Utilitary methods dealing with sequence containers. More...

#include <Bpp/Seq/Container/SequenceContainerTools.h>

Public Member Functions
	SequenceContainerTools ()

virtual	~SequenceContainerTools ()

Static Public Member Functions
template<class SequenceType , class HashType >
static std::unique_ptr< TemplateSequenceContainerInterface< SequenceType, HashType > >	createContainerOfSpecifiedSize (std::shared_ptr< const Alphabet > &alphabet, size_t size)
	Create a container with void sequences. More...

template<class SequenceType , class HashType >
static std::unique_ptr< TemplateSequenceContainerInterface< SequenceType, HashType > >	createContainerWithSequenceNames (std::shared_ptr< const Alphabet > &alphabet, const std::vector< std::string > &seqNames)
	Create a container with specified names. More...

template<class ContFrom , class ContTo , class SequenceType >
static void	convertContainer (const ContFrom &input, ContTo &output)
	Generic function which creates a new container from another one, by specifying the class of sequence to be stored. More...

template<class SequenceType , class HashType >
static void	getSelectedSequences (const TemplateSequenceContainerInterface< SequenceType, HashType > &sequences, const SequenceSelection &selection, TemplateSequenceContainerInterface< SequenceType, HashType > &outputCont)
	Add a specified set of sequences from a container to another. More...

template<class SequenceType , class HashType >
static void	getSelectedSequences (const TemplateSequenceContainerInterface< SequenceType, HashType > &sequences, const std::vector< std::string > &selection, TemplateSequenceContainerInterface< SequenceType, HashType > &outputCont, bool strict=true)
	Add a specified set of sequences from a container to another. More...

template<class SequenceType , class HashType >
static void	keepOnlySelectedSequences (TemplateSequenceContainerInterface< SequenceType, HashType > &sequences, const SequenceSelection &selection)
	Remove all sequences that are not in a given selection from a given container. More...

template<class SequenceType , class HashType >
static bool	sequencesHaveTheSameLength (const TemplateSequenceContainerInterface< SequenceType, HashType > &sc)
	Check if all sequences in a SequenceContainer have the same length. More...

static void	getCounts (const SequenceContainerInterface &sc, std::map< int, unsigned int > &f)
	Compute base counts. More...

static void	getFrequencies (const SequenceContainerInterface &sc, std::map< int, double > &f, double pseudoCount=0)
	Compute base frequencies of a BasicSequenceContainer. More...

static void	getFrequencies (const ProbabilisticSequenceContainerInterface &sc, std::map< int, double > &f, double pseudoCount=0)
	Compute base frequencies of a ProbabilisticSequenceContainer. More...

static void	getFrequencies (const SequenceDataInterface &sc, std::map< int, double > &f, double pseudoCount=0)
	Compute base frequencies of an object implementing the SequenceDataInterface. More...

template<class SequenceType , class HashType >
static void	append (TemplateSequenceContainerInterface< SequenceType, HashType > &seqCont1, const TemplateSequenceContainerInterface< SequenceType, HashType > &seqCont2)
	Append all the sequences of a SequenceContainer to the end of another. More...

template<class SequenceType , class HashType >
static void	mergeByKey (const TemplateSequenceContainerInterface< SequenceType, HashType > &seqCont1, const TemplateSequenceContainerInterface< SequenceType, HashType > &seqCont2, TemplateSequenceContainerInterface< SequenceType, HashType > &outputCont)
	Concatenate the sequences from two containers. More...

template<class SequenceType , class HashType >
static void	convertAlphabet (const TemplateSequenceContainerInterface< SequenceType, HashType > &seqCont, TemplateSequenceContainerInterface< SequenceType, HashType > &outputCont)
	Convert a SequenceContainer to a new alphabet. More...

template<class SequenceType >
static std::unique_ptr< TemplateSequenceContainerInterface< SequenceType > >	getCodonPosition (const TemplateSequenceContainerInterface< SequenceType, std::string > &sequences, size_t pos)
	Extract a certain position (1, 2 or 3) from a container of codon sequences and returns the resulting nucleotide container. More...

Work with sequence names
Note that in case the container is indexed by sequence names, methods working directly on sequence keys will be more efficient!
template<class SequenceType , class HashType >
static bool	hasSequenceWithName (const TemplateSequenceContainerInterface< SequenceType, HashType > &sc, const std::string &name)
	Tells whether a sequence with the given name is present in the container. More...

Detailed Description

Utilitary methods dealing with sequence containers.

Definition at line 29 of file SequenceContainerTools.h.

Constructor & Destructor Documentation

◆ SequenceContainerTools()

bpp::SequenceContainerTools::SequenceContainerTools ( )

inline

Definition at line 32 of file SequenceContainerTools.h.

