file exists;
a valid schema file location has been set using the XMLschemaDirectory parameter in the constructor or the file exists in the default location;
the embedded crosslinking file validates against the schema;
the crosslinking method named in the CROSSLINKING parameter exists;
the crosslinking method can be loaded.

Otherwise the method returns false.

If the CROSSLINKING parameter is empty or equals "none", then the method simply returns false. Otherwise, on failure, the method sets the warning ms_errors::ERR_MSP_CROSSLINKING_FAILEDLOAD.

Parameters

method A pointer to crosslinking method object. This must be a valid pointer to a valid object, which should normally be created using the default constructor ms_quant_method::ms_quant_method.

Returns: True if the method was loaded; false otherwise.

◆ getDatabaseType()

DATABASE_TYPE getDatabaseType ( const int idx ) const

overridevirtual

Return database type if available.

In dat28 format, Mascot 2.6 and later save the type of the searched database(s) in the results file, as db_typeX= lines in the header section. These types are AA (amino acid), NA (nucleic acid) or SL (spectral library).

In MSR format, introduced in Mascot Server 3.0, the 'db_type' column is always present in the search__databases table.

The number of databases is ms_searchparams::getNumberOfDatabases(), so idx should be between 1 and getNumberOfDatabases().

Spectral libraries must have a reference database. If the reference database is not part of the actual search, protein accessions mapped to it have a database number above ms_searchparams::getNumberOfDatabases(). For example, if the search contains one AA database and one spectral library, getNumberOfDatabases() is 2 and the types returned by getDatabaseType() are AA (idx = 1) and SL (idx = 2). The reference database is at index 3 with type SLREF.

To find the number of the reference database of a spectral library, see ms_mascotresfilebase::geReferenceDatabaseNumberOfSL().

Parameters

idx	index of the database; must normally be between 1 and ms_searchparams::getNumberOfDatabases(), or a valid database number returned by ms_mascotresfilebase::getReferenceDatabaseNumberOfSL()

Returns: database type if available. If idx is out of range or isDatabaseTypeAvailable() is false, returns AA.

Implements ms_mascotresfilebase.

◆ getDate()

int getDate ( ) const

overridevirtual

Returns the date and time of the search in seconds since midnight January 1st 1970.

In dat28 format, obtained from the date= line in the header section of the file.

In MSR format, obtained from the 'date' row in the search__header table.

Can be converted to day, month, year etc. using gmtime or similar functions.

Returns: the date and time of the search in seconds since midnight January 1st 1970.

Implements ms_mascotresfilebase.

◆ getDecoyTypeForDB()

ms_mascotoptions::DECOY_ALGORITHM getDecoyTypeForDB ( const int idx = 1 ) const

overridevirtual

Returns the decoy algorithm type for a given database.

In dat28 format, the decoy algorithm type is saved as decoy_type= or decoy_typeX= in the header section, depending on Mascot version.

In MSR format, the algorithm type is saved as the 'decoy_type' column in the search__databases table.

If idx = 1, the method returns the value of decoy_type=. If idx > 1, the method returns the corresponding decoy_typeX= line, or if one doesn't exist, falls back on decoy_type=.

If there is no suitable value in the file or idx is outside its range, the method returns ms_mascotoptions::DECOY_ALGORITHM_NONE.

Parameters

idx	index of the database from 1 to ms_searchparams::getNumberOfDatabases().

Returns: the decoy algorithm type, or ms_mascotoptions::DECOY_ALGORITHM_NONE.

Implements ms_mascotresfilebase.

◆ getEnzyme()

bool getEnzyme	(	ms_enzymefile *	efile,
		const char *	enzymeFileName = `0`
	)		const

overridevirtual

Returns an object that represents the embedded enzyme file as a reduced enzymes file.

In dat28 format, for data files created with Mascot 2.2 and later, the full definition of the enzyme used is included in the Mascot results file. For earlier versions of Mascot, just the name is recorded. This function attempts to read the definition from the results file. If the definition is not present in the results file and a path to the enzymes file has been passed, then this function reads the enzymes file and removes all entries from the list in memory apart from the one with the name specified in the results file.

In MSR format, the full definition of the enzyme used in the search is included in the Mascot results file.

To determine whether the content has been parsed successfully call ms_enzymefile::isValid.

See Object initialising functions in Perl, Java, Python and C#.

Parameters

efile	a pointer to enzymes-file object that will accept the content from the embedded file or the extenal enzymes file if necessary. If successful, the enzyme itself can be retrieved by passing an index of zero to ms_enzymefile::getEnzymeByNumber()
enzymeFileName	is only used for results files prior to Mascot 2.2

Returns: True if the embedded file exists in the results file or if the enzyme specified in the results file can be loaded from the external enzymes file.

Implements ms_mascotresfilebase.

◆ getErrorHandler()

const ms_errs * getErrorHandler ( ) const

inherited

Retrive the error object using this function to get access to all errors and error parameters.

See Error Handling.

Returns: Constant pointer to the error handler

See also: isValid(), getLastError(), getLastErrorString(), clearAllErrors(), getErrorHandler()

Examples: common_error.cpp, and http_helper_getstring.cpp.

◆ getErrorInfoAsString()

std::string getErrorInfoAsString ( const int num ) const

protectedinherited

For saving any errors in the .cdb file

Parameters

num	1..getNumberOfErrors()

Returns: "[Error Number]:[Number of times]:[Error string]"

◆ getErrorNumber()

int getErrorNumber ( const int num = -1 ) const

inherited

Return a specific error number - or ms_errs::ERR_NO_ERROR.

All errors are accumulated into a list in this object, until clearAllErrors() is called.

Errors in other classes are accumulated here. If, for example, there is an error when creating a peptide summary, the errors need to be accessed through this class.

See Error Handling.

See also: getNumberOfErrors(), clearAllErrors(), getErrorNumber(), getErrorString()

In Mascot Parser 2.5 and later, this is implemented by calling: ms_errs::getErrorNumber()

Parameters

num	is the error number in the range 1..getNumberOfErrors(). Passing a value of -1 will return the last error, or ERR_NO_ERROR. If an invalid number is passed, ERR_NO_ERROR will be returned (and no error will be added to the list of errors!).

Returns: the error number

Examples: resfile_error.cpp, and resfile_summary.cpp.

◆ getErrorString()

std::string getErrorString ( const int num ) const

inherited

Return a specific error as a string.

All errors are accumulated into a list in this object, until clearAllErrors() is called. To return a particular error, call this function with a number 1..getNumberOfErrors(). Passing a value of -1 will return the last error, or an empty string. If an invalid number is passed an empty string will be returned (and no error will be added to the list of errors!).

Errors in other classes are accumulated here. If, for example, there is an error when creating a peptide summary, the errors need to be accessed through this class.

In Mascot Parser 2.5 and later, this is implemented by calling ms_errs::getErrorString but functionality is identical to previous versions.

See Error Handling.

See also: getNumberOfErrors(), clearAllErrors(), getErrorNumber(), getErrorString()

Parameters

num	1 to number of errors, or -1

Returns: error string for the given number, or the last error for -1, empty string if none

Examples: resfile_error.cpp, and resfile_summary.cpp.

◆ getExecTime()

int getExecTime ( ) const

overridevirtual

Returns the time taken for the search.

In dat28 format, obtained from the exec_time= line in the header section.

In MSR format, obtained from the 'exec_time' row in the search__header table.

This is the 'wall clock' time, not the CPU time.

Returns: execution time in seconds

Implements ms_mascotresfilebase.

◆ getFastaPath()

std::string getFastaPath ( int idx = 1 ) const

overridevirtual

Returns the path to the FASTA file used.

Available in Mascot 2.2 and later.

Mascot 2.6 and later support spectral libraries. Each spectral library must have a reference database into which found peptide sequences are mapped at the end of the search. The "effective" reference database could be one of the protein sequence databases searched, or it could be a separate database used only for lookup purposes. You can find the database number of the reference database with ms_mascotresfilebase::getReferenceDatabaseNumberOfSL(). If this is larger than getNumberOfDatabases(), the FASTA file path is obtained from the library_reference_fastafile line in the results file header.

Parameters

idx	index of the database from 1 to ms_searchparams::getNumberOfDatabases() for databases or libraries searched, or an index returned by ms_mascotresfilebase::getReferenceDatabaseNumberOfSL().

Returns: The full path to the database or library file used in the search.

Implements ms_mascotresfilebase.

◆ getFastaVer()

std::string getFastaVer ( int idx = 1 ) const

overridevirtual

Returns the FASTA file version.

Mascot 2.6 and later support spectral libraries. Each spectral library must have a reference database into which found peptide sequences are mapped at the end of the search. The "effective" reference database could be one of the protein sequence databases searched, or it could be a separate database used only for lookup purposes. You can find the database number of the reference database with ms_mascotresfilebase::getReferenceDatabaseNumberOfSL(). If this is larger than getNumberOfDatabases(), the FASTA file version is obtained from the library_reference_release line in the results file header.

Parameters

idx	index of the database from 1 to ms_searchparams::getNumberOfDatabases() for databases or libraries searched, or an index returned by ms_mascotresfilebase::getReferenceDatabaseNumberOfSL().

Returns: File name of the database or library searched.

Implements ms_mascotresfilebase.

