#include <Bpp/Seq/SequenceTools.h>

Inheritance diagram for bpp::SequenceTools:

Collaboration diagram for bpp::SequenceTools:

Public Member Functions
	SequenceTools ()

virtual	~SequenceTools ()

Static Public Member Functions
static bool	areSequencesIdentical (const SequenceInterface &seq1, const SequenceInterface &seq2)

static void	subseq (const SequenceInterface &sequence, size_t begin, size_t end, SequenceInterface &output)
	Get a sub-sequence. More...

template<class SequenceTypeOut >
static std::unique_ptr< SequenceTypeOut >	subseq (const SequenceInterface &sequence, size_t begin, size_t end)
	Get a sub-sequence. More...

template<class SequenceTypeOut >
static std::unique_ptr< SequenceTypeOut >	concatenate (const SequenceInterface &seq1, const SequenceInterface &seq2)
	Concatenate two sequences. More...

static void	complement (SequenceInterface &seq)
	Complement the nucleotide sequence itself. More...

static std::unique_ptr< Sequence >	getComplement (const SequenceInterface &sequence)
	Get the complementary sequence of a nucleotide sequence. More...

static std::unique_ptr< Sequence >	transcript (const Sequence &sequence)
	Get the transcription sequence of a DNA sequence. More...

static std::unique_ptr< Sequence >	reverseTranscript (const Sequence &sequence)
	Get the reverse-transcription sequence of a RNA sequence. More...

static void	invert (SequenceInterface &seq)
	Inverse a sequence from 5'->3' to 3'->5' and vice-versa. More...

static std::unique_ptr< SequenceInterface >	getInvert (const SequenceInterface &sequence)
	Inverse a sequence from 5'->3' to 3'->5' and vice-versa. More...

static void	invertComplement (SequenceInterface &seq)
	Inverse and complement a sequence. More...

static double	getPercentIdentity (const SequenceInterface &seq1, const SequenceInterface &seq2, bool ignoreGaps=false)

static size_t	getNumberOfSites (const SequenceInterface &seq)

static size_t	getNumberOfCompleteSites (const SequenceInterface &seq)

static std::unique_ptr< SequenceInterface >	getSequenceWithCompleteSites (const SequenceInterface &seq)
	keep only complete sites in a sequence. More...

static size_t	getNumberOfUnresolvedSites (const SequenceInterface &seq)

static void	removeGaps (SequenceInterface &seq)
	Remove gaps from a sequence. More...

static std::unique_ptr< SequenceInterface >	getSequenceWithoutGaps (const SequenceInterface &seq)
	Get a copy of the sequence without gaps. More...

static void	removeStops (SequenceInterface &seq, const GeneticCode &gCode)
	Remove stops from a codon sequence. More...

static std::unique_ptr< SequenceInterface >	getSequenceWithoutStops (const SequenceInterface &seq, const GeneticCode &gCode)
	Get a copy of the codon sequence without stops. More...

static void	replaceStopsWithGaps (SequenceInterface &seq, const GeneticCode &gCode)
	Replace stop codons by gaps. More...

static std::unique_ptr< BowkerTest >	bowkerTest (const SequenceInterface &seq1, const SequenceInterface &seq2)
	Bowker's test for homogeneity. More...

static void	getPutativeHaplotypes (const SequenceInterface &seq, std::vector< std::unique_ptr< SequenceInterface >> &hap, unsigned int level=2)
	Get all putatives haplotypes from an heterozygous sequence. More...

static std::unique_ptr< Sequence >	combineSequences (const SequenceInterface &s1, const SequenceInterface &s2)
	Combine two sequences. More...

static std::unique_ptr< Sequence >	subtractHaplotype (const SequenceInterface &s, const SequenceInterface &h, std::string name="", unsigned int level=1)
	Subtract haplotype from an heterozygous sequence. More...

static std::unique_ptr< Sequence >	RNYslice (const SequenceInterface &sequence, int ph)
	Get the RNY decomposition of a DNA sequence. More...

static std::unique_ptr< Sequence >	RNYslice (const SequenceInterface &sequence)
	Get the RNY decomposition of a DNA sequence. More...

static void	getCDS (SequenceInterface &sequence, const GeneticCode &gCode, bool checkInit, bool checkStop, bool includeInit=true, bool includeStop=true)
	Extract CDS part from a codon sequence. Optionally check for intiator and stop codons, or both. More...

static size_t	findFirstOf (const SequenceInterface &seq, const SequenceInterface &motif, bool strict=true)
	Find the position of a motif in a sequence. More...

static std::unique_ptr< Sequence >	getRandomSequence (std::shared_ptr< const Alphabet > &alphabet, size_t length)
	Get a random sequence of given size and alphabet, with all state with equal probability. More...

static bool	hasGap (const IntSymbolListInterface &site)

static bool	hasGap (const ProbabilisticSymbolListInterface &site)

static bool	hasGap (const CruxSymbolListInterface &site)

static bool	hasUnresolved (const IntSymbolListInterface &site)

static bool	isGapOnly (const IntSymbolListInterface &site)

static bool	isGapOnly (const ProbabilisticSymbolListInterface &site)

static bool	isGapOnly (const CruxSymbolListInterface &site)

static size_t	numberOfGaps (const IntSymbolListInterface &site)

static size_t	numberOfGaps (const ProbabilisticSymbolListInterface &site)

static size_t	numberOfGaps (const CruxSymbolListInterface &site)

static bool	isGapOrUnresolvedOnly (const IntSymbolListInterface &site)

static bool	isGapOrUnresolvedOnly (const ProbabilisticSymbolListInterface &site)

static bool	isGapOrUnresolvedOnly (const CruxSymbolListInterface &site)

static size_t	numberOfUnresolved (const IntSymbolListInterface &site)

static size_t	numberOfUnresolved (const ProbabilisticSymbolListInterface &site)

static size_t	numberOfUnresolved (const CruxSymbolListInterface &site)

static bool	hasUnknown (const IntSymbolListInterface &site)

static bool	hasUnknown (const ProbabilisticSymbolListInterface &site)

static bool	hasUnknown (const CruxSymbolListInterface &site)

static bool	isComplete (const IntSymbolListInterface &site)

static bool	isComplete (const ProbabilisticSymbolListInterface &site)

static bool	isComplete (const CruxSymbolListInterface &site)

static bool	isConstant (const IntSymbolListInterface &site, bool ignoreUnknown=false, bool unresolvedRaisesException=true)
	Tell if a site is constant, that is displaying the same state in all sequences that do not present a gap. More...

static bool	isConstant (const ProbabilisticSymbolListInterface &site, bool unresolvedRaisesException=true)

static bool	isConstant (const CruxSymbolListInterface &site, bool ignoreUnknown=false, bool unresolvedRaisesException=true)

static bool	areSymbolListsIdentical (const IntSymbolListInterface &list1, const IntSymbolListInterface &list2)

static bool	areSymbolListsIdentical (const ProbabilisticSymbolListInterface &list1, const ProbabilisticSymbolListInterface &list2)

static bool	areSymbolListsIdentical (const CruxSymbolListInterface &l1, const CruxSymbolListInterface &l2)

template<class count_type >
static void	getCounts (const IntSymbolListInterface &list, std::map< int, count_type > &counts)
	Count all states in the list. More...

