#include <RnaSequence.h>

Collaboration diagram for IntaRNA::RnaSequence:

[legend]

Public Types
typedef std::string	String_type
	type for sequence string representation

typedef short	Code_type

typedef std::vector< Code_type >	CodeSeq_type
	type for sequence integer encoded representation

Public Member Functions
	RnaSequence (const std::string &id, const std::string &seqString, const long idxPos0=1, const size_t seqNumber=1)

virtual	~RnaSequence ()

const std::string &	getId () const

const size_t	getSeqNumber () const

size_t	size () const

long	getInOutIndex (const size_t i) const

size_t	getIndex (const long i) const

size_t	getReversedIndex (const size_t i) const

const String_type &	asString () const

const CodeSeq_type &	asCodes () const

bool	isAmbiguous () const

bool	isAmbiguous (const size_t i) const

const bool	operator== (const RnaSequence &rna2) const

Static Public Member Functions
static String_type	getUpperCase (const std::string &seqString)

static CodeSeq_type	getCodeForString (const String_type &seqString)

static Code_type	getCodeForChar (const char nucleotide)

static bool	isValidSequence (const std::string &sequence)

static bool	isValidSequenceIUPAC (const std::string &sequence)

static bool	areComplementary (const RnaSequence &s1, const RnaSequence &s2, const size_t p1, const size_t p2)

static bool	isGU (const RnaSequence &s1, const RnaSequence &s2, const size_t p1, const size_t p2)

Static Public Attributes
static const std::string	SequenceAlphabetIUPAC

static const std::string	SequenceAlphabet

static const size_t	lastPos

Protected Attributes
std::string	id
	ID of this sequence.

String_type	seqString
	The sequence's string representation.

CodeSeq_type	seqCode
	Integer encoding of the sequence.

bool	ambiguous
	Whether or not the sequence contains ambiguous nucleotide encodings.

long	idxPos0
	Input/output index of the first sequence position.

size_t	seqNumber

Static Protected Attributes
static std::locale	codeLocale
	the locale to use for integer encoding

static int	bpGUcodes []
	codes for G and U to check for GU base pairs

Friends
std::ostream &	operator<< (std::ostream &out, const RnaSequence &rna)

Detailed Description

Represents an RNA sequence within IntaRNA and holds all necessary utility functions.

The integer sequence encoding uses the Vienna RNA package encoding functions.

Author: Martin Mann 2014

Member Typedef Documentation

◆ Code_type

typedef short IntaRNA::RnaSequence::Code_type

type for integer encoding of a single sequence letter (currently same as in Vienna package)

◆ CodeSeq_type

typedef std::vector<Code_type> IntaRNA::RnaSequence::CodeSeq_type

type for sequence integer encoded representation

◆ String_type

typedef std::string IntaRNA::RnaSequence::String_type

type for sequence string representation

Constructor & Destructor Documentation

◆ RnaSequence()

IntaRNA::RnaSequence::RnaSequence	(	const std::string &	id,
		const std::string &	seqString,
		const long	idxPos0 = `1`,
		const size_t	seqNumber = `1`
	)

inline

Creates a sequence.

Parameters

id	the name of the sequence
seqString	the nucleotide string encoding the sequence
idxPos0	input/output index of the first sequence position
seqNumber	index of the sequence among the respective sequence set in this call. relevant for accessibility parsing

◆ ~RnaSequence()

IntaRNA::RnaSequence::~RnaSequence ( )

inlinevirtual

Destruction and garbage collection

Member Function Documentation

◆ areComplementary()

bool IntaRNA::RnaSequence::areComplementary	(	const RnaSequence &	s1,
		const RnaSequence &	s2,
		const size_t	p1,
		const size_t	p2
	)

inlinestatic

Whether or not two positions of two RNAs are complementary, ie. can form a base pair

Parameters

s1	first RNA
s2	second RNA
p1	position within s1
p2	position within s2

Returns: true if s1[p1] can form a base pair with s2[p2]; false otherwise

◆ asCodes()

const RnaSequence::CodeSeq_type & IntaRNA::RnaSequence::asCodes ( ) const

inline

Access to the sequence in integer coding using the Vienna RNA package encoding.