◆ getFileName()

std::string getFileName ( const int id = 1 ) const

overridevirtual

Returns the name of the results file passed into the constructor.

Parameters

id	a 1 based index. Unless appendResfile() has been called, this value must be '1'.

Returns: the file name (or file path) of the results file.

Implements ms_mascotresfilebase.

◆ getFirstPassThreshold()

double getFirstPassThreshold ( ) const

overridevirtual

Return the threshold value for the first pass of an automated error tolerant search.

Return the first pass threshold of an automated error tolerant search. This is the significance threshold used at the end of the first pass to select proteins for the second pass.

In Mascot Server 2.7 and earlier, the first pass threshold was always 0.05.

In Mascot Server 2.8 and later, you can specify a target FDR in the search form. If the search is an error tolerant target-decoy search with target FDR, the first pass threshold can differ from 0.05.

See Score thresholds and score filtering (Mascot Server 2.8 and later).

Returns: First pass threshold, or 0.0 if this is not an integrated error tolerant search.

Implements ms_mascotresfilebase.

◆ getHeaderKeyValues()

void getHeaderKeyValues	(	std::vector< std::string > &	keys,
		std::vector< std::string > &	values
	)		const

overridevirtual

Return all the header key-value pairs.

Get all the key-value pairs of the results header. The header contains data such as: number of queries, exec_time (search duration), database types (AA, NA, SL) and task ID.

To get the value of an individual header key, use ms_mascotresfilebase::getHeaderValue().

Parameters

[out]	keys	A vector of non-empty keys.
[out]	values	A vector of strings (some may be empty) in the same order as keys.

Implements ms_mascotresfilebase.

◆ getHeaderValue()

std::string getHeaderValue ( const std::string & key ) const

overridevirtual

Return the header value for the given key.

Get the value associated with the input key in the results header. To get all the values, use ms_mascotresfilebase::getHeaderKeyValues().

Parameters

[in] key A non-empty string.

Returns: the value associated to the key, or empty if the key does not exist.

Implements ms_mascotresfilebase.

◆ getInputQuery()

ms_inputquery getInputQuery ( const int queryNum ) const

overridevirtual

Return the ms_inputquery object for the query given as argument.

This method call is equivalent to creating an ms_inputquery object with the current results file and queryNum as parameter.

Parameters

queryNum is the query number

Returns: ms_inputquery object

Implements ms_mascotresfilebase.

◆ getJobNumber()

int getJobNumber ( const int resfileID = 1 ) const

overridevirtual

Return the job number for this file - obtained from the file name.

The library can only 'guess' at this since the value is not in the results file. To perform this function, it retrieves the job number from the file name, so be warned about changing file names. The function returns 0 if it cannot determine the job number.

Parameters

resfileID is the the 1 based id of the results file. If multiple files have been merged together with appendResfile(), use the file ID returned by appendResfile() or getSrcFileIdForMultiFile() to access the job number of the appended files.

Returns: the derived job number.

Implements ms_mascotresfilebase.

◆ getKeepAlive()

void getKeepAlive	(	KA_TASK &	kaTask,
		int &	kaPercentage,
		std::string &	kaAccession,
		int &	kaHit,
		int &	kaQuery,
		std::string &	kaText
	)		const

inherited

Return the progress indicators used by the keepAlive functions.

See Multiple return values in Perl, Java, Python and C# although there may be issues with some languages and the kaTask parameter.

It is normally easier for client applications to call ms_mascotresults::getCreateSummaryProgress() or outputKeepAlive() than to call this function.

Parameters

kaTask	is the task currently being performed by Mascot Parser. If Parser is doing nothing, then this will be the last task that was completed and kaPercentage will be 100
kaPercentage	is the percentage (0..100) complete for the current kaTask.
kaAccession	is the current 'accession' being processed. See outputKeepAlive() for details of which tasks set this value
kaHit	is the current hit being processed. See outputKeepAlive() for details of which tasks set this value
kaQuery	is the current 'query' being processed. See outputKeepAlive() for details of which tasks set this value
kaText	is the text that would be output by outputKeepAlive()

◆ getLastError()

int getLastError ( ) const

inherited

Return the last error number - or ms_erros::ERR_NO_ERROR.

Same as calling getErrorNumber() with -1 as a parameter.

Returns: error number

Examples: peptide_list.cpp, resfile_error.cpp, and resfile_summary.cpp.

◆ getLastErrorString()

std::string getLastErrorString ( ) const

inherited

Return the last error number - or an empty string.

Same as calling getErrorString() with -1 as a parameter.

Returns: last error string

Examples: peptide_list.cpp, repeat_search.cpp, resfile_error.cpp, resfile_info.cpp, resfile_input.cpp, and resfile_params.cpp.

◆ getLibraryMods()

int getLibraryMods	(	std::vector< std::string > &	modNames,
		std::vector< double > &	modDeltas
	)		const

overridevirtual

Return all the library mod names and deltas.

Get a list of all library modifications. If multiple spectral libraries were searched, this is the combined list of modifications.

Parameters

[out]	modNames	Library modification names.
[out]	modDeltas	Library modification deltas.

Returns: the number of modifications, or 0 if there are none.

Implements ms_mascotresfilebase.

◆ getMascotVer()

std::string getMascotVer ( ) const

overridevirtual

Returns the version of Mascot used to perform the search.

In dat28 format, obtained from the version= entry in the header section of the file.

In MSR format, obtained from the 'version' row in the search__header table.

See also: versionGreaterOrEqual

Returns: the version of Mascot used to perform the search.

Implements ms_mascotresfilebase.

◆ getMasses()

bool getMasses ( ms_masses * masses ) const

inherited

Returns an ms_masses object from the mass values in the results file.

For results files from Mascot 2.2 and later, this function simply calls

    if (getUnimod(&umodConfigFile) && umodConfigFile.isValid())
    {
        masses->copyFrom(&umodConfigFile);
    }

For earlier results files in dat28 format, it reads the residue mass values from the masses section of the file. Since this section either contains average or monoisotopic masses (but not both), the resulting ms_masses object will only have one set of masses.

See Object initialising functions in Perl, Java, Python and C#.

Parameters

masses a pointer to a valid masses object that will accept the content from the section.

Returns: true always.

◆ getMassesKeyValues()

void getMassesKeyValues	(	std::vector< std::string > &	keys,
		std::vector< double > &	values
	)		const

overridevirtual

Return all the residue and modification masses as key-value pairs.

Get all the modification and residue masses as key-value pairs. This includes:

Residue masses (A, B, C, D, etc.)
Terminus masses (N-term, C-term)
Element and atomic masses (H, O, electron, etc.)
Variable modification deltas (delta1, delta2, etc.)
Fixed modification deltas (FixedMod1, FixedMod2, etc.)
Fragment neutral loss (NeutralLoss1, NeutralLoss2, etc.)
Peptide neutral loss (PepNeutralLoss1, PepNeutralLoss2, etc.)
Required peptide neutral loss (ReqPepNeutralLoss1, ReqPepNeutralLoss2, etc.)
Ignore masses (Ignore1, Ignore2, etc.)

To get the value of an individual key, use ms_mascotresfilebase::getMassValue().

In general, it is easier to access these values through ms_searchparams.

Parameters

[out]	keys	A vector of non-empty keys.
[out]	values	A vector of doubles in the same order as keys.

Implements ms_mascotresfilebase.

◆ getMassValue()

double getMassValue ( const std::string & key ) const

overridevirtual

Return the residue or modification mass for the given key.

Get the value associated with the input key in the list of masses. To get all the values, use ms_mascotresfilebase::getMassKeyValues().

Parameters

[in] key A non-empty string.

Returns: the value associated to the key, or 0.0 if the key does not exist.

Implements ms_mascotresfilebase.

◆ getMonoLinkModification()

const ms_modification * getMonoLinkModification	(	const int	modNum,
		const int	monoLink
	)		const

inherited

Returns an ms_modification object that represents a monolink variable modification.

The method performs the following steps:

Fetch the the embedded unimod_xl file (ms_mascotresfilebase::getUnimodXL()).
Fetch the linker name (ms_searchparams::getVarModName()) of modNum.
Find the corresponding ms_umod_modification entry in the embedded unimod_xl file.
Wrap the correct neutral loss element as an ms_modification.

The ms_modification object contains the following fields:

ms_modification::getTitle() returns the modfile-style name, like "Xlink:DSS (K)".
ms_modification::getCode() returns the monolink code.
ms_modification::getMonoLinkTitle() returns a modfile-style title containing the monolink code in square brackets, like "Xlink:DSS[W] (K)".
ms_modification::getDelta() returns the monolink delta corresponding to the monolink code (linker delta - monolink NL).
ms_modification::getPairsWith() returns the code or codes this monolink pairs with, or empty string if not defined.
ms_modification::isGeneratedMonoLinker() returns true.
ms_modification::isLoopLinker() returns true if the monolink NL is zero; otherwise false.
The neutral loss list is empty.

Parameters

modNum	Variable mod index in range 1..32. Usually this comes from the peptide's variable mods string.
monoLink	Index of the neutral loss element. Usually this comes from the peptide's monolink string.

Returns: a pointer, or null if this isn't a linker or the monolink index is invalid.

◆ getMSParserVersion()

std::string getMSParserVersion ( ) const

inherited

Returns the version number of the Mascot Parser library.