static void	getCounts (const ProbabilisticSymbolListInterface &list, std::map< int, double_t > &counts)
	Sum all states in the list. More...

static void	getCounts (const CruxSymbolListInterface &list, std::map< int, double > &counts, bool resolveUnknowns=false)
	Count all states in the list, optionally resolving unknown characters. More...

template<class count_type >
static void	getCounts (const IntSymbolListInterface &list1, const IntSymbolListInterface &list2, std::map< int, std::map< int, count_type >> &counts)
	Count all pair of states for two lists of the same size. More...

static void	getCounts (const ProbabilisticSymbolListInterface &list1, const ProbabilisticSymbolListInterface &list2, std::map< int, std::map< int, double >> &counts)
	Sum along the lists the joined probabilities for all pair of states for two lists of the same size. More...

static void	getCounts (const CruxSymbolListInterface &list1, const CruxSymbolListInterface &list2, std::map< int, std::map< int, double >> &counts, bool resolveUnknowns)
	Count all pairs of states for two lists of the same size, optionally resolving unknown characters. More...

static void	getCountsResolveUnknowns (const IntSymbolListInterface &list, std::map< int, double > &counts)
	Count all states in the list normalizing unknown characters. More...

static void	getCountsResolveUnknowns (const ProbabilisticSymbolListInterface &list, std::map< int, double > &counts)
	Count all states in the list normalizing unknown characters. More...

static void	getCountsResolveUnknowns (const IntSymbolListInterface &list1, const IntSymbolListInterface &list2, std::map< int, std::map< int, double >> &counts)
	Count all pairs of states for two lists of the same size resolving unknown characters. More...

static void	getCountsResolveUnknowns (const ProbabilisticSymbolListInterface &list1, const ProbabilisticSymbolListInterface &list2, std::map< int, std::map< int, double >> &counts)
	Count all pairs of states for two lists of the same size resolving unknown characters. More...

static void	getFrequencies (const CruxSymbolListInterface &list, std::map< int, double > &frequencies, bool resolveUnknowns=false)
	Get all states frequencies in the list. More...

static void	getFrequencies (const CruxSymbolListInterface &list1, const CruxSymbolListInterface &list2, std::map< int, std::map< int, double >> &frequencies, bool resolveUnknowns=false)
	Get all state pairs frequencies for two lists of the same size. More...

static double	getGCContent (const IntSymbolListInterface &list, bool ignoreUnresolved=true, bool ignoreGap=true)
	Get the GC content of a symbol list. More...

static double	getGCContent (const ProbabilisticSymbolListInterface &list, bool ignoreUnresolved=true, bool ignoreGap=true)

static double	getGCContent (const CruxSymbolListInterface &list, bool ignoreUnresolved=true, bool ignoreGap=true)

static size_t	getNumberOfDistinctPositions (const IntSymbolListInterface &l1, const IntSymbolListInterface &l2)
	Get the number of distinct positions. More...

static size_t	getNumberOfDistinctPositions (const ProbabilisticSymbolListInterface &l1, const ProbabilisticSymbolListInterface &l2)

static size_t	getNumberOfDistinctPositions (const CruxSymbolListInterface &l1, const CruxSymbolListInterface &l2)

static size_t	getNumberOfPositionsWithoutGap (const IntSymbolListInterface &l1, const IntSymbolListInterface &l2)
	Get the number of positions without gap (or without null column). More...

static size_t	getNumberOfPositionsWithoutGap (const ProbabilisticSymbolListInterface &l1, const ProbabilisticSymbolListInterface &l2)

static size_t	getNumberOfPositionsWithoutGap (const CruxSymbolListInterface &l1, const CruxSymbolListInterface &l2)

static void	changeGapsToUnknownCharacters (IntSymbolListInterface &l)
	Change all gap elements to unknown characters (or columns of 1). More...

static void	changeGapsToUnknownCharacters (ProbabilisticSymbolListInterface &l)

static void	changeGapsToUnknownCharacters (CruxSymbolListInterface &l)

static void	changeUnresolvedCharactersToGaps (IntSymbolListInterface &l)
	Change all unknown characters to gap elements (or columns of 0). More...

static void	changeUnresolvedCharactersToGaps (ProbabilisticSymbolListInterface &l)

static void	changeUnresolvedCharactersToGaps (CruxSymbolListInterface &l)

static double	variabilityShannon (const CruxSymbolListInterface &list, bool resolveUnknowns)
	Compute the Shannon entropy index of a SymbolList. More...

static double	variabilityFactorial (const IntSymbolListInterface &list)
	Compute the factorial diversity index of a site. More...

static double	mutualInformation (const CruxSymbolListInterface &list1, const CruxSymbolListInterface &list2, bool resolveUnknowns)
	Compute the mutual information between two lists. More...

static double	entropy (const CruxSymbolListInterface &list, bool resolveUnknowns)
	Compute the entropy of a site. This is an alias of method variabilityShannon. More...

static double	jointEntropy (const CruxSymbolListInterface &list1, const CruxSymbolListInterface &list2, bool resolveUnknowns)
	Compute the joint entropy between two lists. More...

static double	heterozygosity (const CruxSymbolListInterface &list)
	Compute the heterozygosity index of a list. More...

static size_t	getNumberOfDistinctCharacters (const IntSymbolListInterface &list)
	Give the number of distinct characters at a list. More...

static size_t	getMajorAlleleFrequency (const IntSymbolListInterface &list)
	return the number of occurrences of the most common allele. More...

static int	getMajorAllele (const CruxSymbolListInterface &list)
	return the state corresponding to the most common allele. More...

static size_t	getMinorAlleleFrequency (const IntSymbolListInterface &list)
	return the number of occurrences of the least common allele. More...

static int	getMinorAllele (const CruxSymbolListInterface &list)
	return the state corresponding to the least common allele. More...

static bool	hasSingleton (const IntSymbolListInterface &list)
	Tell if a list has singletons. More...

static bool	isParsimonyInformativeSite (const IntSymbolListInterface &site)
	Tell if a site is a parsimony informative site. More...

static bool	isTriplet (const IntSymbolListInterface &list)
	Tell if a list has more than 2 distinct characters. More...

static bool	isDoubleton (const IntSymbolListInterface &list)
	Tell if a list has exactly 2 distinct characters. More...

Static Private Attributes
static std::shared_ptr< RNY >	RNY_

static NucleicAcidsReplication	DNARep_

static NucleicAcidsReplication	RNARep_

static NucleicAcidsReplication	transc_

Detailed Description

SequenceTools static class.

Implement methods to manipulate sequences

Definition at line 62 of file SequenceTools.h.

Constructor & Destructor Documentation

◆ SequenceTools()

bpp::SequenceTools::SequenceTools ( )

inline

Definition at line 72 of file SequenceTools.h.

◆ ~SequenceTools()

virtual bpp::SequenceTools::~SequenceTools ( )

inlinevirtual

Definition at line 73 of file SequenceTools.h.

Member Function Documentation

◆ areSequencesIdentical()

bool SequenceTools::areSequencesIdentical	(	const SequenceInterface &	seq1,
		const SequenceInterface &	seq2
	)

static

Parameters

seq1	The first sequence.
seq2	The second sequence.

