Representation of a peptide/protein sequence. More...

#include <OpenMS/CHEMISTRY/AASequence.h>

Classes
class	ConstIterator
	ConstIterator for AASequence. More...

class	Iterator
	Iterator class for AASequence. More...

Public Member Functions
AASequence &	operator= (const AASequence &rhs)
	assignment operator More...

bool	empty () const
	check if sequence is empty More...

Constructors and Destructors
	AASequence ()
	default constructor More...

	AASequence (const AASequence &rhs)
	copy constructor More...

virtual	~AASequence ()
	destructor More...

Accessors
String	toString () const
	returns the peptide as string with modifications embedded in brackets More...

String	toUnmodifiedString () const
	returns the peptide as string without any modifications More...

void	setModification (Size index, const String &modification)
	set the modification of the residue at position index More...

void	setNTerminalModification (const String &modification)
	sets the N-terminal modification More...

const String &	getNTerminalModification () const
	returns the Id of the N-term modification; an empty string is returned if none was set More...

void	setCTerminalModification (const String &modification)
	sets the C-terminal modification More...

const String &	getCTerminalModification () const
	returns the Id of the C-term modification; an empty string is returned if none was set More...

const Residue &	getResidue (SignedSize index) const
	returns a pointer to the residue, which is at position index More...

const Residue &	getResidue (Size index) const
	returns a pointer to the residue, which is at position index More...

EmpiricalFormula	getFormula (Residue::ResidueType type=Residue::Full, Int charge=0) const
	returns the formula of the peptide More...

double	getAverageWeight (Residue::ResidueType type=Residue::Full, Int charge=0) const
	returns the average weight of the peptide More...

double	getMonoWeight (Residue::ResidueType type=Residue::Full, Int charge=0) const
	returns the mono isotopic weight of the peptide More...

const Residue &	operator[] (SignedSize index) const
	returns a pointer to the residue at given position More...

const Residue &	operator[] (Size index) const
	returns a pointer to the residue at given position More...

AASequence	operator+ (const AASequence &peptide) const
	adds the residues of the peptide More...

AASequence &	operator+= (const AASequence &)
	adds the residues of a peptide More...

AASequence	operator+ (const Residue *residue) const
	adds the residues of the peptide More...

AASequence &	operator+= (const Residue *)
	adds the residues of a peptide More...

Size	size () const
	returns the number of residues More...

AASequence	getPrefix (Size index) const
	returns a peptide sequence of the first index residues More...

AASequence	getSuffix (Size index) const
	returns a peptide sequence of the last index residues More...

AASequence	getSubsequence (Size index, UInt number) const
	returns a peptide sequence of number residues, beginning at position index More...

void	getAAFrequencies (Map< String, Size > &frequency_table) const
	compute frequency table of amino acids More...

Predicates
bool	has (const Residue &residue) const
	returns true if the peptide contains the given residue More...

bool	hasSubsequence (const AASequence &peptide) const

bool	hasPrefix (const AASequence &peptide) const

bool	hasSuffix (const AASequence &peptide) const

bool	hasNTerminalModification () const
	predicate which is true if the peptide is N-term modified More...

bool	hasCTerminalModification () const
	predicate which is true if the peptide is C-term modified More...

bool	isModified () const
	returns true if any of the residues is modified More...

bool	isModified (Size index) const
	returns true if the residue at the position is modified More...

bool	operator== (const AASequence &rhs) const
	equality operator. Two sequences are equal iff all amino acids including PTMs are equal More...

bool	operator< (const AASequence &rhs) const
	lesser than operator which compares the C-term mods, sequence including PTMS and N-term mods; can be used for maps More...

bool	operator!= (const AASequence &rhs) const
	inequality operator. Complement of equality operator. More...

Iterators
Iterator	begin ()

ConstIterator	begin () const

Iterator	end ()

ConstIterator	end () const

Static Public Member Functions
static AASequence	fromString (const String &s, bool permissive=true)
	create AASequence object by parsing an OpenMS string More...

static AASequence	fromString (const char *s, bool permissive=true)
	create AASequence object by parsing a C string (character array) More...

