NucleicAcidSearchEngine Class Reference

Inheritance diagram for NucleicAcidSearchEngine:

Collaboration diagram for NucleicAcidSearchEngine:

Classes
struct	AnnotatedHit
class	HasInvalidLength
struct	PrecursorInfo

Public Member Functions
	NucleicAcidSearchEngine ()
Public Member Functions inherited from TOPPBase
	TOPPBase ()=delete
	No default constructor.
	TOPPBase (const TOPPBase &)=delete
	No default copy constructor.
	TOPPBase (const String &name, const String &description, bool official=true, const std::vector< Citation > &citations={}, bool toolhandler_test=true)
	Constructor.
virtual	~TOPPBase ()
	Destructor.
ExitCodes	main (int argc, const char **argv)
	Main routine of all TOPP applications.
String	getToolPrefix () const
	Returns the prefix used to identify the tool.
String	getDocumentationURL () const
	Returns a link to the documentation of the tool (accessible on our servers and only after inclusion in the nightly branch or a release).

Protected Types
typedef multimap< double, AnnotatedHit, greater< double > >	HitsByScore

Protected Member Functions
void	registerOptionsAndFlags_ () override
	Sets the valid command line options (with argument) and flags (without argument).
set< ConstRibonucleotidePtr >	getModifications_ (const set< String > &mod_names)
AdductInfo	parseAdduct_ (const String &adduct)
void	deisotopeAndSingleChargeMSSpectrum_ (MSSpectrum &in, Int min_charge, Int max_charge, double fragment_tolerance, bool fragment_unit_ppm, bool keep_only_deisotoped=false, Size min_isopeaks=3, Size max_isopeaks=10, bool make_single_charged=true)
void	preprocessSpectra_ (PeakMap &exp, double fragment_mass_tolerance, bool fragment_mass_tolerance_unit_ppm, bool single_charge_spectra, bool negative_mode, Int min_charge, Int max_charge, bool include_unknown_charge)
double	calculatePrecursorMass_ (double mz, Int charge, Int isotope, double adduct_mass, bool negative_mode)
void	resolveAmbiguousMods_ (HitsByScore &hits)
void	postProcessHits_ (const PeakMap &exp, vector< HitsByScore > &annotated_hits, IdentificationData &id_data, bool negative_mode)
void	calculateAndFilterFDR_ (IdentificationData &id_data, bool only_top_hits)
void	generateLFQInput_ (IdentificationData &id_data, const String &out_file)
ExitCodes	main_ (int, const char **) override
	The actual "main" method. main_() is invoked by main().
Protected Member Functions inherited from TOPPBase
String	getParamArgument_ (const Param::ParamEntry &entry) const
	Utility function that determines a suitable argument value for the given Param::ParamEntry.
std::vector< ParameterInformation >	paramToParameterInformation_ (const Param &param) const
	Translates the given parameter object into a vector of ParameterInformation, that can be utilized for cl parsing.
ParameterInformation	paramEntryToParameterInformation_ (const Param::ParamEntry &entry, const String &argument="", const String &full_name="") const
	Transforms a ParamEntry object to command line parameter (ParameterInformation).
void	registerParamSubsectionsAsTOPPSubsections_ (const Param &param)
void	registerFullParam_ (const Param &param)
	Register command line parameters for all entries in a Param object.
void	registerStringOption_ (const String &name, const String &argument, const String &default_value, const String &description, bool required=true, bool advanced=false)
	Registers a string option.
void	setValidStrings_ (const String &name, const std::vector< String > &strings)
	Sets the valid strings for a string option or a whole string list.
void	setValidStrings_ (const String &name, const std::string vstrings[], int count)
	Sets the valid strings for a string option or a whole string list.
void	registerInputFile_ (const String &name, const String &argument, const String &default_value, const String &description, bool required=true, bool advanced=false, const StringList &tags=StringList())
	Registers an input file option.
void	registerOutputFile_ (const String &name, const String &argument, const String &default_value, const String &description, bool required=true, bool advanced=false)
	Registers an output file option.
void	registerOutputPrefix_ (const String &name, const String &argument, const String &default_value, const String &description, bool required=true, bool advanced=false)
	Registers an output file prefix used for tools with multiple file output.
void	registerOutputDir_ (const String &name, const String &argument, const String &default_value, const String &description, bool required=true, bool advanced=false)
	Registers an output directory used for tools with multiple output files which are not an output file list, i.e. do not correspond to the number of input files.
void	setValidFormats_ (const String &name, const std::vector< String > &formats, const bool force_OpenMS_format=true)
	Sets the formats for a input/output file option or for all members of an input/output file lists.
void	registerDoubleOption_ (const String &name, const String &argument, double default_value, const String &description, bool required=true, bool advanced=false)
	Registers a double option.
void	setMinInt_ (const String &name, Int min)
	Sets the minimum value for the integer parameter(can be a list of integers,too) name.
void	setMaxInt_ (const String &name, Int max)
	Sets the maximum value for the integer parameter(can be a list of integers,too) name.
void	setMinFloat_ (const String &name, double min)
	Sets the minimum value for the floating point parameter(can be a list of floating points,too) name.
void	setMaxFloat_ (const String &name, double max)
	Sets the maximum value for the floating point parameter(can be a list of floating points,too) name.
void	registerIntOption_ (const String &name, const String &argument, Int default_value, const String &description, bool required=true, bool advanced=false)
	Registers an integer option.
void	registerIntList_ (const String &name, const String &argument, const IntList &default_value, const String &description, bool required=true, bool advanced=false)
	Registers a list of integers option.