This version information is also available:

In Windows from the Mascot Parser DLL in the version 'tab'
From Perl using perl -Mmsparser -e "print msparser->VERSION()"

From Java using:

    JarFile jar = new JarFile(new File(jarName));
    Manifest jarManifest = jar.getManifest();
    Attributes mainAttributes = jarManifest.getMainAttributes();
    String version = (String) mainAttributes.get(Attributes.Name.IMPLEMENTATION_VERSION);

Returns: the version number as a string.

◆ getMultiFileQueryNumber()

int getMultiFileQueryNumber	(	const int	localQuery,
		const int	fileId
	)		const

overridevirtual

Return the multi-file query number from the local query number in an appended file.

See Multiple return values in Perl, Java, Python and C#.

Needs to be called on the 'primary' file object rather than on a ms_mascotresfile_dat or ms_mascotresfile_msr object returned by the getResfile() function.

See Combining multiple results files.

Example: Assume that the primary results file has 10 queries, file 2 has 20 queries and file 3 has 30 queries. This function will return the following:

localQuery	fileId	returned query
6	1	6
11	2	21
1	3	31

See also: getSrcQueryAndFileIdForMultiFile() for the 'inverse' function

Parameters

localQuery	is the query number which should be a value between 1 and getNumQueries() for the file specified by fileId.
fileId	is a 1 based index to the source file.

Returns: the query number that should be used for the primary file, or -1 if an invalid localQuery / fileId parameter combination is passed.

Implements ms_mascotresfilebase.

◆ getNumberOfErrors()

int getNumberOfErrors ( ) const

inherited

Return the number of errors since the last call to clearAllErrors.

This will be zero if there has been no error.

All errors are accumulated into a list in this object, until clearAllErrors() is called.

Errors in other classes are accumulated here. If, for example, there is an error when creating a peptide summary, the errors need to be accessed through this class.

From version 2.5, implemented by calling getErrorHandler()->getNumberOfErrors()

See Error Handling.

See also: getNumberOfErrors(), clearAllErrors(), getErrorNumber(), getErrorString()

Returns: number of errors

Examples: resfile_error.cpp, and resfile_summary.cpp.

◆ getNumberOfResfiles()

int getNumberOfResfiles ( ) const

overridevirtual

Multiple results files can be summed together and treated as 'one'.

See Combining multiple results files.

Thread safe: This method is safe to use from multiple threads. See also Using Parser in multithreaded applications.

Returns: the number of results files that have been combined together. If appendResfile() has not been called then this function will return a value of 1.

Implements ms_mascotresfilebase.

◆ getNumEtSeqsSearched()

int getNumEtSeqsSearched ( const int idx = 0 ) const

overridevirtual

Returns the number of sequences searched in the second pass of an integrated error tolerant search.

In dat28 format, the value is obtained from the et_sequences= or et_sequencesX= line in the header section of the file.

In MSR format, the value is obtained from the 'et_sequences' column in the search__databases table.

See also: getNumSeqs(), getNumSeqsAfterTax() getNumResidues()

See Integrated error tolerant search . This function will return -1 for the Original error tolerant search and for searches prior to Mascot 2.4.1

Parameters

idx index of the database. Specifying a value of 0 (the default) will return the sum of all sequences after taxonomy in all FASTA files searched. Otherwise, the value should be in the range from 1 to ms_searchparams::getNumberOfDatabases(). Specifying a value outside the range of 0..ms_searchparams::getNumberOfDatabases() will result in -1 being returned. If the database at index idx is a spectral library, the value returned is -1.

Returns: the number of sequences that were searched in the second pass of an Integrated error tolerant search

Implements ms_mascotresfilebase.

◆ getNumLibraryEntries()

int getNumLibraryEntries ( const int idx = 0 ) const

overridevirtual

Returns the number of entries in the spectral library searched.

In dat28 format, the value is obtained from the library_entriesX= line in the header section of the file. Spectral library support was added in Mascot 2.6.

In MSR format, the value is obtained by summing up the values of the 'entries' column in the search__spectral_libraries table.

Parameters

idx index of the database. Specifying a value of 0 (the default) will return the sum of all library entries searched. Otherwise, the value should be in the range from 1 to ms_searchparams::getNumberOfDatabases(). Specifying a value outside the range of 0..ms_searchparams::getNumberOfDatabases() will result in -1 being returned. If the database at index idx is not a spectral library, the value returned is -1.

Returns: the number of entries in the spectral library.

Implements ms_mascotresfilebase.

◆ getNumQueries()

int getNumQueries ( const int resfileID = 0 ) const

overridevirtual

Returns the number of queries (peptide masses or ms-ms spectra).

Obtained from the queries= line in the header section of the file (dat28 format) or by getting the maximum value of the 'query_id' column in the query__data table (MSR format).

Thread safe: This method is safe to use from multiple threads. See also Using Parser in multithreaded applications.

Parameters

resfileID is the the 1 based id of the results file. When the default value of 0 is used for a single results file, this is number of queries in the file. For Combining multiple results files supplying a value of zero returns the total number of queries in all the results files that have been combined. Use a value of 1 to get the number of queries just in the first results file.

Returns: the number of queries or -1 if resfileID is invalid

Implements ms_mascotresfilebase.

◆ getNumResidues()

double getNumResidues ( const int idx = 0 ) const

overridevirtual

Returns the number of residues in the FASTA file(s) searched.

In dat28 format, the value is obtained from the residues= or residuesX= line in the header section of the file. Multiple FASTA file support was added in Mascot 2.3.

In MSR format, the value is obtained from the 'residues' column of the search__databases table.

See also: getNumSeqs(), getNumSeqsAfterTax()

Parameters

idx index of the database. Specifying a value of 0 (the default) will return the sum of all sequences after taxonomy in all FASTA files searched. Otherwise, the value should be in the range from 1 to ms_searchparams::getNumberOfDatabases(). Specifying a value outside the range of 0..ms_searchparams::getNumberOfDatabases() will result in -1 being returned. If the database at index idx is a spectral library, the value returned is 0.

Returns: the number of residues in the FASTA file searched. The value is returned as a double, because this method was introduced with 32-bit versions of Parser. These were unable to return an integer larger than 32 bits.

Implements ms_mascotresfilebase.

◆ getNumSeqs()

int getNumSeqs ( const int idx = 0 ) const

overridevirtual

Returns the number of sequences in the FASTA file(s) searched.

In dat28 format, the value is obtained from the sequences= or sequencesX= in the header section of the file. Multiple FASTA file support was added in Mascot 2.3.

In MSR format, the value is obainted from the 'sequences' column in the search__databases table.

See also: getNumSeqsAfterTax(), getNumResidues(), getNumLibraryEntries()

Parameters

idx index of the database. Specifying a value of 0 (the default) will return the sum of all sequences in all FASTA files searched. Otherwise, the value should be in the range from 1 to ms_searchparams::getNumberOfDatabases(). Specifying a value outside the range of 0..ms_searchparams::getNumberOfDatabases() will result in -1 being returned. If the database at index idx is a spectral library, the value returned is 0.

Returns: the number of sequences in the FASTA file(s).

Implements ms_mascotresfilebase.

◆ getNumSeqsAfterTax()

int getNumSeqsAfterTax ( const int idx = 0 ) const

overridevirtual

Returns the number of sequences that passed the taxonomy filter in the FASTA file(s) searched.

In dat28 format, the value is obtained from the sequences_after_tax= or sequences_after_taxX= line in the header section of the file. Multiple FASTA file support was added in Mascot 2.3.

In MSR format, the value is obtained from the 'sequences_after_tax' column of the search__databases table.

See also: getNumSeqs(), getNumResidues(), getNumLibraryEntries()

Parameters

idx index of the database. Specifying a value of 0 (the default) will return the sum of all sequences after taxonomy in all FASTA files searched. Otherwise, the value should be in the range from 1 to ms_searchparams::getNumberOfDatabases(). Specifying a value outside the range of 0..ms_searchparams::getNumberOfDatabases() will result in -1 being returned. If the database at index idx is a spectral library, the value returned is 0.

Returns: the number of sequences that passed the taxonomy filter in the FASTA file(s) searched.

Implements ms_mascotresfilebase.

◆ getObservedCharge()

int getObservedCharge	(	const int	query,
		const bool	decoy = `false`
	)		const

overridevirtual

The 'charge' returned will be 0 for Mr, otherwise it will be 1, -1, 2, -2, 3, -3 etc. and -100 for an error.

In dat28 format, this is obtained from the qexp[query] value. It will come from the SEC_SUMMARY section. If decoy is set to true, it is obtained from the SEC_DECOYSUMMARY section.

In MSR format, the observed charge is obtained from the query__summary table. If decoy is false, the value comes from the standard, target pass of the search; decoy is true, from the standard, decoy pass.

The 'charge' returned will be 0 for Mr, otherwise it will be 1, -1, 2, -2, 3, -3 etc. and -100 for an error.

Possible error values:

If an 'ambiguous' charge state is specified for the whole search or for a specific query, then Mascot just records matches for the highest scoring charge state, and it is this charge state that is returned from this function. For example, the search may have been performed with "2+, 3+ or 4+" and ms_inputquery::getCharge() will return "2+, 3+ or 4+". If the highest scoring peptide match for a particular query was to charge state 4+, then all top 10 matches for that query will be for 4+ and this function will return '4'.

