SequestInfile Class Reference

Sequest input file adapter. More...

#include <OpenMS/FORMAT/SequestInfile.h>

Public Member Functions
	SequestInfile ()
	default constructor More...
	SequestInfile (const SequestInfile &sequest_infile)
	copy constructor More...
virtual	~SequestInfile ()
	destructor More...
SequestInfile &	operator= (const SequestInfile &sequest_infile)
	assignment operator More...
bool	operator== (const SequestInfile &sequest_infile) const
	equality operator More...
void	store (const String &filename)
const String	getEnzymeInfoAsString () const
	returns the enzyme list as a string More...
const String &	getDatabase () const
	returns the used database More...
void	setDatabase (const String &database)
	sets the used database More...
const String &	getNeutralLossesForIons () const
	returns whether neutral losses are considered for the a-, b- and y-ions More...
void	setNeutralLossesForIons (const String &neutral_losses_for_ions)
	sets whether neutral losses are considered for the a-, b- and y-ions More...
const String &	getIonSeriesWeights () const
	returns the weights for the a-, b-, c-, d-, v-, w-, x-, y- and z-ion series More...
void	setIonSeriesWeights (const String &ion_series_weights)
	sets the weights for the a-, b-, c-, d-, v-, w-, x-, y- and z-ion series More...
const String &	getPartialSequence () const
	returns the partial sequences (space delimited) that have to occur in the theoretical spectra More...
void	setPartialSequence (const String &partial_sequence)
	sets the partial sequences (space delimited) that have to occur in the theoretical spectra More...
const String &	getSequenceHeaderFilter () const
	returns the sequences (space delimited) that have to occur, or be absent (preceded by a tilde) in the header of a protein to be considered More...
void	setSequenceHeaderFilter (const String &sequence_header_filter)
	sets the sequences (space delimited) that have to occur, or be absent (preceded by a tilde) in the header of a protein to be considered More...
const String &	getProteinMassFilter () const
	returns the protein mass filter (either min and max mass, or mass and tolerance value in percent) More...
void	setProteinMassFilter (const String &protein_mass_filter)
	sets the protein mass filter (either min and max mass, or mass and tolerance value in percent) More...
float	getPeakMassTolerance () const
	returns the peak mass tolerance More...
void	setPeakMassTolerance (float peak_mass_tolerance)
	sets the peak mass tolerance More...
float	getPrecursorMassTolerance () const
	returns the precursor mass tolerance More...
void	setPrecursorMassTolerance (float precursor_mass_tolerance)
	sets the precursor mass tolerance More...
float	getMatchPeakTolerance () const
	returns the match peak tolerance More...
void	setMatchPeakTolerance (float match_peak_tolerance)
	sets the match peak tolerance More...
float	getIonCutoffPercentage () const
	returns the the cutoff of the ratio matching theoretical peaks/theoretical peaks More...
void	setIonCutoffPercentage (float ion_cutoff_percentage)
	sets the ion cutoff of the ratio matching theoretical peaks/theoretical peaks More...
Size	getPeptideMassUnit () const
	returns the peptide mass unit More...
void	setPeptideMassUnit (Size peptide_mass_unit)
	sets the peptide mass unit More...
Size	getOutputLines () const
	return the number of peptides to be displayed More...
void	setOutputLines (Size output_lines)
	sets the number of peptides to be displayed More...
Size	getEnzymeNumber () const
	returns the enzyme used for cleavage (by means of the number from a list of enzymes) More...
String	getEnzymeName () const