Returns: True if the two sequences have the same content (and, of course, alphabet).

Definition at line 29 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

◆ areSymbolListsIdentical() [1/3]

static bool bpp::SymbolListTools::areSymbolListsIdentical	(	const CruxSymbolListInterface &	l1,
		const CruxSymbolListInterface &	l2
	)

inlinestaticinherited

Definition at line 239 of file SymbolListTools.h.

References bpp::SymbolListTools::areSymbolListsIdentical().

◆ areSymbolListsIdentical() [2/3]

bool SymbolListTools::areSymbolListsIdentical	(	const IntSymbolListInterface &	list1,
		const IntSymbolListInterface &	list2
	)

staticinherited

Parameters

list1	The first site.
list2	The second site.

Returns: True if the two sites have the same content (and, of course, alphabet).

Definition at line 216 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SymbolListTools::areSymbolListsIdentical().

◆ areSymbolListsIdentical() [3/3]

bool SymbolListTools::areSymbolListsIdentical	(	const ProbabilisticSymbolListInterface &	list1,
		const ProbabilisticSymbolListInterface &	list2
	)

staticinherited

Definition at line 236 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

◆ bowkerTest()

unique_ptr< BowkerTest > SequenceTools::bowkerTest	(	const SequenceInterface &	seq1,
		const SequenceInterface &	seq2
	)

static

Bowker's test for homogeneity.

Computes the contingency table of occurrence of all pairs of states and test its symmetry using Bowker's (1948) test.

Reference:

Ababneh F. Bioinformatics 2006 22(10) 1225-1231

Parameters

seq1	The first sequence.
seq2	The second sequence.

Returns: A BowkerTest object with the computed statistic and p-value (computed from a chi square distribution).

Exceptions

SequenceNotAlignedException If the two sequences do not have the same length.

Definition at line 353 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), bpp::RandomTools::pChisq(), and bpp::CruxSymbolListInterface::size().

◆ changeGapsToUnknownCharacters() [1/3]

static void bpp::SymbolListTools::changeGapsToUnknownCharacters ( CruxSymbolListInterface & l )

inlinestaticinherited

Definition at line 709 of file SymbolListTools.h.

References bpp::SymbolListTools::changeGapsToUnknownCharacters().

◆ changeGapsToUnknownCharacters() [2/3]

void SymbolListTools::changeGapsToUnknownCharacters ( IntSymbolListInterface & l )

staticinherited

Change all gap elements to unknown characters (or columns of 1).

Parameters

l	The input list of characters.

Definition at line 501 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SymbolListTools::changeGapsToUnknownCharacters().

◆ changeGapsToUnknownCharacters() [3/3]

void SymbolListTools::changeGapsToUnknownCharacters ( ProbabilisticSymbolListInterface & l )

staticinherited

Definition at line 614 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ changeUnresolvedCharactersToGaps() [1/3]

static void bpp::SymbolListTools::changeUnresolvedCharactersToGaps ( CruxSymbolListInterface & l )

inlinestaticinherited

Definition at line 736 of file SymbolListTools.h.

References bpp::SymbolListTools::changeUnresolvedCharactersToGaps().

◆ changeUnresolvedCharactersToGaps() [2/3]

void SymbolListTools::changeUnresolvedCharactersToGaps ( IntSymbolListInterface & l )

staticinherited

Change all unknown characters to gap elements (or columns of 0).

Parameters

l	The input list of characters.

Definition at line 511 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SymbolListTools::changeUnresolvedCharactersToGaps().

◆ changeUnresolvedCharactersToGaps() [3/3]

void SymbolListTools::changeUnresolvedCharactersToGaps ( ProbabilisticSymbolListInterface & l )

staticinherited

Definition at line 623 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ combineSequences()

unique_ptr< Sequence > SequenceTools::combineSequences	(	const SequenceInterface &	s1,
		const SequenceInterface &	s2
	)

static

Combine two sequences.

Author: Sylvain Gaillard

Definition at line 462 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::alphabet(), bpp::CruxSymbolListInterface::getAlphabet(), bpp::Alphabet::getAlphabetType(), bpp::CoreSequenceInterface::getName(), bpp::TemplateCoreSymbolListInterface< T >::getValue(), bpp::NumTools::max(), and bpp::CruxSymbolListInterface::size().

◆ complement()

void SequenceTools::complement ( SequenceInterface & seq )

static

Complement the nucleotide sequence itself.

Parameters

seq	The sequence to be complemented.

Exceptions

AlphabetException if the sequence is not a nucleotide sequence.

Author: Sylvain Gaillard

Definition at line 49 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::alphabet(), bpp::CruxSymbolListInterface::getAlphabet(), bpp::TemplateCoreSymbolListInterface< T >::getValue(), bpp::AlphabetTools::isDNAAlphabet(), bpp::AlphabetTools::isRNAAlphabet(), bpp::IntSymbolListInterface::setElement(), bpp::CruxSymbolListInterface::size(), and bpp::NucleicAcidsReplication::translate().

◆ concatenate()

template<class SequenceTypeOut >

static std::unique_ptr<SequenceTypeOut> bpp::SequenceTools::concatenate	(	const SequenceInterface &	seq1,
		const SequenceInterface &	seq2
	)

inlinestatic

Concatenate two sequences.

Sequences must have the same name and alphabets. Only first sequence's commentaries are kept.

Parameters

seq1	The first sequence.
seq2	The second sequence.

Returns: A new sequence object with the concatenation of the two sequences. The type of the output sequence is the same as the one of seq1, as it is created using the clone method.

Exceptions

AlphabetMismatchException	If the two alphabets do not match.
Exception	If the sequence names do not match.

Definition at line 137 of file SequenceTools.h.

References bpp::CruxSymbolListInterface::alphabet(), bpp::CruxSymbolListInterface::getAlphabet(), bpp::Alphabet::getAlphabetType(), bpp::CoreSequenceInterface::getName(), and bpp::CruxSymbolListInterface::size().

◆ entropy()

static double bpp::SymbolListTools::entropy	(	const CruxSymbolListInterface &	list,
		bool	resolveUnknowns
	)

inlinestaticinherited

Compute the entropy of a site. This is an alias of method variabilityShannon.

$I = - \sum_x f_x\cdot \ln(f_x)$

where is the frequency of state .

Author: J. Dutheil

Parameters

list	A list.
resolveUnknowns	Tell is unknown characters must be resolved.

Returns: The Shannon entropy index of this list.

Definition at line 817 of file SymbolListTools.h.

References bpp::SymbolListTools::variabilityShannon().

◆ findFirstOf()

size_t SequenceTools::findFirstOf	(	const SequenceInterface &	seq,
		const SequenceInterface &	motif,
		bool	strict = `true`
	)

static

Find the position of a motif in a sequence.

Parameters

seq	The reference sequence
motif	The motif to find
strict	If true (default) find exactly the motif If false find compatible match

Returns: The position of the first occurrence of the motif or the seq length.

Definition at line 642 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), bpp::TemplateCoreSymbolListInterface< T >::getValue(), bpp::AlphabetTools::match(), and bpp::CruxSymbolListInterface::size().