It is therefore not impossible to get different charge values for standard peptide matches from the decoy and target passes of the results files.

In dat28 format, this method can only read charge from the 'summary' and 'decoy_summary' sections. In MSR format, this method can only read charge for standard target or decoy peptide matches. If the peptide match type is error tolerant or crosslink, it's best to use ms_peptide::getCharge(), as these can have different charge state from the standard peptide matches in this query.

The functions getObservedIntensity() and getObservedMass() do not require the decoy parameter as the values will be identical from target and decoy passes.

See also: getObservedMrValue

Parameters

query	is a number in the range 1..getNumQueries()
decoy	should be false for target and true for decoy matches.

Returns: the observed charge for the peptide.

Implements ms_mascotresfilebase.

◆ getObservedIntensity()

double getObservedIntensity ( const int query ) const

overridevirtual

Returns the experimental intensity for the peptide.

In dat28 format, this is obtained from SEC_SUMMARY - qintensity[query]. In MSR format, from the query__summary table.

The observed intensity is not always available and does not need to be supplied by the end user.

Returns 0 if the query cannot be found and sets the error ms_errs::ERR_QUERYOUTOFRANGE.

Parameters

query is a number in the range 1..getNumQueries()

Returns: 0 if the intensity value is not available.

Implements ms_mascotresfilebase.

◆ getObservedMass()

double getObservedMass ( const int query ) const

overridevirtual

Returns the experimental mass value as entered by the user.

In dat28 format, this is obtained from SEC_SUMMARY - qexp[query].

In MSR format, this is obtained from the query__summary table.

Returns 0 if the value cannot be found and sets the error ms_errs::ERR_QUERYOUTOFRANGE.

Parameters

query query number

Returns: the observed peptide mass.

Implements ms_mascotresfilebase.

◆ getObservedMrValue()

double getObservedMrValue	(	const int	query,
		const bool	decoy = `false`
	)		const

overridevirtual

Returns the experimental mass value (as a relative mass) as entered by the user.

In dat28 format, this is obtained from the qmass[query] value. It will come from the SEC_SUMMARY section unless decoy is set to true in which case it is obtained from the SEC_DECOYSUMMARY section.

In MSR format, the value is obtained from the query__summary table. If decoy is false, the value comes from the standard, target pass of the search; decoy is true, from the standard, decoy pass.

See also: getObservedCharge

Returns 0 if the value cannot be found and sets the error ms_errs::ERR_QUERYOUTOFRANGE.

Parameters

query	is a number in the range 1..getNumQueries()
decoy	should only be set to true if ms_searchparams::getDECOY returns true.

Returns: the relative mass of the observed peptide.

Implements ms_mascotresfilebase.

◆ getPercolatorFileNames()

std::vector< std::string > getPercolatorFileNames ( ) const

inherited

Retrieve the filenames use for percolator input and output.

This function will return an empty vector unless setPercolatorFeatures() has been called beforehand.

The offsets into the return array are defined by ms_mascotresfilebase::PERCOLATOR_FILE_NAMES.

See Using STL vector classes vectori, vectord and VectorString in Perl, Java, Python and C#.

You can get the list of Percolator file names without creating an object by using matrix_science::ms_mascotresfilebase::staticGetPercolatorFileNames(const char*, const char*, const ms_mascotoptions&, const char *, const std::vector<std::string>&, std::vector<std::string>&, std::vector<bool>&).

Returns: the list of files.

◆ getProgressInfo()

ms_progress_info * getProgressInfo ( bool forPeptideSummary = false ) const

inherited

If a matrix_science::ms_progress_info object is passed to the constructor, this is returned here.

Parameters

forPeptideSummary should be set to true to get the progress object used when creating the ms_peptidesummary, or false to return the object used when creating the ms_mascotresfilebase object.

Returns: a pointer to the progress information. This will be null if no progressMonitor is passed in the constructor

◆ getQmatch()

int64_t getQmatch	(	const int	query,
		const ms_peptide::PSM_TYPE	pepType
	)		const

overridevirtual

Return the number of peptide masses within precursor tolerance of this query.

Return the 'qmatch' value of the query. This is the count of trials for the query, where a trial is a candidate peptide sequence + modifications whose mass is within precursor tolerance.

The count of trials could be different depending on the peptide type. For example, error tolerant peptide matches normally have much higher count of trials than peptides from the first pass of the search.

Note: This method used to be defined in ms_peptidesummary::getQmatch(). It was moved to ms_mascotresfilebase in Parser 3.0.

Parameters

query	Query number, 1..getNumQueries().
pepType	Peptide match type.

Returns: qmatch value for the query and peptide match type.

Implements ms_mascotresfilebase.

◆ getQplughole()

double getQplughole	(	const int	query,
		const ms_peptide::PSM_TYPE	pepType
	)		const

overridevirtual

Return the threshold score for homologous peptide match (MIS only).

Return the 'qplughole' value of the query. This is the critical value for calculating the homology threshold. The value could be different depending on peptide type, as the emprical score distribution within a query can be different between (for example) the first and second pass of an error tolerant search.

Parameters

query	Query number, 1..getNumQueries().
pepType	Peptide match type.

Returns: qplughole value for the query and peptide match type.

Implements ms_mascotresfilebase.

◆ getQuantitation()

bool getQuantitation ( ms_quant_configfile * qfile ) const

overridevirtual

Returns an object that represents the embedded quantitation file as a reduced quantitation.xml file.

The return value indicates that the embedded quantitation file exists in the results file. Call ms_quant_configfile::isValid to determine whether the XML part has been parsed successfully.

For quantitation_2 and later, the contents of the file are validated against a schema by default. For quantitation_1, to explicitly validate against a schema, use ms_quant_configfile::setSchemaFileName() to choose a schema, and then use ms_quant_configfile::validateDocument() to validate.

See Object initialising functions in Perl, Java, Python and C#.

Deprecated:: See getQuantitationMethod() which is generally easier to use.

Parameters

qfile a pointer to quantitation file object. This must be a valid pointer to a valid object, which should normally be created using the default constructor: ms_quant_configfile::ms_quant_configfile

Returns: true if embedded file exists and false if it doesn't

Implements ms_mascotresfilebase.

◆ getQuantitationMethod()

bool getQuantitationMethod ( ms_quant_method * qm ) const

inherited

Return the quantitation method object from the embedded quantitation file.

This method returns true if all of the following apply:

the embedded quantitation file exists;
a valid schema file location has been set using the XMLschemaDirectory parameter in the constructor or the file exists in the default location;
the embedded quantitation file validates against the schema;
the quantitation method named in the QUANTITATION parameter exists;
the quantitation method can be loaded.

Otherwise the method returns false.

If the QUANTITATION parameter is empty or equals "none", then the method simply returns false. Otherwise, on failure, the method sets the warning ms_errors::ERR_MSP_QUANT_FAILEDLOAD.

Parameters

qm	A pointer to quantitation method object. This must be a valid pointer to a valid object, which should normally be created using the default constructor ms_quant_method::ms_quant_method.

Returns: True if the method was loaded; false otherwise.

◆ getReferenceDatabaseNumberOfSL()

int getReferenceDatabaseNumberOfSL ( const int idx ) const

overridevirtual

Return the database number of the reference database of a spectral library.

The reference database of a spectral library is either one of the databases searched – if the reference database was part of the actual search – or a virtual database whose number is above ms_searchparams::getNumberOfDatabases(). In the first case, getReferenceDatabaseNumberOfSL() returns a database number between 1 and ms_searchparams::getNumberOfDatabases(). In the second case, the number is above getNumberOfDatabases().

If idx does not refer to a spectral library, the method returns -1.

Parameters

idx	Database number of the spectral library of interest, between 1 and ms_searchparams::getNumberOfDatabases() and whose type is SL (see getDatabaseType())

Returns: Database number of the reference database of the spectral library, or -1 if idx is not a spectral library.

Implements ms_mascotresfilebase.

◆ getRepeatSearchString()

std::string getRepeatSearchString	(	const int	query,
		const bool	fullQuery = `false`
	)		const

overridevirtual

To perform a repeat search need to build up appropriate string.

If the 'fullQuery' parameter is false (the default) then the format will be:

mr from(observed, charge) query(querynum) etc.