	returns the enzyme used for cleavage More...
Size	setEnzyme (String enzyme_name)
	sets the enzyme used for cleavage (by means of the number from a list of enzymes) More...
Size	getMaxAAPerModPerPeptide () const
	returns the maximum number of amino acids containing the same modification in a peptide More...
void	setMaxAAPerModPerPeptide (Size max_aa_per_mod_per_peptide)
	sets the maximum number of amino acids containing the same modification in a peptide More...
Size	getMaxModsPerPeptide () const
	returns the maximum number of modifications that are allowed in a peptide More...
void	setMaxModsPerPeptide (Size max_mods_per_peptide)
	set the maximum number of modifications that are allowed in a peptide More...
Size	getNucleotideReadingFrame () const
	returns the nucleotide reading frame More...
void	setNucleotideReadingFrame (Size nucleotide_reading_frame)
Size	getMaxInternalCleavageSites () const
	returns the maximum number of internal cleavage sites More...
void	setMaxInternalCleavageSites (Size max_internal_cleavage_sites)
	sets the maximum number of internal cleavage sites More...
Size	getMatchPeakCount () const
	returns the number of top abundant peaks to match with theoretical ones More...
void	setMatchPeakCount (Size match_peak_count)
	sets the number of top abundant peaks to with theoretical ones More...
Size	getMatchPeakAllowedError () const
	returns the number of top abundant peaks that are allowed not to match with a theoretical peak More...
void	setMatchPeakAllowedError (Size match_peak_allowed_error)
	sets the number of top abundant peaks that are allowed not to match with a theoretical peak More...
bool	getShowFragmentIons () const
	returns whether fragment ions shall be displayed More...
void	setShowFragmentIons (bool show_fragments)
	sets whether fragment ions shall be displayed More...
bool	getPrintDuplicateReferences () const
	returns whether all proteins containing a found peptide should be displayed More...
void	setPrintDuplicateReferences (bool print_duplicate_references)
	sets whether all proteins containing a found peptide should be displayed More...
bool	getRemovePrecursorNearPeaks () const
	return whether peaks near (15 amu) the precursor peak are removed More...
void	setRemovePrecursorNearPeaks (bool remove_precursor_near_peaks)
	sets whether peaks near (15 amu) the precursor peak are removed More...
bool	getMassTypeParent () const
	return the mass type of the parent (0 - monoisotopic, 1 - average mass) More...
void	setMassTypeParent (bool mass_type_parent)
	sets the mass type of the parent (0 - monoisotopic, 1 - average mass) More...
bool	getMassTypeFragment () const
	return the mass type of the fragments (0 - monoisotopic, 1 - average mass) More...
void	setMassTypeFragment (bool mass_type_fragment)
	sets the mass type of the fragments (0 - monoisotopic, 1 - average mass) More...
bool	getNormalizeXcorr () const
	returns whether normalized xcorr values are displayed More...
void	setNormalizeXcorr (bool normalize_xcorr)
	sets whether normalized xcorr values are displayed More...
bool	getResiduesInUpperCase () const
	returns whether residues are in upper case More...
void	setResiduesInUpperCase (bool residues_in_upper_case)
	sets whether residues are in upper case More...
void	addEnzymeInfo (std::vector< String > &enzyme_info)
const std::map< String, std::vector< String > > &	getModifications () const
	return the modifications (the modification names map to the affected residues, the mass change and the type) More...
void	handlePTMs (const String &modification_line, const String &modifications_filename, const bool monoisotopic)