◆ getCDS()

void SequenceTools::getCDS	(	SequenceInterface &	sequence,
		const GeneticCode &	gCode,
		bool	checkInit,
		bool	checkStop,
		bool	includeInit = `true`,
		bool	includeStop = `true`
	)

static

Extract CDS part from a codon sequence. Optionally check for intiator and stop codons, or both.

Parameters

sequence	The sequence to be reduced to CDS part.
gCode	The genetic code according to which start and stop codons are specified.
checkInit	If true, then everything before the initiator codon will be removed, together with the initiator codon if includeInit is false.
checkStop	If true, then everything after the first stop codon will be removed, together with the stop codon if includeStop is false.
includeInit	Tell if initiator codon should be kept or removed. No effect if checkInit is false.
includeStop	Tell if stop codon should be kept or removed. No effect if checkStop is false.

Definition at line 607 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::deleteElement(), bpp::CruxSymbolListInterface::getAlphabet(), bpp::GeneticCode::isStart(), bpp::GeneticCode::isStop(), and bpp::CruxSymbolListInterface::size().

◆ getComplement()

unique_ptr< Sequence > SequenceTools::getComplement ( const SequenceInterface & sequence )

static

Get the complementary sequence of a nucleotide sequence.

See also: DNAReplication

Returns: A new sequence object with the complementary sequence.

Parameters

sequence The sequence to complement.

Exceptions

AlphabetException If the sequence is not a nucleotide sequence.

Definition at line 73 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::alphabet(), bpp::CruxSymbolListInterface::getAlphabet(), bpp::AlphabetTools::isDNAAlphabet(), bpp::AlphabetTools::isRNAAlphabet(), and bpp::NucleicAcidsReplication::translate().

◆ getCounts() [1/6]

static void bpp::SymbolListTools::getCounts	(	const CruxSymbolListInterface &	list,
		std::map< int, double > &	counts,
		bool	resolveUnknowns = `false`
	)

inlinestaticinherited

Count all states in the list, optionally resolving unknown characters.

For instance, in DNA, N will be counted as A=1/4,T=1/4,C=1/4,G=1/4.

Author: J. Dutheil

Parameters

list	The list.
counts	The output map to store the counts (existing ocunts will be incremented).
resolveUnknowns	Tell is unknown characters must be resolved.

Returns: A map with all states and corresponding counts.

Definition at line 360 of file SymbolListTools.h.

References bpp::SymbolListTools::getCounts(), and bpp::SymbolListTools::getCountsResolveUnknowns().

◆ getCounts() [2/6]

static void bpp::SymbolListTools::getCounts	(	const CruxSymbolListInterface &	list1,
		const CruxSymbolListInterface &	list2,
		std::map< int, std::map< int, double >> &	counts,
		bool	resolveUnknowns
	)

inlinestaticinherited

Count all pairs of states for two lists of the same size, optionally resolving unknown characters.

For instance, in DNA, N will be counted as A=1/4,T=1/4,C=1/4,G=1/4.

NB: The two lists do node need to share the same alphabet! The states of the first list will be used as the first index in the output, and the ones from the second list as the second index.

Author: J. Dutheil

Parameters

list1	The first list.
list2	The second list.
counts	The output map to store the counts (existing ocunts will be incremented).
resolveUnknowns	Tell is unknown characters must be resolved. For instance, in DNA, N will be counted as A=1/4,T=1/4,C=1/4,G=1/4.

Returns: A map with all states and corresponding counts.

Definition at line 514 of file SymbolListTools.h.

References bpp::SymbolListTools::getCounts(), and bpp::SymbolListTools::getCountsResolveUnknowns().

◆ getCounts() [3/6]

template<class count_type >

static void bpp::SymbolListTools::getCounts	(	const IntSymbolListInterface &	list,
		std::map< int, count_type > &	counts
	)

inlinestaticinherited

Count all states in the list.

Author: J. Dutheil

Parameters

list	The list.
counts	The output map to store the counts (existing counts will be incremented).

Definition at line 265 of file SymbolListTools.h.

References bpp::CruxSymbolListInterface::size().

Referenced by bpp::SymbolListTools::getCounts(), bpp::SequenceContainerTools::getFrequencies(), bpp::CodonSiteTools::isSynonymousPolymorphic(), and bpp::CodonSiteTools::numberOfNonSynonymousSubstitutions().

◆ getCounts() [4/6]

template<class count_type >

static void bpp::SymbolListTools::getCounts	(	const IntSymbolListInterface &	list1,
		const IntSymbolListInterface &	list2,
		std::map< int, std::map< int, count_type >> &	counts
	)

inlinestaticinherited

Count all pair of states for two lists of the same size.

NB: The two lists do node need to share the same alphabet! The states of the first list will be used as the first index in the output, and the ones from the second list as the second index.

Author: J. Dutheil

Parameters

list1	The first list.
list2	The second list.
counts	The output map to store the counts (existing counts will be incremented).

Definition at line 412 of file SymbolListTools.h.

References bpp::CruxSymbolListInterface::size().

◆ getCounts() [5/6]

static void bpp::SymbolListTools::getCounts	(	const ProbabilisticSymbolListInterface &	list,
		std::map< int, double_t > &	counts
	)

inlinestaticinherited

Sum all states in the list.

Parameters

list	The list.
counts	The output map to store the sum for all states (existing counts will be summed).

Definition at line 282 of file SymbolListTools.h.

References bpp::CruxSymbolListInterface::size().

◆ getCounts() [6/6]

static void bpp::SymbolListTools::getCounts	(	const ProbabilisticSymbolListInterface &	list1,
		const ProbabilisticSymbolListInterface &	list2,
		std::map< int, std::map< int, double >> &	counts
	)

inlinestaticinherited

Sum along the lists the joined probabilities for all pair of states for two lists of the same size.

NB: The two lists do node need to share the same alphabet! The states of the first list will be used as the first index in the output, and the ones from the second list as the second index.

Author: J. Dutheil

Parameters

list1	The first list.
list2	The second list.
counts	The output map to store the counts (existing counts will be summed).

Definition at line 437 of file SymbolListTools.h.

References bpp::CruxSymbolListInterface::size().

◆ getCountsResolveUnknowns() [1/4]

static void bpp::SymbolListTools::getCountsResolveUnknowns	(	const IntSymbolListInterface &	list,
		std::map< int, double > &	counts
	)

inlinestaticinherited

Count all states in the list normalizing unknown characters.

For instance, (1,1,1,1) will be counted as (1/4,1/4,1/4,1/4).

Author: J. Dutheil

Parameters

list	The list.
counts	The output map to store the counts (existing ocunts will be incremented).

Returns: A map with all states and corresponding counts.

Definition at line 306 of file SymbolListTools.h.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SymbolListTools::getCounts().

◆ getCountsResolveUnknowns() [2/4]

void SymbolListTools::getCountsResolveUnknowns	(	const IntSymbolListInterface &	list1,
		const IntSymbolListInterface &	list2,
		std::map< int, std::map< int, double >> &	counts
	)

staticinherited

Count all pairs of states for two lists of the same size resolving unknown characters.

For instance, (1,1,1,1) will be counted as (1/4,1/4,1/4,1/4).

NB: The two lists do node need to share the same alphabet! The states of the first list will be used as the first index in the output, and the ones from the second list as the second index.

Author: J. Dutheil

Parameters

list1	The first list.
list2	The second list.
counts	The output map to store the counts (existing ocunts will be incremented).