If the 'fullQuery' parameter is true then the format will be:

mr from(observer, charge1, charge2...) ions() etc.

where 'etc' will be one or more of the following (split onto several lines here for readability):

 intensity(value) peptol(value, units) seq() comp()  tag() etag() 
 title() instrument() it_mods() index() rtinseconds() rtinseconds[x]() 
 scans scans[x]() rawscans rawscans[x]()

from contains the observed mass, and the charge found in the original search. If the fullQuery parameter is true, then the charge parameter may be a list of charge states to consider, in which case the mr value is for the first charge.
intensity will be returned if an intensity for the peptide was entered.
peptol will be returned if there is a specific tolerance override for this query. In dat28 format, it is taken from the PepTol= line in the queryx section of the results file. In MSR format, from the 'pep_tol' column in the query__data table.
seq() will be returned if there was a sequence query. It is the exact text that was entered by the user. In dat28 format, it comes from seq1= line in the queryx section of the results file. If there were multiple seq() commands in the original search, then these will be in the results file as seq1=, seq2= etc., and will be returned as seq(...) seq(...). In MSR format, the values are selected from the query__seq table.
comp() will be returned if there was a composition query. It is the exact text that was entered by the user. In dat28 format, it comes from comp1= line in the queryx section of the results file. If there were multiple comp() commands in the original search, then these will be in the results file as comp1=, comp2= etc., and will be returned as comp(...) comp(...). In MSR format, the values are selected from the query__comp table.
tag() will be returned if there was a tag query. It is the exact text that was entered by the user. In dat28 format, it comes from tag1=t line in the queryx section of the results file. If there were multiple tag() commands in the original search, then these will be in the results file as tag1=, tag2= etc., and will be returned as tag(...) tag(...). In MSR format, the values are selected from the query__seq_tag table.
etag() will be returned if there was a etag query. It is the exact text that was entered by the user. In dat28 format, it comes from tag1=e line in the queryx section of the results file. If there were multiple etag() commands in the original search, then these will be in the results file as tag1=, tag2= etc., and will be returned as etag(...) etag(...). In MSR format, the values are selected from the query__seq_tag table.
title will be returned if there was a title for the particular MS-MS spectrum. The title is returned as an escaped string.
instrument will be returned if there was an instrument defined at the query level in the original search. It is returned as an escaped string.
it_mods will be returned if modifications were defined at the query level in the original search. If there was more than modification, these will be returned as a comma separated list.
index will be returned if there was an index defined at the query level in the original search which will be the case for all searches in Mascot 2.3 and later. See ms_inputquery::getIndex.
scans or scans[x] will be returned if these were defined at the query level in the original search. They will have the format scans(29-34, 43) or scans[0](29-34) scans[1](43).
rtinseconds or rtinseconds[x] will be returned if these were defined at the query level in the original search. They will have the format rtinseconds(10-20, 25) or rtinseconds[0](10-20) rtinseconds[1](25).
rawscans or rawscans[x] will be returned if these were defined at the query level in the original search. They will have the format, for example, of: rawscans[0](pd0cy1ex1:pd0cy1ex3) rawscans[1](fn2ix1).
rawfile will be returned if these were defined at the query level in the original search. They will have the format, for example, of: rawfile(c:/data/rawfile.raw).
locus will be returned if these were defined at the query level in the original search. They will have the format, for example, of: locus(2.1.1.24.1).
query is only used for MS-MS spectra. To save data transfer with a repeat search, this command is used instead of resubmitting all the MS-MS ions values. When nph-mascot.exe comes to the query(x) command it gets the ions vales from the original .dat file
ions will be used to give a list of peaks.

Returns 0 if the value cannot be found and sets the error ms_errs::ERR_QUERYOUTOFRANGE.

See Automated repeating of searches.

Parameters

query	is a number in the range 1..getNumQueries()
fullQuery	If true, then a complete and self contained sequence query will be returned. See above for details

Returns: repeat search string

Implements ms_mascotresfilebase.

◆ getSearchParameter()

std::string getSearchParameter ( const std::string & key ) const

overridevirtual

Return the search parameter the given key.

Get the value associated with the input key in the search parameters. To get all the values, use ms_mascotresfilebase::getSearchParameterKeyValues().

Parameters

[in] key A non-empty string.

Returns: the value associated to the key, or empty if the key does not exist.

Implements ms_mascotresfilebase.

◆ getSearchParametersKeyValues()

void getSearchParametersKeyValues	(	std::vector< std::string > &	keys,
		std::vector< std::string > &	values
	)		const

overridevirtual

Return all the search parameters as key-value pairs.

Get all the search parameters as key-value pairs. Search parameters are more easily accessible through ms_searchparams. This low-level method is useful for creating repeat searches, where the search parameters should just be copied as is.

To get the value of an individual header key, use ms_mascotresfilebase::getSearchParameter().

Parameters

[out]	keys	A vector of non-empty keys.
[out]	values	A vector of strings (some may be empty) in the same order as keys.

Implements ms_mascotresfilebase.

◆ getSLDatabaseNumbersOfReference()

std::vector< int > getSLDatabaseNumbersOfReference ( const int idx ) const

overridevirtual

Return the database numbers of the spectral libraries whose reference database is at the given index.

The reference database of a spectral library is either one of the databases searched – if the reference database was part of the actual search – or a virtual database whose number is above ms_searchparams::getNumberOfDatabases(). The same database can be the reference database of multiple spectral libraries.

If idx does not refer to a reference database, the method returns the empty vector.

Parameters

idx	Database number of the reference database of interest.

Returns: A vector of database numbers of spectral libraries whose reference database idx is. This vector can be empty.

Implements ms_mascotresfilebase.

◆ getSLExecCommand()

std::string getSLExecCommand ( int idx = 1 ) const

overridevirtual

Returns the library search command line and parameters (sl_exec_command).

The command line for the library search is typically like:

    ../bin/NIST/mspepsearch/MSPepSearch.exe m a P /Z 0.1 /M 0.602993 /LIB [PATH_TO_MSP_FILE] /INP [PATH_TO_MSP_FILE] /OUTTAB [PATH_TO_TSV_FILE] /HITS 10 /MinMF 0 /NumCompared /OutPrecursorMz /OutDeltaPrecursorMz /OutSpecNum

The exact contents depend on the file paths, fragment tolerance and library search options specified in mascot.dat.

In dat28 format, the command string is saved as sl_exec_commandX= line in the header section.

In MSR format, the command string is saved in the search__spectral_libraries table as 'sl_exec_command'.

If idx is outside its range, the method returns the empty string.

Parameters

idx	index of the database from 1 to ms_searchparams::getNumberOfDatabases().

Returns: the command line for the spectral library search of the given library.

Implements ms_mascotresfilebase.

◆ getSLFragmentTolerance()

double getSLFragmentTolerance ( int idx = 1 ) const

overridevirtual

Returns the effective spectral library fragment tolerance.

When a search is run against a spectral library, the effective fragment tolerance is calculated from the user-configured library fragment tolerance and the tolerance specified in the search parameters. This may be different from ms_searchparams::getITOL() and ms_searchparams::getITOLU().

The tolerance unit can be retrieved with getSLFragmentToleranceUnit().

In dat28 format, in Mascot 2.6.01 and later, the effective tolerance value and unit are saved in the header section of the results file as sl_itolX=. For files created by Mascot 2.6.00, the value is parsed from the sl_exec_commandX= line if present.

In MSR format, the effective tolerance value and unit are saved in the search__spectral_libraries table as 'itol'.

If idx is outside its range, the method returns 0.0.

Parameters

idx	index of the database from 1 to ms_searchparams::getNumberOfDatabases().

Returns: the effective fragment tolerance.

Implements ms_mascotresfilebase.

◆ getSLFragmentToleranceUnit()

std::string getSLFragmentToleranceUnit ( int idx = 1 ) const

overridevirtual

Returns the unit of the effective spectral library fragment tolerance.

When a search is run against a spectral library, the effective fragment tolerance is calculated from the user-configured library fragment tolerance and the tolerance specified in the search parameters. This may be different from ms_searchparams::getITOL() and ms_searchparams::getITOLU().

The tolerance can be retrieved with getSLFragmentTolerance().

In dat28 format, in Mascot 2.6.01 and later, the effective tolerance value and unit are saved in the header section of the results file as sl_itolX=. For files created by Mascot 2.6.00, the value is parsed from the sl_exec_commandX= line if present.

In MSR format, the effective tolerance value and unit are saved in the search__spectral_libraries table as 'itol_units'.

If idx is outside its range, the method returns 0.0.

Parameters

idx	index of the database from 1 to ms_searchparams::getNumberOfDatabases().

Returns: the tolerance unit.

Implements ms_mascotresfilebase.

◆ getSrcQueryAndFileIdForMultiFile()

bool getSrcQueryAndFileIdForMultiFile	(	const int	q,
		int &	gsqNewQuery,
		int &	gsqFileId
	)		const

overridevirtual

Return the query number and file ID in the source results file.

See Multiple return values in Perl, Java, Python and C#.

Useful for combining multiple results files (see Combining multiple results files) but also returns valid values for a single file.

Example: Assume that the primary results file has 10 queries, file 2 has 20 queries and file 3 has 30 queries. This function will return the following:

q	newQuery	fileId
6	6	1
21	11	2
31	1	3

Thread safe: This method is safe to use from multiple threads. See also Using Parser in multithreaded applications.

See also: getMultiFileQueryNumber() for the 'inverse' function

Parameters

q	is the query number which should be a value between 1 and getNumQueries().
gsqNewQuery	is used to return the query number in the specified source file.
gsqFileId	is a 1 based index to the source file.

Returns: true if the query is in the range 1..getNumQueries().

Implements ms_mascotresfilebase.

◆ getTaxonomy()

bool getTaxonomy ( ms_taxonomyfile * tfile ) const

overridevirtual

Returns an object that represents the embedded taxonomy file as a reduced taxonomy file.

The return value only indicates that the embedded file exists. If you want to find out whether the content has been parsed successfully, call the methods of matrix_science::ms_taxonomyfile.

See Object initialising functions in Perl, Java, Python and C#.

Parameters

tfile a pointer to taxonomy file object that will accept the content from the embedded taxonomy file.

Returns: true if the embedded taxonomy file was read and parsed.