Protected Member Functions
const std::map< String, std::vector< String > > &	getEnzymeInfo_ () const
	returns the enzyme list More...
void	setStandardEnzymeInfo_ ()
	returns some standard enzymes (used to initialize the enzyme list) More...

Protected Attributes
std::map< String, std::vector< String > >	enzyme_info_
	an endline-delimited list of enzymes; each with cutting direction 0 (N to C) /1; cuts after (list of aa); doesn't cut before (list of aa); the attributes are tab-delimited More...
String	database_
	database used More...
String	snd_database_
	second database used More...
String	neutral_losses_for_ions_
	whether neutral losses are considered for the a-; b- and y-ions (e.g. 011 for b- and y-ions) More...
String	ion_series_weights_
	weights for the a-; b-; c-; d-; v-; w-; x-; y- and z-ion series; space delimited More...
String	partial_sequence_
	space-delimited list of sequence parts that have to occur in the theoretical spectra More...
String	sequence_header_filter_
	space-delimited list of sequences that have to occur or be absent (preceded by a tilde) in a protein header; to be considered More...
String	protein_mass_filter_
float	precursor_mass_tolerance_
	tolerance for matching a theoretical to an experimental peptide More...
float	peak_mass_tolerance_
	tolerance for matching a theoretical to an experimental peak More...
float	match_peak_tolerance_
	minimum distance between two experimental peaks More...
float	ion_cutoff_percentage_
	cutoff of the ratio matching theoretical peaks/theoretical peaks More...
Size	peptide_mass_unit_
	peptide mass unit (0 = amu; 1 = mmu; 2 = ppm) More...
Size	output_lines_
	number of peptides to be displayed More...
Size	enzyme_number_
	number of the enzyme used for cleavage More...
Size	max_AA_per_mod_per_peptide_
	maximum number of amino acids containing the same modification in a peptide More...
Size	max_mods_per_peptide_
	maximum number of modifications per peptide More...
Size	nucleotide_reading_frame_
Size	max_internal_cleavage_sites_
	maximum number of internal cleavage sites More...
Size	match_peak_count_
	number of the top abundant peaks to match with theoretical one More...
Size	match_peak_allowed_error_
	number of peaks that may lack this test More...
bool	show_fragment_ions_
	whether to display fragment ions More...
bool	print_duplicate_references_
	whether all proteins containing a found peptide should be displayed More...
bool	remove_precursor_near_peaks_
	whether peaks near (15 amu) the precursor peak are removed More...
bool	mass_type_parent_
	mass type of the parent peak (0 - monoisotopic; 1 - average) More...
bool	mass_type_fragment_
	mass type of fragment peaks (0 - monoisotopic; 1 - average) More...
bool	normalize_xcorr_
	whether to display normalized xcorr values More...
bool	residues_in_upper_case_
	whether residues are in upper case More...
std::map< String, std::vector< String > >	PTMname_residues_mass_type_
	the modification names map to the affected residues, the mass change and the type More...

Detailed Description

Sequest input file adapter.

Creates a sequest.params file for Sequest search from a peak list.

Constructor & Destructor Documentation

SequestInfile() [1/2]

SequestInfile

(

)

default constructor

SequestInfile() [2/2]

SequestInfile

(

const SequestInfile &

sequest_infile

)

copy constructor

~SequestInfile()

virtual ~SequestInfile ( )

virtual

destructor

Member Function Documentation

addEnzymeInfo()

void addEnzymeInfo

(

std::vector< String > &

enzyme_info

)

adds an enzyme to the list and sets is as used the vector consists of four strings: name, cut direction: 0 (N to C) / 1, cuts after (list of aa), doesn't cut before (list of aa)

getDatabase()

const String& getDatabase

(

)

const

returns the used database

getEnzymeInfo_()

const std::map<String, std::vector<String> >& getEnzymeInfo_ ( ) const

protected

returns the enzyme list

getEnzymeInfoAsString()

const String getEnzymeInfoAsString

(

)

const

returns the enzyme list as a string

getEnzymeName()

String getEnzymeName

(

)

const

returns the enzyme used for cleavage

getEnzymeNumber()

Size getEnzymeNumber

(

)

const

returns the enzyme used for cleavage (by means of the number from a list of enzymes)

getIonCutoffPercentage()

float getIonCutoffPercentage

(

)

const

returns the the cutoff of the ratio matching theoretical peaks/theoretical peaks

getIonSeriesWeights()

const String& getIonSeriesWeights

(

)

const

returns the weights for the a-, b-, c-, d-, v-, w-, x-, y- and z-ion series

getMassTypeFragment()

bool getMassTypeFragment

(

)

const

return the mass type of the fragments (0 - monoisotopic, 1 - average mass)

getMassTypeParent()

bool getMassTypeParent

(

)

const

return the mass type of the parent (0 - monoisotopic, 1 - average mass)

getMatchPeakAllowedError()

Size getMatchPeakAllowedError

(

)

const

returns the number of top abundant peaks that are allowed not to match with a theoretical peak

getMatchPeakCount()

Size getMatchPeakCount

(

)

const

returns the number of top abundant peaks to match with theoretical ones

getMatchPeakTolerance()

float getMatchPeakTolerance

(

)

const

returns the match peak tolerance

getMaxAAPerModPerPeptide()

Size getMaxAAPerModPerPeptide

(

)

const

returns the maximum number of amino acids containing the same modification in a peptide

getMaxInternalCleavageSites()

Size getMaxInternalCleavageSites

(

)

const

returns the maximum number of internal cleavage sites

getMaxModsPerPeptide()