Returns: A map with all states and corresponding counts.

Definition at line 357 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

◆ getCountsResolveUnknowns() [3/4]

static void bpp::SymbolListTools::getCountsResolveUnknowns	(	const ProbabilisticSymbolListInterface &	list,
		std::map< int, double > &	counts
	)

inlinestaticinherited

Count all states in the list normalizing unknown characters.

For instance, (1,1,1,1) will be counted as (1/4,1/4,1/4,1/4).

Author: J. Dutheil

Parameters

list	The list.
counts	The output map to store the counts (existing ocunts will be incremented).

Returns: A map with all states and corresponding counts.

Definition at line 331 of file SymbolListTools.h.

References bpp::CruxSymbolListInterface::size(), and bpp::VectorTools::sum().

◆ getCountsResolveUnknowns() [4/4]

void SymbolListTools::getCountsResolveUnknowns	(	const ProbabilisticSymbolListInterface &	list1,
		const ProbabilisticSymbolListInterface &	list2,
		std::map< int, std::map< int, double >> &	counts
	)

staticinherited

Count all pairs of states for two lists of the same size resolving unknown characters.

For instance, (1,1,1,1) will be counted as (1/4,1/4,1/4,1/4).

NB: The two lists do node need to share the same alphabet! The states of the first list will be used as the first index in the output, and the ones from the second list as the second index.

Author: J. Dutheil

Parameters

list1	The first list.
list2	The second list.
counts	The output map to store the counts (existing ocunts will be incremented).

Returns: A map with all states and corresponding counts.

Definition at line 522 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ getFrequencies() [1/2]

void SymbolListTools::getFrequencies	(	const CruxSymbolListInterface &	list,
		std::map< int, double > &	frequencies,
		bool	resolveUnknowns = `false`
	)

staticinherited

Get all states frequencies in the list.

Author: J. Dutheil

Parameters

list	The list.
resolveUnknowns	Tell is unknown characters must be resolved. For instance, in DNA, N will be counted as A=1/4,T=1/4,C=1/4,G=1/4.
frequencies	The output map with all states and corresponding frequencies. Existing frequencies will be erased if any.

Definition at line 380 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

Referenced by bpp::CodonSiteTools::generateCodonSiteWithoutRareVariant(), bpp::SiteContainerTools::getConsensus(), bpp::CodonSiteTools::meanNumberOfSynonymousPositions(), bpp::CodonSiteTools::piNonSynonymous(), bpp::CodonSiteTools::piSynonymous(), and bpp::SiteContainerTools::removeGapSites().

◆ getFrequencies() [2/2]

void SymbolListTools::getFrequencies	(	const CruxSymbolListInterface &	list1,
		const CruxSymbolListInterface &	list2,
		std::map< int, std::map< int, double >> &	frequencies,
		bool	resolveUnknowns = `false`
	)

staticinherited

Get all state pairs frequencies for two lists of the same size.

Author: J. Dutheil

Parameters

list1	The first list.
list2	The second list.
resolveUnknowns	Tell is unknown characters must be resolved. For instance, in DNA, N will be counted as A=1/4,T=1/4,C=1/4,G=1/4. For ProbabilisticSymbolList, (1,1,1,1) states will be counted as (1/4,1/4,1/4,1/4).
frequencies	The output map with all state pairs and corresponding frequencies. Existing frequencies will be erased if any.

Definition at line 396 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ getGCContent() [1/3]

static double bpp::SymbolListTools::getGCContent	(	const CruxSymbolListInterface &	list,
		bool	ignoreUnresolved = `true`,
		bool	ignoreGap = `true`
	)

inlinestaticinherited

Definition at line 609 of file SymbolListTools.h.

References bpp::SymbolListTools::getGCContent().

◆ getGCContent() [2/3]

double SymbolListTools::getGCContent	(	const IntSymbolListInterface &	list,
		bool	ignoreUnresolved = `true`,
		bool	ignoreGap = `true`
	)

staticinherited

Get the GC content of a symbol list.

Parameters

list The list.

Returns: The proportion of G and C states in the list.

Parameters

ignoreUnresolved	Do not count unresolved states (or columns that sum > 1). Otherwise, weight by each state probability in case of ambiguity (e.g. the R state counts for 0.5) (or columns are normalized).
ignoreGap	Do not count gaps (or null columns) in total

Exceptions

AlphabetException If the list is not made of nucleotide states.

Definition at line 415 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), bpp::TemplateCoreSymbolListInterface< T >::getValue(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SymbolListTools::getGCContent().

◆ getGCContent() [3/3]

double SymbolListTools::getGCContent	(	const ProbabilisticSymbolListInterface &	list,
		bool	ignoreUnresolved = `true`,
		bool	ignoreGap = `true`
	)

staticinherited

Definition at line 544 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), bpp::TemplateCoreSymbolListInterface< T >::getValue(), and bpp::CruxSymbolListInterface::size().

◆ getInvert()

unique_ptr< SequenceInterface > SequenceTools::getInvert ( const SequenceInterface & sequence )

static

Inverse a sequence from 5'->3' to 3'->5' and vice-versa.

ABCDEF becomes FEDCBA, and the sense attribute is changed (may be inhibited).

Parameters

sequence The sequence to inverse.

Returns: A new sequence object containing the inverted sequence, of the same type as the input sequence (via the clone method).

Author: Sylvain Gaillard

Definition at line 137 of file SequenceTools.cpp.

References bpp::SequenceInterface::clone().

◆ getMajorAllele()

int SymbolListTools::getMajorAllele ( const CruxSymbolListInterface & list )

staticinherited

return the state corresponding to the most common allele.

Parameters

list A list

Returns: The most frequent state.

Definition at line 817 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ getMajorAlleleFrequency()

size_t SymbolListTools::getMajorAlleleFrequency ( const IntSymbolListInterface & list )

staticinherited

return the number of occurrences of the most common allele.

Parameters

list A list

Returns: The frequency (number of sequences) displaying the most frequent state.

Definition at line 795 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ getMinorAllele()

int SymbolListTools::getMinorAllele ( const CruxSymbolListInterface & list )

staticinherited

return the state corresponding to the least common allele.

Parameters

list A list

Returns: The less frequent state.

Definition at line 866 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ getMinorAlleleFrequency()

size_t SymbolListTools::getMinorAlleleFrequency ( const IntSymbolListInterface & list )

staticinherited

return the number of occurrences of the least common allele.

Parameters

list A list

Returns: The frequency (number of sequences) displaying the less frequent state.

Definition at line 844 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ getNumberOfCompleteSites()

size_t SequenceTools::getNumberOfCompleteSites ( const SequenceInterface & seq )

static

Returns: The number of complete sites in the sequences, i.e. all positions without gaps and unresolved states (generic characters).

Parameters

seq	The sequence to analyse.

Definition at line 234 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::alphabet(), count(), and bpp::CruxSymbolListInterface::size().

◆ getNumberOfDistinctCharacters()

size_t SymbolListTools::getNumberOfDistinctCharacters ( const IntSymbolListInterface & list )

staticinherited

Give the number of distinct characters at a list.

Parameters

list A list

Returns: The number of distinct characters in the given list.

Definition at line 774 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

Referenced by bpp::CodonSiteTools::numberOfSubstitutions().