Returns: the integer encoding of the sequence

◆ asString()

const RnaSequence::String_type & IntaRNA::RnaSequence::asString ( ) const

inline

Access to the sequence in character encoding.

Returns: the character encoding of the sequence

◆ getCodeForChar()

RnaSequence::Code_type IntaRNA::RnaSequence::getCodeForChar ( const char nucleotide )

inlinestatic

Utility function that converts a nucleotide's char representation into its integer encoding.

NOTE: encoding covers only upper case characters! Otherwise an exception is raised.

Parameters

nucleotide the char to encode

Returns: the integer encoding

Exceptions

std::runtime_error if an unsupported nucleotide character is given

◆ getCodeForString()

RnaSequence::CodeSeq_type IntaRNA::RnaSequence::getCodeForString ( const String_type & seqString )

inlinestatic

Utility function that converts a sequence's string representation into its integer encoding

NOTE: encoding covers only upper case characters! Otherwise an exception is raised.

Parameters

seqString the string to encode

Returns: the integer encoding

Exceptions

std::runtime_error if an unsupported nucleotide character is given

◆ getId()

const std::string & IntaRNA::RnaSequence::getId ( ) const

inline

Access to the sequence's ID.

Returns: the ID of the sequence.

◆ getIndex()

size_t IntaRNA::RnaSequence::getIndex ( const long i ) const

inline

Provides the internal sequence position of an input/output index given that the first position represents idxPos0.

Parameters

i	the input/output index of interest

Returns: the internal position, i.e. i shifted by idxPos0

◆ getInOutIndex()

long IntaRNA::RnaSequence::getInOutIndex ( const size_t i ) const

inline

Provides the input/output index of a given sequence position.

Parameters

i	the position of interest

Returns: the input/output index shifted by idxPos0

◆ getReversedIndex()

size_t IntaRNA::RnaSequence::getReversedIndex ( const size_t i ) const

inline

Provides the reverse index of a given sequence position.

Parameters

i	the index of interest

Returns: the reverse index, i.e. (seq.size()-i-1)

◆ getSeqNumber()

const size_t IntaRNA::RnaSequence::getSeqNumber ( ) const

inline

Access to the sequence's index among the respective input sequence set of the call arguments

Returns: the sequence index among the input sequence set (1-based)

◆ getUpperCase()

RnaSequence::String_type IntaRNA::RnaSequence::getUpperCase ( const std::string & seqString )

inlinestatic

Utility function that converts a string into the internal sequence's string representation. This covers an upper case conversion.

Parameters

seqString sequence string

Returns: the internally used sequence string representation

◆ isAmbiguous() [1/2]

bool IntaRNA::RnaSequence::isAmbiguous ( ) const

inline

Whether or not the sequence contains ambiguous nucleotide encodings.

Returns: true if the sequence contains ambiguous nucleotide encodings; false otherwise

◆ isAmbiguous() [2/2]

bool IntaRNA::RnaSequence::isAmbiguous ( const size_t i ) const

inline

Whether or not a specific sequence position shows an ambiguous nucleotide encoding.

Parameters

i	the sequence position of interest

Returns: true if the sequence contains an ambiguous nucleotide encoding at position i; false otherwise

◆ isGU()

bool IntaRNA::RnaSequence::isGU	(	const RnaSequence &	s1,
		const RnaSequence &	s2,
		const size_t	p1,
		const size_t	p2
	)

inlinestatic

Whether or not two positions of two RNAs are forming a GU base pair

Parameters

s1	first RNA
s2	second RNA
p1	position within s1
p2	position within s2

Returns: true if (s1[p1]=G and s2[p2]==U) or (s1[p1]=U and s2[p2]==G); false otherwise