◆ ~SequenceContainerTools()

virtual bpp::SequenceContainerTools::~SequenceContainerTools ( )

inlinevirtual

Definition at line 33 of file SequenceContainerTools.h.

Member Function Documentation

◆ append()

template<class SequenceType , class HashType >

static void bpp::SequenceContainerTools::append	(	TemplateSequenceContainerInterface< SequenceType, HashType > &	seqCont1,
		const TemplateSequenceContainerInterface< SequenceType, HashType > &	seqCont2
	)

inlinestatic

Append all the sequences of a SequenceContainer to the end of another.

Parameters

seqCont1	The SequenceContainer in which the sequences will be added.
seqCont2	The SequenceContainer from which the sequences are taken.

Definition at line 403 of file SequenceContainerTools.h.

References bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::addSequence(), bpp::TemplateSequenceDataInterface< HashType >::getNumberOfSequences(), bpp::TemplateSequenceDataInterface< HashType >::getSequenceKeys(), and bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::sequence().

◆ convertAlphabet()

template<class SequenceType , class HashType >

static void bpp::SequenceContainerTools::convertAlphabet	(	const TemplateSequenceContainerInterface< SequenceType, HashType > &	seqCont,
		TemplateSequenceContainerInterface< SequenceType, HashType > &	outputCont
	)

inlinestatic

Convert a SequenceContainer to a new alphabet.

Parameters

seqCont	The container to convert.
outputCont	A container (most likely empty) with an alphabet into which the container will be converted.

Definition at line 453 of file SequenceContainerTools.h.

References bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::addSequence(), bpp::TemplateSequenceDataInterface< HashType >::getAlphabet(), bpp::TemplateSequenceDataInterface< HashType >::getNumberOfSequences(), bpp::TemplateSequenceDataInterface< HashType >::getSequenceKeys(), and bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::sequence().

◆ convertContainer()

template<class ContFrom , class ContTo , class SequenceType >

static void bpp::SequenceContainerTools::convertContainer	(	const ContFrom &	input,
		ContTo &	output
	)

inlinestatic

Generic function which creates a new container from another one, by specifying the class of sequence to be stored.

Compared to several copy constructors, this function allows to change the class of the inner sequence class used for storing sequences. The function used the addSequence method, so that it can also be used to concatenate containers.

Parameters

input	The container to copy.
output	The container where new sequences will be appended.

Definition at line 125 of file SequenceContainerTools.h.

◆ createContainerOfSpecifiedSize()

template<class SequenceType , class HashType >

static std::unique_ptr< TemplateSequenceContainerInterface<SequenceType, HashType> > bpp::SequenceContainerTools::createContainerOfSpecifiedSize	(	std::shared_ptr< const Alphabet > &	alphabet,
		size_t	size
	)

inlinestatic

Create a container with void sequences.

A new VectorSequenceContainer with the specified alphabet is created. The destruction of this new container is up to the user. Sequences have name "0", "1",... "n-1" and no content and comments.

Parameters

alphabet	The alphabet to use in the container.
size	The number of sequences in the container.

Returns: A pointer toward a newly created container.

Definition at line 78 of file SequenceContainerTools.h.

References bpp::TextTools::toString().

◆ createContainerWithSequenceNames()

template<class SequenceType , class HashType >

static std::unique_ptr< TemplateSequenceContainerInterface<SequenceType, HashType> > bpp::SequenceContainerTools::createContainerWithSequenceNames	(	std::shared_ptr< const Alphabet > &	alphabet,
		const std::vector< std::string > &	seqNames
	)

inlinestatic

Create a container with specified names.

A new VectorSequenceContainer with the specified alphabet is created. The destruction of this new container is up to the user. Sequences have the specified names and no content and comments.

Parameters

alphabet	The alphabet to use in the container.
seqNames	The names of the sequences.

Returns: A pointer toward a newly created container.

Exceptions

Exception If two sequence names are not unique.

Definition at line 102 of file SequenceContainerTools.h.

◆ getCodonPosition()

template<class SequenceType >

static std::unique_ptr< TemplateSequenceContainerInterface<SequenceType> > bpp::SequenceContainerTools::getCodonPosition	(	const TemplateSequenceContainerInterface< SequenceType, std::string > &	sequences,
		size_t	pos
	)

inlinestatic

Extract a certain position (1, 2 or 3) from a container of codon sequences and returns the resulting nucleotide container.

Parameters

sequences	The input sequence container, with codon alphabet.
pos	The codon position to retrieve.

Returns: A SequenceContainer with a nucleotide alphabet.

Exceptions

AlphabetException If input sequences are not registered with a codon alphabet.

Definition at line 478 of file SequenceContainerTools.h.