◆ getNumberOfDistinctPositions() [1/3]

static size_t bpp::SymbolListTools::getNumberOfDistinctPositions	(	const CruxSymbolListInterface &	l1,
		const CruxSymbolListInterface &	l2
	)

inlinestaticinherited

Definition at line 646 of file SymbolListTools.h.

References bpp::SymbolListTools::getNumberOfDistinctPositions().

◆ getNumberOfDistinctPositions() [2/3]

size_t SymbolListTools::getNumberOfDistinctPositions	(	const IntSymbolListInterface &	l1,
		const IntSymbolListInterface &	l2
	)

staticinherited

Get the number of distinct positions.

The comparison in achieved from position 0 to the minimum size of the two vectors.

Parameters

l1	SymbolList 1.
l2	SymbolList 2.

Returns: The number of distinct positions.

Exceptions

AlphabetMismatchException if the two lists have not the same alphabet type.

Definition at line 469 of file SymbolListTools.cpp.

References count(), bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SymbolListTools::getNumberOfDistinctPositions().

◆ getNumberOfDistinctPositions() [3/3]

size_t SymbolListTools::getNumberOfDistinctPositions	(	const ProbabilisticSymbolListInterface &	l1,
		const ProbabilisticSymbolListInterface &	l2
	)

staticinherited

Definition at line 581 of file SymbolListTools.cpp.

References count(), bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

◆ getNumberOfPositionsWithoutGap() [1/3]

static size_t bpp::SymbolListTools::getNumberOfPositionsWithoutGap	(	const CruxSymbolListInterface &	l1,
		const CruxSymbolListInterface &	l2
	)

inlinestaticinherited

Definition at line 682 of file SymbolListTools.h.

References bpp::SymbolListTools::getNumberOfPositionsWithoutGap().

◆ getNumberOfPositionsWithoutGap() [2/3]

size_t SymbolListTools::getNumberOfPositionsWithoutGap	(	const IntSymbolListInterface &	l1,
		const IntSymbolListInterface &	l2
	)

staticinherited

Get the number of positions without gap (or without null column).

The comparison in achieved from position 0 to the minimum size of the two vectors.

Parameters

l1	SymbolList 1.
l2	SymbolList 2.

Returns: The number of positions without gap (or columns with at least a non zero value)

Exceptions

AlphabetMismatchException if the two lists have not the same alphabet type.

Definition at line 485 of file SymbolListTools.cpp.

References count(), bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SymbolListTools::getNumberOfPositionsWithoutGap().

◆ getNumberOfPositionsWithoutGap() [3/3]

size_t SymbolListTools::getNumberOfPositionsWithoutGap	(	const ProbabilisticSymbolListInterface &	l1,
		const ProbabilisticSymbolListInterface &	l2
	)

staticinherited

Definition at line 598 of file SymbolListTools.cpp.

References count(), bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

◆ getNumberOfSites()

size_t SequenceTools::getNumberOfSites ( const SequenceInterface & seq )

static

Returns: The number of sites in the sequences, i.e. all positions without gaps.

Parameters

seq	The sequence to analyse.

Definition at line 220 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::alphabet(), count(), and bpp::CruxSymbolListInterface::size().

◆ getNumberOfUnresolvedSites()

size_t SequenceTools::getNumberOfUnresolvedSites ( const SequenceInterface & seq )

static

Returns: The number of unresolved sites in the sequence.

Parameters

seq	The sequence to analyse.

Author: Sylvain Gaillard

Definition at line 264 of file SequenceTools.cpp.

References count(), bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

◆ getPercentIdentity()

double SequenceTools::getPercentIdentity	(	const SequenceInterface &	seq1,
		const SequenceInterface &	seq2,
		bool	ignoreGaps = `false`
	)

static

Returns: The identity percent of 2 sequence. One match is counted if the two sequences have identical states.

Parameters

seq1	The first sequence.
seq2	The second sequence.
ignoreGaps	If true, only positions without gaps will be used for the counting.

Exceptions

AlphabetMismatchException	If the two sequences do not have the same alphabet.
SequenceNotAlignedException	If the two sequences do not have the same length.

Definition at line 183 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::alphabet(), bpp::CruxSymbolListInterface::getAlphabet(), bpp::Alphabet::getAlphabetType(), bpp::Alphabet::getGapCharacterCode(), bpp::TemplateCoreSymbolListInterface< T >::getValue(), and bpp::CruxSymbolListInterface::size().

◆ getPutativeHaplotypes()

void SequenceTools::getPutativeHaplotypes	(	const SequenceInterface &	seq,
		std::vector< std::unique_ptr< SequenceInterface >> &	hap,
		unsigned int	level = `2`
	)

static

Get all putatives haplotypes from an heterozygous sequence.

Parameters

seq	The sequence to resolve
hap	The vector to fill with the new sequences
level	The maximum number of states that a generic char must code (if this number is higher than level, the state will not be resolved). For instance if level = 3 and Alphabet is DNA, all generic char will be resolved but N.

Author: Sylvain Gaillard

Definition at line 405 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), bpp::CoreSequenceInterface::getName(), bpp::CruxSymbolListInterface::size(), and bpp::TextTools::toString().

◆ getRandomSequence()

unique_ptr< Sequence > SequenceTools::getRandomSequence	(	std::shared_ptr< const Alphabet > &	alphabet,
		size_t	length
	)

static

Get a random sequence of given size and alphabet, with all state with equal probability.

Parameters

alphabet	The alphabet to use.
length	The length of the sequence to generate.

Returns: A pointer toward a new Sequence object.

Definition at line 677 of file SequenceTools.cpp.

References bpp::RandomTools::giveIntRandomNumberBetweenZeroAndEntry().

◆ getSequenceWithCompleteSites()

unique_ptr< SequenceInterface > SequenceTools::getSequenceWithCompleteSites ( const SequenceInterface & seq )

static

keep only complete sites in a sequence.

The deleteElement method of the Sequence object will be used where appropriate.

Parameters

seq	The sequence to analyse.

Definition at line 248 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::alphabet(), bpp::SequenceInterface::clone(), and bpp::CruxSymbolListInterface::size().

◆ getSequenceWithoutGaps()

unique_ptr< SequenceInterface > SequenceTools::getSequenceWithoutGaps ( const SequenceInterface & seq )

static

Get a copy of the sequence without gaps.

A whole new sequence will be created by adding all non-gap positions. The original sequence will be cloned to serve as a template.

Parameters

seq	The sequence to analyse.

Returns: A new sequence object without gaps.

Definition at line 278 of file SequenceTools.cpp.

References bpp::SequenceInterface::clone(), bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

◆ getSequenceWithoutStops()

unique_ptr< SequenceInterface > SequenceTools::getSequenceWithoutStops	(	const SequenceInterface &	seq,
		const GeneticCode &	gCode
	)

static

Get a copy of the codon sequence without stops.

A whole new sequence will be created by adding all non-stop positions. The original sequence will be cloned to serve as a template.

Parameters

seq	The sequence to analyse.
gCode	The genetic code according to which stop codons are specified.

Returns: A new sequence object without stops.

Exceptions

Exception if the input sequence does not have a codon alphabet.

Definition at line 306 of file SequenceTools.cpp.