Size getMaxModsPerPeptide

(

)

const

returns the maximum number of modifications that are allowed in a peptide

getModifications()

const std::map<String, std::vector<String> >& getModifications

(

)

const

return the modifications (the modification names map to the affected residues, the mass change and the type)

getNeutralLossesForIons()

const String& getNeutralLossesForIons

(

)

const

returns whether neutral losses are considered for the a-, b- and y-ions

getNormalizeXcorr()

bool getNormalizeXcorr

(

)

const

returns whether normalized xcorr values are displayed

getNucleotideReadingFrame()

Size getNucleotideReadingFrame

(

)

const

returns the nucleotide reading frame

getOutputLines()

Size getOutputLines

(

)

const

return the number of peptides to be displayed

getPartialSequence()

const String& getPartialSequence

(

)

const

returns the partial sequences (space delimited) that have to occur in the theoretical spectra

getPeakMassTolerance()

float getPeakMassTolerance

(

)

const

returns the peak mass tolerance

getPeptideMassUnit()

Size getPeptideMassUnit

(

)

const

returns the peptide mass unit

getPrecursorMassTolerance()

float getPrecursorMassTolerance

(

)

const

returns the precursor mass tolerance

getPrintDuplicateReferences()

bool getPrintDuplicateReferences

(

)

const

returns whether all proteins containing a found peptide should be displayed

getProteinMassFilter()

const String& getProteinMassFilter

(

)

const

returns the protein mass filter (either min and max mass, or mass and tolerance value in percent)

getRemovePrecursorNearPeaks()

bool getRemovePrecursorNearPeaks

(

)

const

return whether peaks near (15 amu) the precursor peak are removed

getResiduesInUpperCase()

bool getResiduesInUpperCase

(

)

const

returns whether residues are in upper case

getSequenceHeaderFilter()

const String& getSequenceHeaderFilter

(

)

const

returns the sequences (space delimited) that have to occur, or be absent (preceded by a tilde) in the header of a protein to be considered

getShowFragmentIons()

bool getShowFragmentIons

(

)

const

returns whether fragment ions shall be displayed

handlePTMs()

void handlePTMs	(	const String &	modification_line,
		const String &	modifications_filename,
		const bool	monoisotopic
	)

retrieves the name, mass change, affected residues, type and position for all modifications from a string

Parameters

modification_line
modifications_filename
monoisotopic

Exceptions

Exception::FileNotFound	is thrown if the given file is not found
Exception::FileNotReadable	is thrown if the given file could not be read
Exception::ParseError	is thrown if the given file could not be parsed

operator=()

SequestInfile& operator=

(

const SequestInfile &

sequest_infile

)

assignment operator

operator==()

bool operator==

(

const SequestInfile &

sequest_infile

)

const

equality operator

setDatabase()

void setDatabase

(

const String &

database

)

sets the used database

setEnzyme()

Size setEnzyme

(

String

enzyme_name

)

sets the enzyme used for cleavage (by means of the number from a list of enzymes)

setIonCutoffPercentage()

void setIonCutoffPercentage

(

float

ion_cutoff_percentage

)

sets the ion cutoff of the ratio matching theoretical peaks/theoretical peaks

setIonSeriesWeights()

void setIonSeriesWeights

(

const String &

ion_series_weights

)

sets the weights for the a-, b-, c-, d-, v-, w-, x-, y- and z-ion series

setMassTypeFragment()

void setMassTypeFragment

(

bool

mass_type_fragment

)

sets the mass type of the fragments (0 - monoisotopic, 1 - average mass)

setMassTypeParent()

void setMassTypeParent

(

bool

mass_type_parent

)

sets the mass type of the parent (0 - monoisotopic, 1 - average mass)

setMatchPeakAllowedError()

void setMatchPeakAllowedError

(

Size

match_peak_allowed_error

)

sets the number of top abundant peaks that are allowed not to match with a theoretical peak

setMatchPeakCount()

void setMatchPeakCount

(

Size

match_peak_count

)

sets the number of top abundant peaks to with theoretical ones

setMatchPeakTolerance()

void setMatchPeakTolerance

(

float

match_peak_tolerance

)

sets the match peak tolerance

setMaxAAPerModPerPeptide()