References bpp::TemplateSequenceDataInterface< HashType >::getAlphabet(), bpp::TemplateSequenceDataInterface< HashType >::getNumberOfSequences(), bpp::TemplateSequenceDataInterface< HashType >::getSequenceKeys(), and bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::sequence().

◆ getCounts()

static void bpp::SequenceContainerTools::getCounts	(	const SequenceContainerInterface &	sc,
		std::map< int, unsigned int > &	f
	)

inlinestatic

Compute base counts.

Example of usage: getting the GC count from a sequence container. map<int, unsigned int> counts; SequenceContainerTools::getCounts(myContainer, counts); //My container is previously defined. int GCcontent = counts[1] + counts[2] ;

States are stored as their int code.

Definition at line 272 of file SequenceContainerTools.h.

References bpp::TemplateSequenceDataInterface< HashType >::getNumberOfSequences(), bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::sequence(), and bpp::AbstractTemplateSymbolList< T >::size().

◆ getFrequencies() [1/3]

static void bpp::SequenceContainerTools::getFrequencies	(	const ProbabilisticSequenceContainerInterface &	sc,
		std::map< int, double > &	f,
		double	pseudoCount = `0`
	)

inlinestatic

Compute base frequencies of a ProbabilisticSequenceContainer.

Example of usage: getting the GC content from a sequence container. map<int, double> freqs; SequenceContainerTools::getFrequencies(myContainer, freqs); //My container is previously defined. double GCcontent = (freqs[1] + freqs[2]) / (freqs[0] + freqs[1] + freqs[2] + freqs[3]);

States are stored as their int code.

Definition at line 339 of file SequenceContainerTools.h.

References bpp::TemplateSequenceDataInterface< HashType >::getAlphabet(), bpp::SymbolListTools::getCounts(), bpp::TemplateSequenceDataInterface< HashType >::getNumberOfSequences(), bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::sequence(), and bpp::ProbabilisticSymbolList::size().

◆ getFrequencies() [2/3]

static void bpp::SequenceContainerTools::getFrequencies	(	const SequenceContainerInterface &	sc,
		std::map< int, double > &	f,
		double	pseudoCount = `0`
	)

inlinestatic

Compute base frequencies of a BasicSequenceContainer.

Example of usage: getting the GC content from a sequence container. map<int, double> freqs; SequenceContainerTools::getFrequencies(myContainer, freqs); //My container is previously defined. double GCcontent = (freqs[1] + freqs[2]) / (freqs[0] + freqs[1] + freqs[2] + freqs[3]);

States are stored as their int code.

Definition at line 297 of file SequenceContainerTools.h.

References bpp::TemplateSequenceDataInterface< HashType >::getAlphabet(), bpp::SymbolListTools::getCounts(), bpp::TemplateSequenceDataInterface< HashType >::getNumberOfSequences(), bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::sequence(), and bpp::AbstractTemplateSymbolList< T >::size().

Referenced by getFrequencies().

◆ getFrequencies() [3/3]

static void bpp::SequenceContainerTools::getFrequencies	(	const SequenceDataInterface &	sc,
		std::map< int, double > &	f,
		double	pseudoCount = `0`
	)

inlinestatic

Compute base frequencies of an object implementing the SequenceDataInterface.

This method will try to cast the input data and call the corresponding method is any. An exception will be thrown if the cast failed.

Definition at line 375 of file SequenceContainerTools.h.

References getFrequencies().

◆ getSelectedSequences() [1/2]

template<class SequenceType , class HashType >

static void bpp::SequenceContainerTools::getSelectedSequences	(	const TemplateSequenceContainerInterface< SequenceType, HashType > &	sequences,
		const SequenceSelection &	selection,
		TemplateSequenceContainerInterface< SequenceType, HashType > &	outputCont
	)

inlinestatic

Add a specified set of sequences from a container to another.

Sequences are specified by their position, beginning at 0. Name verification will be performed, only if the output container is not empty, based on the assumption that the container passed as argument is a correct one. Redundant selection is not checked, so be careful with what you're doing!

Author: Julien Dutheil

Parameters

sequences	The container from which sequences are to be taken.
selection	The positions of all sequences to retrieve.
outputCont	A container where the selection should be added.

Exceptions

Exception In case of bad sequence name, alphabet mismatch, etc.

Definition at line 150 of file SequenceContainerTools.h.

References bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::addSequence(), and bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::sequence().

Referenced by bpp::SiteContainerTools::merge().

◆ getSelectedSequences() [2/2]

template<class SequenceType , class HashType >

static void bpp::SequenceContainerTools::getSelectedSequences	(	const TemplateSequenceContainerInterface< SequenceType, HashType > &	sequences,
		const std::vector< std::string > &	selection,
		TemplateSequenceContainerInterface< SequenceType, HashType > &	outputCont,
		bool	strict = `true`
	)

inlinestatic

Add a specified set of sequences from a container to another.