Static Protected Member Functions
static String::ConstIterator	parseModRoundBrackets_ (const String::ConstIterator str_it, const String &str, AASequence &aas)

static String::ConstIterator	parseModSquareBrackets_ (const String::ConstIterator str_it, const String &str, AASequence &aas)

static void	parseString_ (const String &peptide, AASequence &aas, bool permissive=true)

Protected Attributes
std::vector< const Residue * >	peptide_

const ResidueModification *	n_term_mod_

const ResidueModification *	c_term_mod_

Friends
Stream operators
std::ostream &	operator<< (std::ostream &os, const AASequence &peptide)
	writes a peptide to an output stream More...

std::istream &	operator>> (std::istream &is, const AASequence &peptide)
	reads a peptide from an input stream More...

Detailed Description

Representation of a peptide/protein sequence.

This class represents amino acid sequences in OpenMS. An AASequence instance primarily contains a sequence of residues. The residues are represented as instances of Residue. Each amino acid has only one instance, which is accessible using the ResidueDB instance (singleton).

To create an AASequence instance for a specific amino acid sequence, use the AASequence::fromString function. For example, AASequence::fromString("DFPIANGER") produces an instance of AASequence for the peptide "DFPIANGER".

A critical property of amino acid sequences is that they can be modified. Which means that one or more amino acids are chemically modified, e.g. oxidized. This is represented via Residue instances which carry a ResidueModification object. This is also handled in the ResidueDB.

Modifications are specified using a unique string identifier present in the ModificationsDB in brackets after the modified amino acid or by providing the mass of the residue in square brackets. For example AASequence::fromString("DFPIAM(Oxidation)GER") creates an instance of the peptide "DFPIAMGER" with an oxidized methionine (AASequence::fromString("DFPIAM[+16]GER") and AASequence::fromString("DFPIAM[147]GER") are equivalent). N-terminal modifications are specified by writing the modification as prefix to the sequence. C-terminal modifications are specified by writing the modification as suffix. C-terminal modifications are distinguished from modifications of the last amino acid by considering the specificity of the modification as stored in ModificationsDB.

Note there is a subtle difference between AASequence::fromString("DFPIAM[+16]GER") and AASequence::fromString("DFPIAM[+15.9949]GER") – while the former will try to find the first modification matching to a mass difference of 16 +/- 0.5, the latter will try to find the closest matching modification to the exact mass. This usually gives the intended results.

Arbitrary/unknown amino acids (usually due to an unknown modification) can be specified using tags preceded by X: "X[weight]". This indicates a new amino acid ("X") with the specified weight, e.g. "RX[148.5]T"". Note that this tag does not alter the amino acids to the left (R) or right (T). Rather, X represents an amino acid on its own. Be careful when converting AASequence to an EmpiricalFormula using getFormula(), as tags will not be considered in this case (there exists no formula for them). However, they have an influence on getMonoWeight() and getAverageWeight()!

Constructor & Destructor Documentation

AASequence ( )

default constructor

AASequence ( const AASequence & rhs )

copy constructor

virtual ~AASequence ( )

virtual

destructor

Member Function Documentation

Iterator begin ( )

inline

ConstIterator begin ( ) const

inline

bool empty ( ) const

check if sequence is empty

Iterator end ( )

inline

ConstIterator end ( ) const

inline

References OpenMS::operator<<(), and OpenMS::operator>>().

static AASequence fromString	(	const String &	s,
		bool	permissive = `true`
	)

static

create AASequence object by parsing an OpenMS string

Parameters

s	Input string
permissive	If set, skip spaces and replace stop codon symbols ("*", "#", "+") by "X" (unknown amino acid) during parsing

Exceptions

Exception::ParseError if an invalid string representation of an AA sequence is passed

Referenced by FoundProteinFunctor::addHit(), SimpleSearchEngine::main_(), and TOPPViewBase::showSpectrumGenerationDialog().

static AASequence fromString	(	const char *	s,
		bool	permissive = `true`
	)

static

create AASequence object by parsing a C string (character array)

Parameters

s	Input string
permissive	If set, skip spaces and replace stop codon symbols ("*", "#", "+") by "X" (unknown amino acid) during parsing

Exceptions

Exception::ParseError if an invalid string representation of an AA sequence is passed

void getAAFrequencies ( Map< String, Size > & frequency_table ) const

compute frequency table of amino acids

double getAverageWeight	(	Residue::ResidueType	type = `Residue::Full`,
		Int	charge = `0`
	)		const

returns the average weight of the peptide

const String& getCTerminalModification ( ) const

returns the Id of the C-term modification; an empty string is returned if none was set