Implements ms_mascotresfilebase.

◆ getUnimod()

bool getUnimod	(	ms_umod_configfile *	ufile,
		bool	useSchemaFromResfile = `false`
	)		const

overridevirtual

Returns an object that represents the embedded unimod file as a reduced unimod_2.xml file.

The return value only indicates that the embedded Unimod XML exists in the results file. If you want to find out whether the XML part has been parsed successfully, call ms_umod_configfile::isValid

See Object initialising functions in Perl, Java, Python and C#.

Parameters

ufile a pointer to unimod file object that will accept the XML content.

useSchemaFromResfile determines where the location of the XML schema is defined. If 'true', then the schema location should have been defined by specifying XMLschemaDirectory in the constructor. If 'false', then ms_umod_configfile::setSchemaFileName must have been called on ufile before calling this function. This parameter was added in Parser 2.5, and the default value is false to ensure that it is backward compatible with previous versions.

Returns: true if embedded file exists and false if it doesn't.

Implements ms_mascotresfilebase.

◆ getUnimodXL()

bool getUnimodXL	(	ms_umod_configfile *	ufile,
		bool	useSchemaFromResfile = `false`
	)		const

overridevirtual

Returns an object that represents the embedded unimod_xl file as a reduced unimod_xl.xml file.

The return value only indicates that the embedded Unimod crosslinking file exists in the results file. If you want to find out whether the XML part has been parsed successfully, call ms_umod_configfile::isValid

See Object initialising functions in Perl, Java, Python and C#.

Parameters

ufile	a pointer to unimod file object that will accept the XML content.
useSchemaFromResfile	determines where the location of the XML schema is defined. If 'true', then the schema location should have been defined by specifying XMLschemaDirectory in the constructor. If 'false', then ms_umod_configfile::setSchemaFileName must have been called on ufile before calling this function. getUnimodXL uses the same schema as ms_mascotresfilebase::getUnimod.

Returns: true if embedded file exists and false if it doesn't.

Implements ms_mascotresfilebase.

◆ getUniqueTaskID()

std::string getUniqueTaskID ( ) const

overridevirtual

Returns the unique task ID used by Mascot Daemon.

Although this value is a number, it is a 64 bit integer. Some languages on some platforms cannot deal with 64 bit integers properly, so the value is returned as a string. For searches with no taskid, an empty string is returned.

Returns: unique task id as a string

Implements ms_mascotresfilebase.

◆ getXMLschemaFilePath()

std::string getXMLschemaFilePath ( XML_SCHEMA XMLschema ) const

inherited

Gets the XML schema to be used by functions using quantitation or unimod.

See also: setXMLschemaFilePath

Parameters

XMLschema The XML_SCHEMA enumeration value of the required xml schema file.

Returns: The requested xml schema value or an empty string if it has not been set.

◆ hasEnzyme()

bool hasEnzyme ( ) const

overridevirtual

Return true if the results file contains information about the enzyme used.

Check whether the results file contains enzyme information as an embedded 'enzymes' file.

Returns: true if the file contains enzyme information. Always true for results from Mascot Server 2.2 and later.

Implements ms_mascotresfilebase.

◆ hasQuantitation()

bool hasQuantitation ( ) const

overridevirtual

Return true if the results file contains quantitation data.

Check whether the results file contains an embedded quantitation method.

Returns: true if the file has an embedded quantitation method.

Implements ms_mascotresfilebase.

◆ hasRT()

bool hasRT ( ) const

overridevirtual

Return true if the results file contains retention time data.

Check whether the first query has retention time stored in the RTINSECONDS field. If it does, return true. The implicit assumption is that all the other queries also have (or don't have) RTINSECONDS if the first query has (or doesn't have).

Returns: true if the file contains retention time data.

Implements ms_mascotresfilebase.

◆ isDatabaseTypeAvailable()

bool isDatabaseTypeAvailable ( ) const

overridevirtual

Check whether database types are available.

In dat28 format, Mascot 2.6 and later save the type of the database(s) in the results file, as db_typeX= lines in the header section. If the types are not available, the database or databases searched could be AA or NA.

In MSR format, introduced in Mascot Server 3.0, the 'db_type' column is always present in the search__databases table.

Returns: Whether the db_typeX= lines exist or not in the dat28 results file. Always true in MSR format. false.

Implements ms_mascotresfilebase.

◆ isErrorTolerant()

bool isErrorTolerant ( ) const

overridevirtual

Returns true if the search was an error tolerant search.

In dat28 format, obtained from the ERRORTOLERANT value in the parameters section. In MSR format, obtained from the ERRORTOLERANT value in the search__parameters table.

In Mascot versions 1.8 and later, an error tolerant search can be run as a repeat search. In this case, one or more ACCESSIONs (which may be retrieved using ms_searchparams::getACCESSION ) must have been specified, and the results file will just contain the error tolerant search results. In Mascot 2.2 and later, a single search can be performed which contains both the standard search results and the error tolerant search results of automatically selected proteins. In this case, ms_searchparams::getACCESSION will return an empty string.

See Error tolerant searches.

See also: https://www.matrixscience.com/help/error_tolerant_help.html

Returns: true is the result file is from an error tolerant search, false otherwise

Implements ms_mascotresfilebase.

◆ isMSMS()

bool isMSMS ( ) const

overridevirtual

Returns true if the search was an MSMS search (SEARCH=MIS).

Since all types of search may be entered as a sequence query, it may be more useful to use the anyMSMS() member.

Returns: true if SEARCH=MIS in the parameters section or search__parameters table of the file.

Implements ms_mascotresfilebase.

◆ isPMF()

bool isPMF ( ) const

overridevirtual

Returns true if the search was a PMF search (SEARCH=PMF).

Since all types of search may be entered as a sequence query, it may be more useful to use the anyPMF() member.

Returns: true if SEARCH=PMF in the parameters section or search__parameters table of the file.

Implements ms_mascotresfilebase.

◆ isSQ()

bool isSQ ( ) const

overridevirtual

Returns true if the search was a sequence query search (SEARCH=SQ).

Since all types of search may be entered as a sequence query, it may be more useful to use the anySQ() member.

Returns: true if SEARCH=SQ in the parameters section or search__parameters table of the file.

Implements ms_mascotresfilebase.

◆ isValid()

bool isValid ( ) const

inherited

Call this function to determine if there have been any errors.

This will return true unless there have been any fatal errors.

See Error Handling.

Returns: True if no fatal error occured

See also: getLastError(), getLastErrorString(), clearAllErrors(), getErrorHandler()

Examples: common_error.cpp, config_enzymes.cpp, config_fragrules.cpp, config_license.cpp, config_mascotdat.cpp, config_masses.cpp, config_modfile.cpp, config_procs.cpp, config_quantitation.cpp, config_taxonomy.cpp, http_helper_getstring.cpp, peptide_list.cpp, repeat_search.cpp, resfile_error.cpp, resfile_info.cpp, resfile_input.cpp, resfile_params.cpp, resfile_summary.cpp, and tools_aahelper.cpp.

◆ outputKeepAlive()

bool outputKeepAlive ( ) const

inherited

Outputs the "keep-alive" string during time-consuming operations.

For HTML reports with large result files it is sometimes necessary to output HTML comments to keep the connection alive. This can be done by specifying the interval at which the text is output (keepAliveInterval) and the text that should be output (keepAliveText) as parameters to the ms_mascotresfilebase::ms_mascotresfilebase() constructor.

If the value of keepAliveInterval passed to ms_mascotresfilebase::ms_mascotresfilebase is not 0, then the text specfied by keepAliveText will be output approximately every keepAliveInterval seconds. A 'd' in the keepAliveText will be replaced by the number of seconds since the process started.

This functionality is implemented by calling this function 'often', rather than by using a separate thread. This means that the times between calls will not be accurate. A computationally intensive application that uses Mascot Parser can also call this function as required.

From version 2.3 onwards, the keepAliveText can contain tags that allow different text to be output for different lengthy tasks. The tags are:

ci= - output when creating a cache file.
rf= - output when reading the .dat file.
ap= - output when assigning peptides to proteins.
gp= - output when grouping proteins.
ul= - output when calling ms_peptidesummary::createUnassignedList()
qu= - output when calculating quantitation intensities for reporter or multiplex protocols.
cc= - output when creating a cache file as part of calling ms_peptidesummary::ms_peptidesummary
fd= - output when calling ms_mascotresults::getThresholdForFDRAboveIdentity or ms_mascotresults::getThresholdForFDRAboveHomology.

The text can also include the following tags which are substituted by values:

%d - The time elapsed since the initial call to ms-mascotresfile.
%p - The percentage complete for the current task.
%h - The hit number.
%q - The query number.
%a - The accession string for the current protein being processed.
%f - The filename of the .dat file being processed. May be useful for the ci= value with Combining multiple results files

The following table indicates which values are available for which tasks:

	ci=	rf=	ap=	gp=	ul=	cc=	fd=
%d	X	X	X	X	X	X	X
%p	X	X	X	X	X	X	X
%h			X	X		X
%q			X	X	X	X
%a			X	X		X
%f	X	X	X	X	X	X

The %a and %h values for cc= are not output for the second half of caching.