void setMaxAAPerModPerPeptide

(

Size

max_aa_per_mod_per_peptide

)

sets the maximum number of amino acids containing the same modification in a peptide

setMaxInternalCleavageSites()

void setMaxInternalCleavageSites

(

Size

max_internal_cleavage_sites

)

sets the maximum number of internal cleavage sites

setMaxModsPerPeptide()

void setMaxModsPerPeptide

(

Size

max_mods_per_peptide

)

set the maximum number of modifications that are allowed in a peptide

setNeutralLossesForIons()

void setNeutralLossesForIons

(

const String &

neutral_losses_for_ions

)

sets whether neutral losses are considered for the a-, b- and y-ions

setNormalizeXcorr()

void setNormalizeXcorr

(

bool

normalize_xcorr

)

sets whether normalized xcorr values are displayed

setNucleotideReadingFrame()

void setNucleotideReadingFrame

(

Size

nucleotide_reading_frame

)

sets the nucleotide reading frame: 0 The FASTA file contains amino acid codes. No translation is needed. This is the best and fastest case. 1 The DNA sequence is scanned left to right (forward direction). The amino acid code starts with the first DNA code. 2 The DNA sequence is scanned left to right (forward direction). The amino acid code starts with the second DNA code. 3 The DNA sequence is scanned left to right (forward direction). The amino acid code starts with the third DNA code. 4 The DNA sequence is scanned right to left (backward direction for the complementary strand). The amino acid code starts with the first DNA code. 5 The DNA sequence is scanned right to left (backward direction for the complementary strand). The amino acid code starts with the second DNA code. 6 The DNA sequence is scanned right to left (backward direction for the complementary strand). The amino acid code starts with the third DNA code. 7 Use each of the DNA translations of the codes 1, 2, 3. 8 Use each of the DNA translations of the codes 4, 5, 6. 9 Use each of the DNA translations of the codes 1, 2, 3, 4, 5, 6.

setOutputLines()

void setOutputLines

(

Size

output_lines

)

sets the number of peptides to be displayed

setPartialSequence()

void setPartialSequence

(

const String &

partial_sequence

)

sets the partial sequences (space delimited) that have to occur in the theoretical spectra

setPeakMassTolerance()

void setPeakMassTolerance

(

float

peak_mass_tolerance

)

sets the peak mass tolerance

setPeptideMassUnit()

void setPeptideMassUnit

(

Size

peptide_mass_unit

)

sets the peptide mass unit

setPrecursorMassTolerance()

void setPrecursorMassTolerance

(

float

precursor_mass_tolerance

)

sets the precursor mass tolerance

setPrintDuplicateReferences()

void setPrintDuplicateReferences

(

bool

print_duplicate_references

)

sets whether all proteins containing a found peptide should be displayed

setProteinMassFilter()

void setProteinMassFilter

(

const String &

protein_mass_filter

)

sets the protein mass filter (either min and max mass, or mass and tolerance value in percent)

setRemovePrecursorNearPeaks()

void setRemovePrecursorNearPeaks

(

bool

remove_precursor_near_peaks

)

sets whether peaks near (15 amu) the precursor peak are removed

setResiduesInUpperCase()

void setResiduesInUpperCase

(

bool

residues_in_upper_case

)

sets whether residues are in upper case

setSequenceHeaderFilter()

void setSequenceHeaderFilter

(

const String &

sequence_header_filter

)

sets the sequences (space delimited) that have to occur, or be absent (preceded by a tilde) in the header of a protein to be considered

setShowFragmentIons()

void setShowFragmentIons

(

bool

show_fragments

)

sets whether fragment ions shall be displayed

setStandardEnzymeInfo_()

void setStandardEnzymeInfo_ ( )

protected

returns some standard enzymes (used to initialize the enzyme list)

store()

void store

(

const String &

filename

)

stores the experiment data in a Sequest input file that can be used as input for Sequest shell execution