void	registerDoubleList_ (const String &name, const String &argument, const DoubleList &default_value, const String &description, bool required=true, bool advanced=false)
	Registers a list of doubles option.
void	registerStringList_ (const String &name, const String &argument, const StringList &default_value, const String &description, bool required=true, bool advanced=false)
	Registers a list of strings option.
void	registerInputFileList_ (const String &name, const String &argument, const StringList &default_value, const String &description, bool required=true, bool advanced=false, const StringList &tags=StringList())
	Registers a list of input files option.
void	registerOutputFileList_ (const String &name, const String &argument, const StringList &default_value, const String &description, bool required=true, bool advanced=false)
	Registers a list of output files option.
void	registerFlag_ (const String &name, const String &description, bool advanced=false)
	Registers a flag.
void	registerSubsection_ (const String &name, const String &description)
	Registers an allowed subsection in the INI file (usually from OpenMS algorithms).
void	registerTOPPSubsection_ (const String &name, const String &description)
	Registers an allowed subsection in the INI file originating from the TOPP tool itself.
void	addEmptyLine_ ()
	Adds an empty line between registered variables in the documentation.
String	getStringOption_ (const String &name) const
	Returns the value of a previously registered string option (use getOutputDirOption() for output directories)
String	getOutputDirOption (const String &name) const
	Returns the value of a previously registered output_dir option.
double	getDoubleOption_ (const String &name) const
	Returns the value of a previously registered double option.
Int	getIntOption_ (const String &name) const
	Returns the value of a previously registered integer option.
StringList	getStringList_ (const String &name) const
	Returns the value of a previously registered StringList.
IntList	getIntList_ (const String &name) const
	Returns the value of a previously registered IntList.
DoubleList	getDoubleList_ (const String &name) const
	Returns the value of a previously registered DoubleList.
bool	getFlag_ (const String &name) const
	Returns the value of a previously registered flag.
const ParameterInformation &	findEntry_ (const String &name) const
	Finds the entry in the parameters_ array that has the name name.
Param const &	getParam_ () const
	Return all parameters relevant to this TOPP tool.
void	checkParam_ (const Param &param, const String &filename, const String &location) const
	Checks top-level entries of param according to the information during registration.
void	fileParamValidityCheck_ (const StringList &param_value, const String &param_name, const ParameterInformation &p) const
	checks if files of an input file list exist
void	fileParamValidityCheck_ (String &param_value, const String &param_name, const ParameterInformation &p) const
	checks if an input file exists (respecting the flags)
void	checkIfIniParametersAreApplicable_ (const Param &ini_params)
	Checks if the parameters of the provided ini file are applicable to this tool.
void	printUsage_ ()
	Prints the tool-specific command line options and appends the common options.
void	writeLogInfo_ (const String &text) const
	Writes a string to the log file and to OPENMS_LOG_INFO.
void	writeLogWarn_ (const String &text) const
	Writes a string to the log file and to OPENMS_LOG_WARN.
void	writeLogError_ (const String &text) const
	Writes a string to the log file and to OPENMS_LOG_ERROR.
void	writeDebug_ (const String &text, UInt min_level) const
	Writes a string to the log file and to OPENMS_LOG_DEBUG if the debug level is at least min_level.
void	writeDebug_ (const String &text, const Param &param, UInt min_level) const
	Writes a String followed by a Param to the log file and to OPENMS_LOG_DEBUG if the debug level is at least min_level.
ExitCodes	runExternalProcess_ (const QString &executable, const QStringList &arguments, const QString &workdir="", const std::map< QString, QString > &env=std::map< QString, QString >()) const
	Runs an external process via ExternalProcess and prints its stderr output on failure or if debug_level > 4.
ExitCodes	runExternalProcess_ (const QString &executable, const QStringList &arguments, String &proc_stdout, String &proc_stderr, const QString &workdir="", const std::map< QString, QString > &env=std::map< QString, QString >()) const
const String &	getIniLocation_ () const
	Returns the location of the ini file where parameters are taken from. E.g. if the command line was TOPPTool -instance 17, then this will be "TOPPTool:17:". Note the ':' at the end.
const String &	toolName_ () const
	Returns the tool name.
void	inputFileReadable_ (const String &filename, const String &param_name) const
	Checks if an input file exists, is readable and is not empty.
void	outputFileWritable_ (const String &filename, const String &param_name) const
	Checks if an output file is writable.
bool	parseRange_ (const String &text, double &low, double &high) const
	Parses a range string ([a]:[b]) into two variables (doubles)
bool	parseRange_ (const String &text, Int &low, Int &high) const
	Parses a range string ([a]:[b]) into two variables (integers)
void	addDataProcessing_ (ConsensusMap &map, const DataProcessing &dp) const
	Data processing setter for consensus maps.
void	addDataProcessing_ (FeatureMap &map, const DataProcessing &dp) const
	Data processing setter for feature maps.
void	addDataProcessing_ (PeakMap &map, const DataProcessing &dp) const
	Data processing setter for peak maps.
DataProcessing	getProcessingInfo_ (DataProcessing::ProcessingAction action) const
	Returns the data processing information.
DataProcessing	getProcessingInfo_ (const std::set< DataProcessing::ProcessingAction > &actions) const
	Returns the data processing information.
template<typename Writer >
void	writeToolDescription_ (Writer &writer, std::string write_type, std::string fileExtension)
	Helper function avoiding repeated code between CTD, JSON and CWL.