References bpp::SequenceInterface::clone(), bpp::CruxSymbolListInterface::getAlphabet(), bpp::GeneticCode::isStop(), and bpp::CruxSymbolListInterface::size().

◆ hasGap() [1/3]

static bool bpp::SymbolListTools::hasGap ( const CruxSymbolListInterface & site )

inlinestaticinherited

Definition at line 36 of file SymbolListTools.h.

References bpp::SymbolListTools::hasGap().

◆ hasGap() [2/3]

bool SymbolListTools::hasGap ( const IntSymbolListInterface & site )

staticinherited

Parameters

site A site.

Returns: True if the site contains one or several gap(s).

Definition at line 22 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SiteContainerTools::changeGapsToUnknownCharacters(), bpp::SiteContainerTools::getSitesWithoutGaps(), bpp::SymbolListTools::hasGap(), bpp::NoGapTemplateSiteContainerIterator< SiteType, SequenceType, HashType >::nextSiteWithoutGapPosition(), bpp::CodonSiteTools::numberOfNonSynonymousSubstitutions(), bpp::CodonSiteTools::numberOfSubstitutions(), and bpp::NoGapTemplateSiteContainerIterator< SiteType, SequenceType, HashType >::previousSiteWithoutGapPosition().

◆ hasGap() [3/3]

bool SymbolListTools::hasGap ( const ProbabilisticSymbolListInterface & site )

staticinherited

Definition at line 33 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ hasSingleton()

bool SymbolListTools::hasSingleton ( const IntSymbolListInterface & list )

staticinherited

Tell if a list has singletons.

Parameters

list A list.

Returns: True if the list has singletons.

Definition at line 892 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ hasUnknown() [1/3]

static bool bpp::SymbolListTools::hasUnknown ( const CruxSymbolListInterface & site )

inlinestaticinherited

Definition at line 152 of file SymbolListTools.h.

References bpp::SymbolListTools::hasUnknown().

◆ hasUnknown() [2/3]

bool SymbolListTools::hasUnknown ( const IntSymbolListInterface & site )

staticinherited

Parameters

site A site.

Returns: True if the site contains one or several unknown characters.

Definition at line 109 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SymbolListTools::hasUnknown().

◆ hasUnknown() [3/3]

bool SymbolListTools::hasUnknown ( const ProbabilisticSymbolListInterface & site )

staticinherited

Definition at line 120 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ hasUnresolved()

bool SymbolListTools::hasUnresolved ( const IntSymbolListInterface & site )

staticinherited

Parameters

site A site.

Returns: True if the site contains one or several unresolved state.

Definition at line 46 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

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

◆ heterozygosity()

double SymbolListTools::heterozygosity ( const CruxSymbolListInterface & list )

staticinherited

Compute the heterozygosity index of a list.

$H = 1 - \sum_x f_x^2$

where is the frequency of state .

Parameters

list A list.

Returns: The heterozygosity index of this list.

Definition at line 760 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ invert()

void SequenceTools::invert ( SequenceInterface & seq )

static

Inverse a sequence from 5'->3' to 3'->5' and vice-versa.

ABCDEF becomes FEDCBA, and the sense attribute is changed (may be inhibited).

Parameters

seq	The sequence to inverse.

Author: Sylvain Gaillard

Definition at line 121 of file SequenceTools.cpp.

References bpp::TemplateCoreSymbolListInterface< T >::getValue(), bpp::IntSymbolListInterface::setElement(), and bpp::CruxSymbolListInterface::size().

◆ invertComplement()

void SequenceTools::invertComplement ( SequenceInterface & seq )

static

Inverse and complement a sequence.

This method is more accurate than calling invert and complement separately.

Parameters

seq	The sequence to inverse and complement.

Author: Sylvain Gaillard

Definition at line 146 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::alphabet(), bpp::CruxSymbolListInterface::getAlphabet(), bpp::TemplateCoreSymbolListInterface< T >::getValue(), bpp::AlphabetTools::isDNAAlphabet(), bpp::AlphabetTools::isRNAAlphabet(), bpp::IntSymbolListInterface::setElement(), bpp::CruxSymbolListInterface::size(), and bpp::NucleicAcidsReplication::translate().

◆ isComplete() [1/3]

static bool bpp::SymbolListTools::isComplete ( const CruxSymbolListInterface & site )

inlinestaticinherited

Definition at line 174 of file SymbolListTools.h.

References bpp::SymbolListTools::isComplete().

◆ isComplete() [2/3]

bool SymbolListTools::isComplete ( const IntSymbolListInterface & site )

staticinherited

Parameters

site A site.

Returns: True if the site contains no gap and no unknown characters.

Definition at line 134 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SiteContainerTools::getCompleteSites(), bpp::SymbolListTools::isComplete(), bpp::CompleteTemplateSiteContainerIterator< SiteType, SequenceType, HashType >::nextCompleteSitePosition(), and bpp::CompleteTemplateSiteContainerIterator< SiteType, SequenceType, HashType >::previousCompleteSitePosition().

◆ isComplete() [3/3]

bool SymbolListTools::isComplete ( const ProbabilisticSymbolListInterface & site )

staticinherited

Definition at line 145 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ isConstant() [1/3]

static bool bpp::SymbolListTools::isConstant	(	const CruxSymbolListInterface &	site,
		bool	ignoreUnknown = `false`,
		bool	unresolvedRaisesException = `true`
	)

inlinestaticinherited

Definition at line 208 of file SymbolListTools.h.

References bpp::SymbolListTools::isConstant().

◆ isConstant() [2/3]

bool SymbolListTools::isConstant	(	const IntSymbolListInterface &	site,
		bool	ignoreUnknown = `false`,
		bool	unresolvedRaisesException = `true`
	)

staticinherited

Tell if a site is constant, that is displaying the same state in all sequences that do not present a gap.

Parameters

site	A site.
ignoreUnknown	If true, positions with unknown positions will be ignored. Otherwise, a site with one single state + any uncertain state will not be considered as constant.
unresolvedRaisesException	In case of ambiguous case (gap only site for instance), throw an exception. Otherwise returns false.

Returns: True if the site is made of only one state.

Definition at line 258 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::CodonSiteTools::fixedDifferences(), bpp::CodonSiteTools::generateCodonSiteWithoutRareVariant(), bpp::SymbolListTools::isConstant(), bpp::CodonSiteTools::isFourFoldDegenerated(), bpp::CodonSiteTools::isMonoSitePolymorphic(), bpp::CodonSiteTools::isSynonymousPolymorphic(), bpp::CodonSiteTools::numberOfNonSynonymousSubstitutions(), bpp::CodonSiteTools::numberOfSubstitutions(), bpp::CodonSiteTools::piNonSynonymous(), and bpp::CodonSiteTools::piSynonymous().

◆ isConstant() [3/3]

bool SymbolListTools::isConstant	(	const ProbabilisticSymbolListInterface &	site,
		bool	unresolvedRaisesException = `true`
	)

staticinherited

Definition at line 320 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ isDoubleton()

bool SymbolListTools::isDoubleton ( const IntSymbolListInterface & list )

staticinherited

Tell if a list has exactly 2 distinct characters.

Parameters

list A list.