EmpiricalFormula getFormula	(	Residue::ResidueType	type = `Residue::Full`,
		Int	charge = `0`
	)		const

returns the formula of the peptide

double getMonoWeight	(	Residue::ResidueType	type = `Residue::Full`,
		Int	charge = `0`
	)		const

returns the mono isotopic weight of the peptide

Referenced by SimpleSearchEngine::main_(), and TOPPViewBase::showSpectrumGenerationDialog().

const String& getNTerminalModification ( ) const

returns the Id of the N-term modification; an empty string is returned if none was set

AASequence getPrefix ( Size index ) const

returns a peptide sequence of the first index residues

const Residue& getResidue ( SignedSize index ) const

returns a pointer to the residue, which is at position index

const Residue& getResidue ( Size index ) const

returns a pointer to the residue, which is at position index

AASequence getSubsequence	(	Size	index,
		UInt	number
	)		const

returns a peptide sequence of number residues, beginning at position index

AASequence getSuffix ( Size index ) const

returns a peptide sequence of the last index residues

bool has ( const Residue & residue ) const

returns true if the peptide contains the given residue

bool hasCTerminalModification ( ) const

predicate which is true if the peptide is C-term modified

bool hasNTerminalModification ( ) const

predicate which is true if the peptide is N-term modified

bool hasPrefix ( const AASequence & peptide ) const

returns true if the peptide has the given prefix n-term mod is also checked (c-term as well, if prefix is of same length)

bool hasSubsequence ( const AASequence & peptide ) const

returns true if the peptide contains the given peptide

Note: c-term and n-term mods are ignored

bool hasSuffix ( const AASequence & peptide ) const

returns true if the peptide has the given suffix c-term mod is also checked (n-term as well, if suffix is of same length)

bool isModified ( ) const

returns true if any of the residues is modified

bool isModified ( Size index ) const

returns true if the residue at the position is modified

bool operator!= ( const AASequence & rhs ) const

inequality operator. Complement of equality operator.

AASequence operator+ ( const AASequence & peptide ) const

adds the residues of the peptide

AASequence operator+ ( const Residue * residue ) const

adds the residues of the peptide

AASequence& operator+= ( const AASequence & )

adds the residues of a peptide

AASequence& operator+= ( const Residue * )

adds the residues of a peptide

bool operator< ( const AASequence & rhs ) const

lesser than operator which compares the C-term mods, sequence including PTMS and N-term mods; can be used for maps

AASequence& operator= ( const AASequence & rhs )

assignment operator

bool operator== ( const AASequence & rhs ) const

equality operator. Two sequences are equal iff all amino acids including PTMs are equal

const Residue& operator[] ( SignedSize index ) const

returns a pointer to the residue at given position

const Residue& operator[] ( Size index ) const

returns a pointer to the residue at given position

static String::ConstIterator parseModRoundBrackets_	(	const String::ConstIterator	str_it,
		const String &	str,
		AASequence &	aas
	)

staticprotected

static String::ConstIterator parseModSquareBrackets_	(	const String::ConstIterator	str_it,
		const String &	str,
		AASequence &	aas
	)

staticprotected

static void parseString_	(	const String &	peptide,
		AASequence &	aas,
		bool	permissive = `true`
	)

staticprotected

void setCTerminalModification ( const String & modification )

sets the C-terminal modification

void setModification	(	Size	index,
		const String &	modification
	)

set the modification of the residue at position index

void setNTerminalModification ( const String & modification )

sets the N-terminal modification

Size size ( ) const

returns the number of residues

Referenced by AAIndex::calculateGB(), and SimpleSearchEngine::HasInvalidPeptideLengthPredicate::operator()().

String toString ( ) const

returns the peptide as string with modifications embedded in brackets

String toUnmodifiedString ( ) const

returns the peptide as string without any modifications

Friends And Related Function Documentation

std::ostream& operator<<	(	std::ostream &	os,
		const AASequence &	peptide
	)

friend

writes a peptide to an output stream

std::istream& operator>>	(	std::istream &	is,
		const AASequence &	peptide
	)

friend

reads a peptide from an input stream

Member Data Documentation

const ResidueModification* c_term_mod_

protected

const ResidueModification* n_term_mod_

protected

std::vector<const Residue*> peptide_

protected

Classes

Public Member Functions

Static Public Member Functions

Static Protected Member Functions

Protected Attributes

Friends

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation

Friends And Related Function Documentation

Member Data Documentation