Protected Attributes
vector< String >	fragment_ion_codes_
map< String, String >	ambiguous_mods_
bool	resolve_ambiguous_mods_
Protected Attributes inherited from TOPPBase
String	version_
	Version string (if empty, the OpenMS/TOPP version is printed)
String	verboseVersion_
	Version string including additional revision/date time information. Note: This differs from version_ only if not provided by the user.
bool	official_
	Flag indicating if this an official TOPP tool.
std::vector< Citation >	citations_
	Papers, specific for this tool (will be shown in '–help')
bool	toolhandler_test_
	Enable the ToolHandler tests.
ProgressLogger::LogType	log_type_
	Type of progress logging.
bool	test_mode_
	Test mode.
Int	debug_level_
	Debug level set by -debug.

Private Types
using	ConstRibonucleotidePtr = const Ribonucleotide *

Additional Inherited Members
Public Types inherited from TOPPBase
enum	ExitCodes {   EXECUTION_OK , INPUT_FILE_NOT_FOUND , INPUT_FILE_NOT_READABLE , INPUT_FILE_CORRUPT ,   INPUT_FILE_EMPTY , CANNOT_WRITE_OUTPUT_FILE , ILLEGAL_PARAMETERS , MISSING_PARAMETERS ,   UNKNOWN_ERROR , EXTERNAL_PROGRAM_ERROR , PARSE_ERROR , INCOMPATIBLE_INPUT_DATA ,   INTERNAL_ERROR , UNEXPECTED_RESULT , EXTERNAL_PROGRAM_NOTFOUND }
	Exit codes. More...
Static Public Member Functions inherited from TOPPBase
static void	setMaxNumberOfThreads (int num_threads)
	Sets the maximal number of usable threads.
Static Public Attributes inherited from TOPPBase
static const char *	TAG_OUTPUT_FILE = "output file"
static const char *	TAG_INPUT_FILE = "input file"
static const char *	TAG_OUTPUT_DIR = "output dir"
static const char *	TAG_OUTPUT_PREFIX = "output prefix"
static const char *	TAG_ADVANCED = "advanced"
static const char *	TAG_REQUIRED = "required"
static const Citation	cite_openms
	The latest and greatest OpenMS citation.
Static Protected Attributes inherited from TOPPBase
static String	topp_ini_file_
	.TOPP.ini file for storing system default parameters