A 'complete' example string might be: ' ul=Creating unassigned list (%p% complete)\n qu=Calculating quantitation component intensities (%p% complete)\ ci=Creating cache file (%p% complete)\n rf=Reading results file (%p% complete)\n ap=Assigning peptides to proteins (%p% complete) hit=%h, time=%d\n gp=Found protein group: %a, hit=%h, %p% complete, %d seconds\n cc=Caching results (%p% complete)\n fd=Calculating false discovery rate (%p% complete)\n '

Any text before the first tag will be used as a default for cases where text isn't supplied for a particular task. For example:

Processing: %p% complete gp=Grouping %a

would output the text:

Processing 23% complete

for all tasks except the protein grouping which would output:

Grouping gi|12345

Returns: true if the work is complete, false otherwise

◆ params()

ms_searchparams & params ( ) const

inlineinherited

Returns a reference to the search parameters class.

For C# only, params is a keyword, so this function is renamed to _params.

Returns: reference to the ms_searchparams object

◆ resetKeepAlive()

void resetKeepAlive	(	const int	keepAliveInterval,
		const char *	keepAliveText,
		const bool	propagateToAppended = `true`,
		const bool	resetStartTime = `false`
	)

inherited

Replace the existing keepAlive values with new values.

KeepAlive values are passed when creating the ms_mascotresfilebase object, but it can be useful to change these at a later time.

See outputKeepAlive() for further details.

Parameters

keepAliveInterval	is the new interval in seconds. Specify a value of -1 to keep the old value, or 0 to stop outputting keepAliveText.
keepAliveText	is the text to output every keepAliveInterval seconds while the file is being loaded, or while other tasks are in progress.
propagateToAppended	only has meaning if additional files have been appended by calling appendResfile().
resetStartTime	can be set to true to reset the "%d" value to zero. See outputKeepAlive() for details.

◆ resfileType()

ms_mascotresfilebase::RESFILE_TYPE resfileType ( const std::string & fileName )

staticinherited

Return the results format of the file provided as an argument.

This method tries to open the file and 'sniff' the first few bytes. If those bytes are the SQLite database header, then this is a Mascot Search Results (MSR) file and the method returns RESFILE_MSR. If the bytes look like a MIME format header, then this is a dat28 (.dat) file and the method returns RESFILE_DAT28. In any other case, the method returns RESFILE_UNKNOWN.

Parameters

fileName relative or absolute path to the file to 'sniff'.

Returns: the file type.

◆ setErrorInfoFromString()

bool setErrorInfoFromString ( const std::string & e )

protectedinherited

For restoring any errors in the .cdb file

Parameters

e	is the stored string obtained from calling getErrorInfoAsString

Returns: true if the input string is parsed successfully

◆ setPercolatorFeatures() [1/2]

void setPercolatorFeatures	(	const char *	percolatorFeatures,
		const char *	additionalFeatures,
		const bool	useRetentionTimes
	)

inherited

Set Percolator features before creating an ms_peptidesummary with Percolator scoring (deprecated).

Deprecated:: This function is deprecated and has been replaced with matrix_science::ms_mascotresfilebase::setPercolatorFeatures(const ms_mascotoptions&, const char*, const std::vector<std::string>&).

The names (and contents!) of the Percolator files depend on the features that have been enabled. When running from a report script on Mascot Server, turning on an additional feature in percolatorFeatures will cause Mascot to create a new file, but the old file will still be available if the feature is removed again from percolatorFeatures.

When running outside Mascot Server, the parameters passed to this method must match the parameters used by the report scripts, in order to get the same Percolator file names. If the pip/pop files are from Mascot Server 2.8 or later, please use matrix_science::ms_mascotresfilebase::setPercolatorFeatures(const ms_mascotoptions&, const char*, const std::vector<std::string>&) and the same mascot.dat options as were used on the server.

Parameters

percolatorFeatures	is normally retrieved by calling ms_mascotoptions::getPercolatorFeatures().
additionalFeatures	is normally a string passed to ms-createpip.exe. For example, `"-a numUniqPeps -r varmods"` would add numUniqPeps and remove varmods from the default. An empty string means nothing is added or removed from ms_mascotoptions::getPercolatorFeatures().
useRetentionTimes	is a flag to indicate whether retention time information is used by percolator.exe. This value is normally retrieved by calling ms_mascotoptions::isPercolatorUseRT().

◆ setPercolatorFeatures() [2/2]

void setPercolatorFeatures	(	const ms_mascotoptions &	options,
		const char *	additionalFeatures,
		const std::vector< std::string > &	adapterParameters = `std::vector<std::string>()`
	)

inherited

Set Percolator features before creating an ms_peptidesummary with Percolator scoring.

The names (and contents!) of the Percolator files depend on the features that have been enabled. When running from a report script on Mascot Server, turning on an additional feature in PercolatorFeatures will cause Mascot to create a new file, but the old file will still be available if the feature is removed again from PercolatorFeatures.

The method uses the following fields from options:

PercolatorFeatures (string)
PercolatorUseRT (true/false)
PercolatorUseProteins (true/false)
PercolatorExeFlags (string)
PercolatorTargetRankScoreThreshold (int)
PercolatorTargetRankRelativeThreshold (double)

When running outside Mascot Server, the parameters passed to this method must match the parameters used by the report scripts, in order to get the same Percolator file names. If the pip/pop files are from Mascot Server 2.8 or later, please use the same mascot.dat options as were used on the server. Make sure you also use the same adapterParameters.

Parameters

options	contains the options stored in mascot.dat.
additionalFeatures	is normally a string passed to ms-createpip.exe For example, `"-a numUniqPeps -r varmods"` would add numUniqPeps and remove varmods from the default
adapterParameters	is a vector of parameters to ML adapters introduced in Mascot Server 3.0. If the vector is not empty, then the parameters are sorted and hashed into an additional MD5 checksum component of the pip/pop file names.

◆ setXMLschemaFilePath()

bool setXMLschemaFilePath	(	XML_SCHEMA	XMLschema,
		const char *	path
	)

inherited

Sets the XML schema to be used by functions using quantitation or unimod.

It is generally easier to pass a directory as the XMLschemaDirectory parameter to the constructor rather than calling this function for each of the required schema.

Warning: if a relative path for the xsd is specified, then this will be relative to the document and not relative to the current working directory.

Example:

  std::string qs;
  qs  = "http://www.matrixscience.com/xmlns/schema/quantitation_1 ";
  qs += "C:/myfiles/quant_schema_1.xsd ";
  qs += "http://www.matrixscience.com/xmlns/schema/quantitation_2 ";
  qs += "../schema%20files/quantitation_2.xsd";
  setXMLschemaFilePath(XML_SCHEMA_QUANTITATION, qs.c_str());
*

The default values used in cases where this function has not been called and no parameter is passed to the constructor are the values suitable for scripts and programs running on the Mascot Server. These values are:

XML_SCHEMA_QUANTITATION : 
    http://www.matrixscience.com/xmlns/schema/quantitation_1 ../html/xmlns/schema/quantitation_1/quantitation_1.xsd
    http://www.matrixscience.com/xmlns/schema/quantitation_2 ../html/xmlns/schema/quantitation_2/quantitation_2.xsd

XML_SCHEMA_UNIMOD :
    http://www.unimod.org/xmlns/schema/unimod_2 ../html/xmlns/schema/unimod_2/unimod_2.xsd

XML_SCHEMA_CROSSLINKING :
    http://www.matrixscience.com/xmlns/schema/crosslinking_1 ../html/xmlns/schema/crosslinking_1/crosslinking_1.xsd

Parameters

XMLschema	must be one of the valid XML_SCHEMA values
path	should be a list of pairs "_schema_alias_ SPACE _file_path_", where SPACE is the space character. See XML_SCHEMA for the supported _scheama_alias_ values for each type of schema

Returns: true if the XMLschema value is valid

◆ staticGetPercolatorFileNames() [1/2]

bool staticGetPercolatorFileNames	(	const char *	szFileName,
		const char *	cacheDirectory,
		const char *	percolatorFeatures,
		const char *	additionalFeatures,
		const bool	useRetentionTimes,
		std::vector< std::string > &	filenames,
		std::vector< bool > &	exists
	)

staticinherited

Returns a list of the Percolator input and output files for the specified data file (deprecated).

Deprecated:: This function is deprecated and has been replaced with matrix_science::ms_mascotresfilebase::staticGetPercolatorFileNames(const char*, const char*, const ms_mascotoptions&, const char *, const std::vector<std::string>&, std::vector<std::string>&, std::vector<bool>&).

This static function can be called without creating an ms_mascotresfilebase object, and can be used in advance of creating an object to see if the percolator files will need to be created. If an object has already been created, it is normally easier to call setPercolatorFeatures() and then getPercolatorFileNames().

See Using Percolator scores and Using STL vector classes vectori, vectord and VectorString in Perl, Java, Python and C#.

Parameters

szFileName	is the absolute or relative path to the results file.
cacheDirectory	will normally be the value returned from ms_mascotoptions::getCacheDirectory. If it's empty, then the default pattern is used (../data/cache/%Y/%d).
percolatorFeatures	is normally retrieved by calling ms_mascotoptions::getPercolatorFeatures(). The filenames encode the features so that there is no conflict.
additionalFeatures	is normally a string passed to ms-createpip.exe. For example, `"-a numUniqPeps -r varmods"` would add numUniqPeps and remove varmods from the default. Any other parameters except -a and -r are ignored. An empty string means nothing is added or removed from percolatorFeatures.
useRetentionTimes	is a flag to indicate whether retention time information is used by percolator.exe.
filenames	returns the list of files. The offsets are defined by ms_mascotresfilebase::PERCOLATOR_FILE_NAMES.
exists	is a boolean vector which will return flags indicating if the Percolator files exists. The values correspond to the values in filenames vector.