Sequences are specified by their names. Name verification will be performed, only if the output container is not empty, based on the assumption that the container passed as argument is a correct one. Redundant selection is not checked, so be careful with what you're doing!

Author: Julien Dutheil

Parameters

sequences	The container from which sequences are to be taken.
selection	The names of all sequences to retrieve.
outputCont	A container where the selection should be added.
strict	If yes, trying to select a sequence that is not present will raise an exception. If no, only available sequence will be added.

Exceptions

Exception In case of bad sequence name, alphabet mismatch, etc.

Definition at line 181 of file SequenceContainerTools.h.

References bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::addSequence(), bpp::TemplateSequenceDataInterface< HashType >::hasSequence(), and bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::sequence().

◆ hasSequenceWithName()

template<class SequenceType , class HashType >

static bool bpp::SequenceContainerTools::hasSequenceWithName	(	const TemplateSequenceContainerInterface< SequenceType, HashType > &	sc,
		const std::string &	name
	)

inlinestatic

Tells whether a sequence with the given name is present in the container.

Parameters

sc	The sequence container to check.
name	The query sequence name.

Definition at line 51 of file SequenceContainerTools.h.

References bpp::TemplateSequenceDataInterface< HashType >::getNumberOfSequences(), and bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::sequence().

◆ keepOnlySelectedSequences()

template<class SequenceType , class HashType >

static void bpp::SequenceContainerTools::keepOnlySelectedSequences	(	TemplateSequenceContainerInterface< SequenceType, HashType > &	sequences,
		const SequenceSelection &	selection
	)

inlinestatic

Remove all sequences that are not in a given selection from a given container.

A new VectorSequenceContainer is created with specified sequences. The destruction of the container is up to the user. Sequences are specified by their position, beginning at 0. Redundant selection is not checked, so be careful with what you're doing!

Parameters

sequences	The container from which sequences are to be taken.
selection	The positions of all sequences to retrieve.

Returns: A new container with all selected sequences.

Definition at line 219 of file SequenceContainerTools.h.

References bpp::VectorTools::diff(), bpp::TemplateSequenceDataInterface< HashType >::getSequenceKeys(), and bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::removeSequence().

◆ mergeByKey()

template<class SequenceType , class HashType >

static void bpp::SequenceContainerTools::mergeByKey	(	const TemplateSequenceContainerInterface< SequenceType, HashType > &	seqCont1,
		const TemplateSequenceContainerInterface< SequenceType, HashType > &	seqCont2,
		TemplateSequenceContainerInterface< SequenceType, HashType > &	outputCont
	)

inlinestatic

Concatenate the sequences from two containers.

Author: Julien Dutheil

Parameters

seqCont1	First container.
seqCont2	Second container. This container must contain sequences with the same keys as in seqcont1. Additional sequences will be ignored.
outputCont	Output sequence container to which concatenated sequences will be added.

Exceptions

AlphabetMismatchException If the alphabet in the 3 containers do not match.

Definition at line 429 of file SequenceContainerTools.h.

References bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::addSequence(), bpp::TemplateSequenceDataInterface< HashType >::getAlphabet(), bpp::TemplateSequenceDataInterface< HashType >::getSequenceKeys(), and bpp::TemplateSequenceContainerInterface< SequenceType, HashType >::sequence().

◆ sequencesHaveTheSameLength()

template<class SequenceType , class HashType >

static bool bpp::SequenceContainerTools::sequencesHaveTheSameLength ( const TemplateSequenceContainerInterface< SequenceType, HashType > & sc )

inlinestatic

Check if all sequences in a SequenceContainer have the same length.

Parameters

sc	The container to check.

Returns: True is all sequence have the same length.

Definition at line 243 of file SequenceContainerTools.h.

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

Bpp/Seq/Container/SequenceContainerTools.h

Public Member Functions

Static Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ SequenceContainerTools()

◆ ~SequenceContainerTools()

Member Function Documentation

◆ append()

◆ convertAlphabet()

◆ convertContainer()

◆ createContainerOfSpecifiedSize()

◆ createContainerWithSequenceNames()

◆ getCodonPosition()

◆ getCounts()

◆ getFrequencies() [1/3]

◆ getFrequencies() [2/3]

◆ getFrequencies() [3/3]

◆ getSelectedSequences() [1/2]

◆ getSelectedSequences() [2/2]

◆ hasSequenceWithName()

◆ keepOnlySelectedSequences()

◆ mergeByKey()

◆ sequencesHaveTheSameLength()