---

Class Documentation

NucleicAcidSearchEngine::AnnotatedHit

struct NucleicAcidSearchEngine::AnnotatedHit

Collaboration diagram for NucleicAcidSearchEngine::AnnotatedHit:

Class Members
vector< PeakAnnotation >	annotations
IdentifiedOligoRef	oligo_ref
double	precursor_error_ppm
const PrecursorInfo *	precursor_ref
NASequence	sequence

Member Typedef Documentation

ConstRibonucleotidePtr

using ConstRibonucleotidePtr = const Ribonucleotide*

private

HitsByScore

typedef multimap<double, AnnotatedHit, greater<double> > HitsByScore

protected

Constructor & Destructor Documentation

NucleicAcidSearchEngine()

NucleicAcidSearchEngine ( )

inline

Member Function Documentation

calculateAndFilterFDR_()

void calculateAndFilterFDR_ ( IdentificationData &  id_data, bool  only_top_hits  )

inlineprotected

References FalseDiscoveryRate::applyToObservationMatches(), IDFilter::filterObservationMatchesByScore(), IdentificationData::findScoreType(), DefaultParamHandler::getDefaults(), TOPPBase::getDoubleOption_(), TOPPBase::getFlag_(), IdentificationData::getObservationMatches(), IdentificationData::getObservations(), OPENMS_LOG_INFO, IDFilter::removeDecoys(), DefaultParamHandler::setParameters(), and Param::setValue().

Referenced by main_().

calculatePrecursorMass_()

double calculatePrecursorMass_ ( double  mz, Int  charge, Int  isotope, double  adduct_mass, bool  negative_mode  )

inlineprotected

References OpenMS::Constants::C13C12_MASSDIFF_U, and OpenMS::Constants::PROTON_MASS_U.

Referenced by main_().

deisotopeAndSingleChargeMSSpectrum_()

void deisotopeAndSingleChargeMSSpectrum_ ( MSSpectrum &  in, Int  min_charge, Int  max_charge, double  fragment_tolerance, bool  fragment_unit_ppm, bool  keep_only_deisotoped = false, Size  min_isopeaks = 3, Size  max_isopeaks = 10, bool  make_single_charged = true  )

inlineprotected

References OpenMS::Constants::C13C12_MASSDIFF_U, MSSpectrum::clear(), MSSpectrum::findNearest(), Peak1D::getMZ(), OpenMS::Constants::PROTON_MASS_U, Peak1D::setMZ(), and MSSpectrum::sortByPosition().

Referenced by preprocessSpectra_().

generateLFQInput_()

void generateLFQInput_ ( IdentificationData &  id_data, const String &  out_file  )

inlineprotected

References ListUtils::concatenate(), IdentificationData::getObservationMatches(), OpenMS::Math::median(), and SVOutStream::modifyStrings().

Referenced by main_().

getModifications_()

set< ConstRibonucleotidePtr > getModifications_ ( const set< String > &  mod_names )

inlineprotected

References ambiguous_mods_, RibonucleotideDB::getInstance(), Ribonucleotide::isAmbiguous(), and resolve_ambiguous_mods_.

Referenced by main_().

main_()

ExitCodes main_ ( int  argc, const char **  argv  )

inlineoverrideprotectedvirtual

The actual "main" method. main_() is invoked by main().

Implements TOPPBase.