Returns: true if all files exist

◆ staticGetPercolatorFileNames() [2/2]

bool staticGetPercolatorFileNames	(	const char *	szFileName,
		const char *	cacheDirectory,
		const ms_mascotoptions &	options,
		const char *	additionalFeatures,
		const std::vector< std::string > &	adapterParameters,
		std::vector< std::string > &	filenames,
		std::vector< bool > &	exists
	)

staticinherited

Returns a list of the Percolator input and output files for the specified data file.

This static function can be called without creating an ms_mascotresfilebase object, and can be used in advance of creating an object to see if the percolator files will need to be created. If an object has already been created, it is normally easier to call setPercolatorFeatures() and then getPercolatorFileNames().

The function uses the following fields from options:

PercolatorFeatures (string)
PercolatorUseRT (true/false)
PercolatorUseProteins (true/false)
PercolatorExeFlags (string)
PercolatorTargetRankScoreThreshold (int)
PercolatorTargetRankRelativeThreshold (double)

Make sure you set PercolatorExeFlags in options based on whether the results file has any queries with a retention time. Otherwise, this method may generate a filename different from setPercolatorFeatures().

    bool anyRT = (whether any query has RTINSECONDS);
    std::string percolatorFlags = options.getPercolatorRtFlags(anyRT, options.isPercolatorUseRT());
    options.setPercolatorExeFlags(percolatorFlags.c_str());

See Using Percolator scores and Using STL vector classes vectori, vectord and VectorString in Perl, Java, Python and C#.

Parameters

szFileName	is the absolute or relative path to the results file.
cacheDirectory	will normally be the value returned from ms_mascotoptions::getCacheDirectory. If it's empty, then the default pattern is used (../data/cache/%Y/%d).
options	contains the options stored in mascot.dat It is used to access the relevant options to generate the file names.
additionalFeatures	is normally a string passed to ms-createpip.exe. For example, `"-a numUniqPeps -r varmods"` would add numUniqPeps and remove varmods from the default. Any other parameters except -a and -r are ignored. An empty string means nothing is added or removed from ms_mascotoptions::getPercolatorFeatures().
adapterParameters	is a vector of parameters to ML adapters introduced in Mascot Server 3.0. If the vector is not empty, then the parameters are sorted and hashed into an additional MD5 checksum component of the pip/pop file names.
filenames	returns the list of files. The offsets are defined by ms_mascotresfilebase::PERCOLATOR_FILE_NAMES.
exists	is a boolean vector which will return flags indicating if the Percolator files exists. The values correspond to the values in filenames vector.

Returns: true if all files exist

◆ versionGreaterOrEqual()

bool versionGreaterOrEqual	(	int	major,
		int	minor,
		int	revision
	)		const

inherited

Compare the value returned by getMascotVer() with the passed version number.

Utility function to perform easy comparison. For example, to test if a results file could have taxonomy information, use:

if (versionGreaterOrEqual(2, 4, 0)) then ...

Note: Versions 2.3.1 to 2.4.0 of Mascot Parser returned the incorrect value. This was fixed in 2.4.1

Parameters

major	is the major version to be compared with
minor	is the minor version to be compared with
revision	is the minor revision to be compared with

Returns: Will return true if the version of the file is greater than or equal to the passed value

◆ willCreateCache() [1/2]

bool willCreateCache	(	const char *	szFileName,
		const ms_mascotoptions &	opts,
		const char *	applicationName,
		std::string &	resfileCacheFileName,
		unsigned int &	cacheStatus
	)

staticinherited

Returns true if a cache file will be created when the ms_mascotresfile_dat constructor is called.

This static function can be called without creating an ms_mascotresfile_msr or ms_mascotresfile_dat object. It can be used in advance of creating the object to see if there will be a delay while (re)creating the cache file(s).

The purpose of this method is to get the status of the cache in addition of whether the cache will be created or not.

See Multiple return values in Perl, Java, Python and C#

See Static functions in Perl, Java, Python and C#

Parameters

[in]	szFileName	is the absolute or relative path to the Fxxxxx.dat file
[in]	opts	normally loaded from the mascot.dat file using ms_datfile::getMascotOptions()
[in]	applicationName	is the name of the application or script that is calling this function. The applicationName is searched for in the return value from ms_mascotoptions::getResultsCache and ms_mascotoptions::getResfileCache to determine if the application should be using cache files. If it is not found then the function returns false and sets the cacheStatus to ms_peptidesummary::RESFILE_CACHE_DISABLED_IN_OPTIONS. If null, or an empty string is passed, no check is made.
[out]	resfileCacheFileName	returns the name of the ms_mascotresfilebase cache file if one exists or would be created
[out]	cacheStatus	is the ms_peptidesummary::CACHE_STATUS enumeration which gives more details about why the cache file may or may not be created. Multiple values may be bitwise OR'd toegether.

Returns: true if either of the cache files will be (re-)created because they does not exist or are not complete or not up to date. It will return false if the options specify that the applicationName shouldn't create or use cache files.

◆ willCreateCache() [2/2]

bool willCreateCache	(	const char *	szFileName,
		const unsigned int	flags,
		const char *	cacheDirectory,
		std::string *	cacheFileName
	)

staticinherited

Returns true if a cache file will be created when the ms_mascotresfile_dat constructor is called.

This static function can be called without creating an ms_mascotresfile_dat or ms_mascotresfile_msr object, and can be used in advance of creating an object to see if there will be a delay while (re)creating a cache file. The function has the same parameters as the ms_mascotresfilebase constructor.

The behaviour depends on the file type (ms_mascotresfilebase::resfileType()). If it is MSR, this method always returns false, because MSR files do not need a resfile cache. If it is dat28 format (.dat), a resfile cache may be needed.

See Static functions in Perl, Java, Python and C#

See Multiple return values in Perl, Java, Python and C#.

Parameters

[in]	szFileName	- see ms_mascotresfilebase::ms_mascotresfilebase
[in]	flags	- see ms_mascotresfilebase::ms_mascotresfilebase
[in]	cacheDirectory	- see ms_mascotresfilebase::ms_mascotresfilebase
[out]	cacheFileName	- the full path name of the cache file. For languages other than C++, this will be a reference rather than a pointer to a std::string.

Returns: true if the cache file will be (re-)created because it does not exist or is not complete or not up to date. If the RESFILE_USE_CACHE flag has not been specified, it will always return false

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

ms_mascotresfile_msr.hpp
ms_mascotresfile_msr.cpp

Public Types

Public Member Functions

Static Public Member Functions

Protected Member Functions

Detailed Description

Member Enumeration Documentation

◆ FLAGS

◆ KA_TASK

◆ PERCOLATOR_FILE_NAMES

◆ RESFILE_TYPE

◆ XML_SCHEMA

Constructor & Destructor Documentation

◆ ms_mascotresfile_msr()

Member Function Documentation

◆ anyCrosslinkedMatches()

◆ anyErrorTolerantMatches()

◆ anyFastaMatches()

◆ anyMSMS()

◆ anyPMF()

◆ anySpectralLibraryMatches()

◆ anySQ()

◆ anyTag()

◆ appendErrors()

◆ appendResfile()

◆ clearAllErrors()

◆ copyFrom()

◆ createResfile()

◆ get_ms_mascotresults_params() [1/2]

◆ get_ms_mascotresults_params() [2/2]

◆ getCacheDirectory()

◆ getCacheFileName()

◆ getCrosslinking()

◆ getCrosslinkingMethod()

◆ getDatabaseType()

◆ getDate()

◆ getDecoyTypeForDB()

◆ getEnzyme()

◆ getErrorHandler()

◆ getErrorInfoAsString()

◆ getErrorNumber()

◆ getErrorString()

◆ getExecTime()

◆ getFastaPath()

◆ getFastaVer()

◆ getFileName()

◆ getFirstPassThreshold()

◆ getHeaderKeyValues()

◆ getHeaderValue()

◆ getInputQuery()

◆ getJobNumber()

◆ getKeepAlive()

◆ getLastError()

◆ getLastErrorString()

◆ getLibraryMods()

◆ getMascotVer()

◆ getMasses()

◆ getMassesKeyValues()

◆ getMassValue()

◆ getMonoLinkModification()

◆ getMSParserVersion()

◆ getMultiFileQueryNumber()

◆ getNumberOfErrors()

◆ getNumberOfResfiles()

◆ getNumEtSeqsSearched()

◆ getNumLibraryEntries()

◆ getNumQueries()

◆ getNumResidues()

◆ getNumSeqs()

◆ getNumSeqsAfterTax()

◆ getObservedCharge()

◆ getObservedIntensity()

◆ getObservedMass()

◆ getObservedMrValue()

◆ getPercolatorFileNames()

◆ getProgressInfo()

◆ getQmatch()

◆ getQplughole()

◆ getQuantitation()

◆ getQuantitationMethod()

◆ getReferenceDatabaseNumberOfSL()