◆ isValidSequence()

bool IntaRNA::RnaSequence::isValidSequence ( const std::string & sequence )

inlinestatic

Utility function that tests whether or not a given sequence is a valid RNA sequence

◆ isValidSequenceIUPAC()

bool IntaRNA::RnaSequence::isValidSequenceIUPAC ( const std::string & sequence )

inlinestatic

Utility function that tests whether or not a given sequence is a valid RNA sequence according to IUPAC encoding

◆ operator==()

const bool IntaRNA::RnaSequence::operator== ( const RnaSequence & rna2 ) const

inline

Checks for equality

Parameters

rna2	the RnaSequence to compare to

Returns: true if both are describing the same sequence with the same identifier.

◆ size()

size_t IntaRNA::RnaSequence::size ( ) const

inline

Access to the length of the sequence.

Returns: the length of the sequence.

Friends And Related Symbol Documentation

◆ operator<<

std::ostream & operator<<	(	std::ostream &	out,
		const RnaSequence &	rna
	)

friend

prints the sequence id and the sequence to stream

Parameters

out	the ostream to write to
rna	the RnaSequence object to add

Returns: the altered stream out

Member Data Documentation

◆ ambiguous

bool IntaRNA::RnaSequence::ambiguous

protected

Whether or not the sequence contains ambiguous nucleotide encodings.

◆ bpGUcodes

int IntaRNA::RnaSequence::bpGUcodes[]

staticprotected

codes for G and U to check for GU base pairs

◆ codeLocale

std::locale IntaRNA::RnaSequence::codeLocale

staticprotected

the locale to use for integer encoding

◆ id

std::string IntaRNA::RnaSequence::id

protected

ID of this sequence.

◆ idxPos0

long IntaRNA::RnaSequence::idxPos0

protected

Input/output index of the first sequence position.

◆ lastPos

const size_t IntaRNA::RnaSequence::lastPos

static

constant that serves as a placeholder for the last position within a sequence independent of its real size

◆ seqCode

CodeSeq_type IntaRNA::RnaSequence::seqCode

protected

Integer encoding of the sequence.

◆ seqNumber

size_t IntaRNA::RnaSequence::seqNumber

protected

index of the sequence within the overall input (1-based). relevant for reading accessibility files

◆ seqString

String_type IntaRNA::RnaSequence::seqString

protected

The sequence's string representation.

◆ SequenceAlphabet

const std::string IntaRNA::RnaSequence::SequenceAlphabet

static

Allowed nucleotide single letter character alphabet (uppercase only)

◆ SequenceAlphabetIUPAC

const std::string IntaRNA::RnaSequence::SequenceAlphabetIUPAC

static

Allowed nucleotide single letter character alphabet according to IUPAC codes and their lower case variants.

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

src/IntaRNA/RnaSequence.h

Public Types

Public Member Functions

Static Public Member Functions

Static Public Attributes

Protected Attributes

Static Protected Attributes

Friends

Detailed Description

Member Typedef Documentation

◆ Code_type

◆ CodeSeq_type

◆ String_type

Constructor & Destructor Documentation

◆ RnaSequence()

◆ ~RnaSequence()

Member Function Documentation

◆ areComplementary()

◆ asCodes()

◆ asString()

◆ getCodeForChar()

◆ getCodeForString()

◆ getId()

◆ getIndex()

◆ getInOutIndex()

◆ getReversedIndex()

◆ getSeqNumber()

◆ getUpperCase()

◆ isAmbiguous() [1/2]

◆ isAmbiguous() [2/2]

◆ isGU()

◆ isValidSequence()

◆ isValidSequenceIUPAC()

◆ operator==()

◆ size()

Friends And Related Symbol Documentation

◆ operator<<

Member Data Documentation

◆ ambiguous

◆ bpGUcodes

◆ codeLocale

◆ id

◆ idxPos0

◆ lastPos

◆ seqCode

◆ seqNumber

◆ seqString

◆ SequenceAlphabet

◆ SequenceAlphabetIUPAC