References PeakFileOptions::addMSLevel(), ScoredProcessingResult::addProcessingStep(), MSExperiment::addSpectrum(), NucleicAcidSearchEngine::AnnotatedHit::annotations, ModifiedNASequenceGenerator::applyFixedModifications(), ModifiedNASequenceGenerator::applyVariableModifications(), ProcessingSoftware::assigned_scores, File::basename(), MSExperiment::begin(), calculateAndFilterFDR_(), IdentificationData::calculateCoverages(), calculatePrecursorMass_(), DBSearchParam::charges, PeakFileOptions::clearMSLevels(), MetaboliteSpectralMatching::computeHyperScore(), DBSearchParam::database, RNaseDigestion::digest(), DBSearchParam::digestion_enzyme, MSExperiment::end(), ProgressLogger::endProgress(), TOPPBase::EXECUTION_OK, IdentificationDataConverter::exportIDs(), IdentificationDataConverter::exportMzTab(), DBSearchParam::fixed_mods, fragment_ion_codes_, DBSearchParam::fragment_mass_tolerance, DBSearchParam::fragment_tolerance_ppm, generateLFQInput_(), IdentificationData::getCurrentProcessingStep(), IdentificationData::getDBSearchParams(), TOPPBase::getDoubleOption_(), TOPPBase::getFlag_(), IdentificationData::getIdentifiedOligos(), TOPPBase::getIntList_(), TOPPBase::getIntOption_(), AdductInfo::getMassShift(), getModifications_(), NucleicAcidSpectrumGenerator::getMultipleSpectra(), MSExperiment::getNrSpectra(), MzTab::getNucleicAcidSectionRows(), IdentificationData::getObservations(), MzTab::getOligonucleotideSectionRows(), MzTab::getOSMSectionRows(), DefaultParamHandler::getParameters(), IdentificationData::getParentSequences(), MSExperiment::getPrimaryMSRunPath(), MSSpectrum::getRT(), TOPPBase::getStringList_(), TOPPBase::getStringOption_(), FileTypes::IDXML, TOPPBase::ILLEGAL_PARAMETERS, IdentificationDataConverter::importSequences(), OMSFile::load(), FASTAFile::load(), FileHandler::loadExperiment(), TOPPBase::log_type_, DBSearchParam::mass_type, DBSearchParam::max_length, DBSearchParam::min_length, DBSearchParam::missed_cleavages, DBSearchParam::molecule_type, FileTypes::MZML, NucleicAcidSearchEngine::AnnotatedHit::oligo_ref, OPENMS_LOG_DEBUG, OPENMS_LOG_ERROR, OPENMS_LOG_INFO, OPENMS_LOG_WARN, parseAdduct_(), postProcessHits_(), NucleicAcidSearchEngine::AnnotatedHit::precursor_error_ppm, DBSearchParam::precursor_mass_tolerance, NucleicAcidSearchEngine::AnnotatedHit::precursor_ref, DBSearchParam::precursor_tolerance_ppm, preprocessSpectra_(), InputFile::primary_files, IdentificationData::registerAdduct(), IdentificationData::registerDBSearchParam(), IdentificationData::registerInputFile(), IdentificationData::registerParentSequence(), IdentificationData::registerProcessingSoftware(), IdentificationData::registerProcessingStep(), IdentificationData::registerScoreType(), resolve_ambiguous_mods_, NucleicAcidSearchEngine::AnnotatedHit::sequence, IdentificationData::setCurrentProcessingStep(), RNaseDigestion::setEnzyme(), ProgressLogger::setLogType(), EnzymaticDigestion::setMissedCleavages(), MSSpectrum::setName(), FileHandler::setOptions(), DefaultParamHandler::setParameters(), ProgressLogger::setProgress(), MSSpectrum::setRT(), Param::setValue(), Software::setVersion(), MSExperiment::size(), MSExperiment::sortSpectra(), ProgressLogger::startProgress(), OMSFile::store(), MzTabFile::store(), FileHandler::storeExperiment(), FileHandler::storeIdentifications(), TOPPBase::test_mode_, TOPPBase::toolName_(), NASequence::toString(), DBSearchParam::variable_mods, and TOPPBase::version_.

parseAdduct_()

AdductInfo parseAdduct_ ( const String &  adduct )

inlineprotected

References OPENMS_LOG_DEBUG, and String::split().