Parameters

filename

the name of the file in which the infile is stored into

Exceptions

Exception::UnableToCreateFile

is thrown if the file could not be created

Member Data Documentation

database_

String database_

protected

database used

enzyme_info_

std::map<String, std::vector<String> > enzyme_info_

protected

an endline-delimited list of enzymes; each with cutting direction 0 (N to C) /1; cuts after (list of aa); doesn't cut before (list of aa); the attributes are tab-delimited

enzyme_number_

Size enzyme_number_

protected

number of the enzyme used for cleavage

ion_cutoff_percentage_

float ion_cutoff_percentage_

protected

cutoff of the ratio matching theoretical peaks/theoretical peaks

ion_series_weights_

String ion_series_weights_

protected

weights for the a-; b-; c-; d-; v-; w-; x-; y- and z-ion series; space delimited

mass_type_fragment_

bool mass_type_fragment_

protected

mass type of fragment peaks (0 - monoisotopic; 1 - average)

mass_type_parent_

bool mass_type_parent_

protected

mass type of the parent peak (0 - monoisotopic; 1 - average)

match_peak_allowed_error_

Size match_peak_allowed_error_

protected

number of peaks that may lack this test

match_peak_count_

Size match_peak_count_

protected

number of the top abundant peaks to match with theoretical one

match_peak_tolerance_

float match_peak_tolerance_

protected

minimum distance between two experimental peaks

max_AA_per_mod_per_peptide_

Size max_AA_per_mod_per_peptide_

protected

maximum number of amino acids containing the same modification in a peptide

max_internal_cleavage_sites_

Size max_internal_cleavage_sites_

protected

maximum number of internal cleavage sites

0 The FASTA file contains amino acid codes. No translation is needed. This is the best and fastest case. 1 The DNA sequence is scanned left to right (forward direction). The amino acid code starts with the first DNA code. 2 The DNA sequence is scanned left to right (forward direction). The amino acid code starts with the second DNA code. 3 The DNA sequence is scanned left to right (forward direction). The amino acid code starts with the third DNA code. 4 The DNA sequence is scanned right to left (backward direction for the complementary strand). The amino acid code starts with the first DNA code. 5 The DNA sequence is scanned right to left (backward direction for the complementary strand). The amino acid code starts with the second DNA code. 6 The DNA sequence is scanned right to left (backward direction for the complementary strand). The amino acid code starts with the third DNA code. 7 Use each of the DNA translations of the codes 1; 2; 3. 8 Use each of the DNA translations of the codes 4; 5; 6. 9 Use each of the DNA translations of the codes 1; 2; 3; 4; 5; 6.

max_mods_per_peptide_

Size max_mods_per_peptide_

protected

maximum number of modifications per peptide

neutral_losses_for_ions_

String neutral_losses_for_ions_

protected

whether neutral losses are considered for the a-; b- and y-ions (e.g. 011 for b- and y-ions)

normalize_xcorr_

bool normalize_xcorr_

protected

whether to display normalized xcorr values

nucleotide_reading_frame_

Size nucleotide_reading_frame_

protected

nucleotide reading frame:

output_lines_

Size output_lines_

protected

number of peptides to be displayed

partial_sequence_

String partial_sequence_

protected

space-delimited list of sequence parts that have to occur in the theoretical spectra

peak_mass_tolerance_

float peak_mass_tolerance_

protected

tolerance for matching a theoretical to an experimental peak

peptide_mass_unit_

Size peptide_mass_unit_

protected

peptide mass unit (0 = amu; 1 = mmu; 2 = ppm)

precursor_mass_tolerance_

float precursor_mass_tolerance_

protected

tolerance for matching a theoretical to an experimental peptide

print_duplicate_references_

bool print_duplicate_references_

protected

whether all proteins containing a found peptide should be displayed

protein_mass_filter_

String protein_mass_filter_

protected

PTMname_residues_mass_type_

std::map<String, std::vector<String> > PTMname_residues_mass_type_

protected

the modification names map to the affected residues, the mass change and the type

remove_precursor_near_peaks_

bool remove_precursor_near_peaks_

protected

whether peaks near (15 amu) the precursor peak are removed

residues_in_upper_case_

bool residues_in_upper_case_

protected

whether residues are in upper case

sequence_header_filter_

String sequence_header_filter_

protected

space-delimited list of sequences that have to occur or be absent (preceded by a tilde) in a protein header; to be considered

show_fragment_ions_

bool show_fragment_ions_

protected

whether to display fragment ions

snd_database_

String snd_database_

protected

second database used