Referenced by main_().

postProcessHits_()

void postProcessHits_ ( const PeakMap &  exp, vector< HitsByScore > &  annotated_hits, IdentificationData &  id_data, bool  negative_mode  )

inlineprotected

References ScoredProcessingResult::addScore(), NucleicAcidSearchEngine::PrecursorInfo::adduct, ObservationMatch::adduct_opt, NucleicAcidSearchEngine::AnnotatedHit::annotations, NucleicAcidSearchEngine::PrecursorInfo::charge, IdentificationData::cleanup(), IdentificationData::getCurrentProcessingStep(), IdentificationData::getInputFiles(), SpectrumSettings::getNativeID(), SpectrumSettings::getPrecursors(), MSSpectrum::getRT(), IdentificationData::getScoreTypes(), NucleicAcidSearchEngine::PrecursorInfo::isotope, NucleicAcidSearchEngine::AnnotatedHit::oligo_ref, OPENMS_LOG_DEBUG, ObservationMatch::peak_annotations, NucleicAcidSearchEngine::AnnotatedHit::precursor_error_ppm, OpenMS::Constants::UserParam::PRECURSOR_ERROR_PPM_USERPARAM, NucleicAcidSearchEngine::AnnotatedHit::precursor_ref, IdentificationData::registerIdentifiedOligo(), IdentificationData::registerObservation(), IdentificationData::registerObservationMatch(), resolve_ambiguous_mods_, resolveAmbiguousMods_(), IdentifiedSequence< SeqType >::sequence, NucleicAcidSearchEngine::AnnotatedHit::sequence, MetaInfoInterface::setMetaValue(), and NASequence::toString().

Referenced by main_().

preprocessSpectra_()

void preprocessSpectra_ ( PeakMap &  exp, double  fragment_mass_tolerance, bool  fragment_mass_tolerance_unit_ppm, bool  single_charge_spectra, bool  negative_mode, Int  min_charge, Int  max_charge, bool  include_unknown_charge  )

inlineprotected

References deisotopeAndSingleChargeMSSpectrum_(), ThresholdMower::filterPeakMap(), Normalizer::filterPeakMap(), NLargest::filterPeakSpectrum(), WindowMower::filterPeakSpectrum(), SpectrumSettings::getNativeID(), DefaultParamHandler::getParameters(), SpectrumSettings::getPrecursors(), OPENMS_LOG_DEBUG, OPENMS_LOG_ERROR, OPENMS_LOG_INFO, OPENMS_LOG_WARN, Precursor::setCharge(), DefaultParamHandler::setParameters(), SpectrumSettings::setPrecursors(), Param::setValue(), MSExperiment::size(), MSSpectrum::sortByPosition(), and MSExperiment::sortSpectra().

Referenced by main_().

registerOptionsAndFlags_()

void registerOptionsAndFlags_ ( )

inlineoverrideprotectedvirtual

Sets the valid command line options (with argument) and flags (without argument).

The options '-ini' '-log' '-instance' '-debug' and the flag '–help' are automatically registered.

Implements TOPPBase.

References fragment_ion_codes_, RibonucleotideDB::getInstance(), TOPPBase::registerDoubleOption_(), TOPPBase::registerFlag_(), TOPPBase::registerInputFile_(), TOPPBase::registerIntList_(), TOPPBase::registerIntOption_(), TOPPBase::registerOutputFile_(), TOPPBase::registerStringList_(), TOPPBase::registerStringOption_(), TOPPBase::registerTOPPSubsection_(), String::remove(), TOPPBase::setMaxFloat_(), TOPPBase::setMinFloat_(), TOPPBase::setMinInt_(), TOPPBase::setValidFormats_(), and TOPPBase::setValidStrings_().

resolveAmbiguousMods_()

void resolveAmbiguousMods_ ( HitsByScore &  hits )

inlineprotected

References ambiguous_mods_, NASequence::empty(), RibonucleotideDB::getInstance(), OPENMS_PRECONDITION, and NASequence::size().

Referenced by postProcessHits_().

Member Data Documentation

ambiguous_mods_

map<String, String> ambiguous_mods_

protected

Referenced by getModifications_(), and resolveAmbiguousMods_().

fragment_ion_codes_

vector<String> fragment_ion_codes_

protected

Referenced by main_(), and registerOptionsAndFlags_().

resolve_ambiguous_mods_

bool resolve_ambiguous_mods_

protected

Referenced by getModifications_(), main_(), and postProcessHits_().