Returns: True if the site has exactly 2 distinct characters

Definition at line 946 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ isGapOnly() [1/3]

static bool bpp::SymbolListTools::isGapOnly ( const CruxSymbolListInterface & site )

inlinestaticinherited

Definition at line 64 of file SymbolListTools.h.

References bpp::SymbolListTools::isGapOnly().

◆ isGapOnly() [2/3]

bool SymbolListTools::isGapOnly ( const IntSymbolListInterface & site )

staticinherited

Parameters

site A site.

Returns: True if the site contains only gaps.

Definition at line 59 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SymbolListTools::isGapOnly(), bpp::SiteContainerTools::removeGapOnlySites(), and bpp::SiteContainerTools::removeGapOrUnresolvedOnlySites().

◆ isGapOnly() [3/3]

bool SymbolListTools::isGapOnly ( const ProbabilisticSymbolListInterface & site )

staticinherited

Definition at line 71 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ isGapOrUnresolvedOnly() [1/3]

static bool bpp::SymbolListTools::isGapOrUnresolvedOnly ( const CruxSymbolListInterface & site )

inlinestaticinherited

Definition at line 108 of file SymbolListTools.h.

References bpp::SymbolListTools::isGapOrUnresolvedOnly().

◆ isGapOrUnresolvedOnly() [2/3]

bool SymbolListTools::isGapOrUnresolvedOnly ( const IntSymbolListInterface & site )

staticinherited

Parameters

site A site.

Returns: True if the site contains only gaps.

Definition at line 84 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SymbolListTools::isGapOrUnresolvedOnly(), and bpp::SiteContainerTools::removeGapOrUnresolvedOnlySites().

◆ isGapOrUnresolvedOnly() [3/3]

bool SymbolListTools::isGapOrUnresolvedOnly ( const ProbabilisticSymbolListInterface & site )

staticinherited

Definition at line 95 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ isParsimonyInformativeSite()

bool SymbolListTools::isParsimonyInformativeSite ( const IntSymbolListInterface & site )

staticinherited

Tell if a site is a parsimony informative site.

At least two distinct characters must be present.

Parameters

site a Site.

Returns: True if the site is parsimony informative.

Definition at line 912 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ isTriplet()

bool SymbolListTools::isTriplet ( const IntSymbolListInterface & list )

staticinherited

Tell if a list has more than 2 distinct characters.

Parameters

list A list.

Returns: True if the list has more than 2 distinct characters

Definition at line 935 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ jointEntropy()

double SymbolListTools::jointEntropy	(	const CruxSymbolListInterface &	list1,
		const CruxSymbolListInterface &	list2,
		bool	resolveUnknowns
	)

staticinherited

Compute the joint entropy between two lists.

$H_{i,j} = - \sum_x \sum_y p_{x,y}\ln\left(p_{x,y}\right)$

where $p_{x,y}$ is the frequency of the pair .

Author: J. Dutheil

Parameters

list1	First list
list2	Second list
resolveUnknowns	Tell is unknown characters must be resolved.

Returns: The mutual information for the pair of lists.

Definition at line 706 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

◆ mutualInformation()

double SymbolListTools::mutualInformation	(	const CruxSymbolListInterface &	list1,
		const CruxSymbolListInterface &	list2,
		bool	resolveUnknowns
	)

staticinherited

Compute the mutual information between two lists.

$MI = \sum_x \sum_y p_{x,y}\ln\left(\frac{p_{x,y}}{p_x \cdot p_y}\right)$

where and are the frequencies of states and , and $p_{x,y}$ is the frequency of the pair .

Author: J. Dutheil

Parameters

list1	First list
list2	Second list
resolveUnknowns	Tell is unknown characters must be resolved.

Returns: The mutual information for the pair of lists.

Definition at line 656 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

◆ numberOfGaps() [1/3]

static size_t bpp::SymbolListTools::numberOfGaps ( const CruxSymbolListInterface & site )

inlinestaticinherited

Definition at line 86 of file SymbolListTools.h.

References bpp::SymbolListTools::numberOfGaps().

◆ numberOfGaps() [2/3]

size_t SymbolListTools::numberOfGaps ( const IntSymbolListInterface & site )

staticinherited

Parameters

site A site.

Returns: the numbed of gaps.

Definition at line 159 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SequenceApplicationTools::getSitesToAnalyse(), and bpp::SymbolListTools::numberOfGaps().

◆ numberOfGaps() [3/3]

size_t SymbolListTools::numberOfGaps ( const ProbabilisticSymbolListInterface & site )

staticinherited

Definition at line 172 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ numberOfUnresolved() [1/3]

static size_t bpp::SymbolListTools::numberOfUnresolved ( const CruxSymbolListInterface & site )

inlinestaticinherited

Definition at line 130 of file SymbolListTools.h.

References bpp::SymbolListTools::numberOfUnresolved().

◆ numberOfUnresolved() [2/3]

size_t SymbolListTools::numberOfUnresolved ( const IntSymbolListInterface & site )

staticinherited

Parameters

site A site.

Returns: the numbed of unresolved.

Definition at line 187 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SequenceApplicationTools::getSitesToAnalyse(), and bpp::SymbolListTools::numberOfUnresolved().

◆ numberOfUnresolved() [3/3]

size_t SymbolListTools::numberOfUnresolved ( const ProbabilisticSymbolListInterface & site )

staticinherited

Definition at line 200 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ removeGaps()

void SequenceTools::removeGaps ( SequenceInterface & seq )

static

Remove gaps from a sequence.

The deleteElement method of the Sequence object will be used where appropriate.

Parameters

seq	The sequence to analyse.

Definition at line 294 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::deleteElement(), bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

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

◆ removeStops()

void SequenceTools::removeStops	(	SequenceInterface &	seq,
		const GeneticCode &	gCode
	)

static

Remove stops from a codon sequence.

The deleteElement method of the Sequence object will be used where appropriate.

Parameters

seq	The sequence to analyse.
gCode	The genetic code according to which stop codons are specified.

Exceptions

Exception if the input sequence does not have a codon alphabet.

Definition at line 324 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::deleteElement(), bpp::CruxSymbolListInterface::getAlphabet(), bpp::GeneticCode::isStop(), and bpp::CruxSymbolListInterface::size().

◆ replaceStopsWithGaps()

void SequenceTools::replaceStopsWithGaps	(	SequenceInterface &	seq,
		const GeneticCode &	gCode
	)

static

Replace stop codons by gaps.

The setElement method of the Sequence object will be used where appropriate.

Parameters

seq	The sequence to analyse.
gCode	The genetic code according to which stop codons are specified.

Exceptions

Exception if the input sequence does not have a codon alphabet.

Definition at line 338 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), bpp::GeneticCode::isStop(), bpp::IntSymbolListInterface::setElement(), and bpp::CruxSymbolListInterface::size().

◆ reverseTranscript()

unique_ptr< Sequence > SequenceTools::reverseTranscript ( const Sequence & sequence )

static

Get the reverse-transcription sequence of a RNA sequence.

Translate RNA sequence into DNA sequence.

See also: DNAReplication

Returns: sequence A new sequence object with the reverse-transcription sequence.

Parameters

sequence The sequence to reverse-transcript.

Exceptions

AlphabetException If the sequence is not a RNA sequence.

Definition at line 108 of file SequenceTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::alphabet(), bpp::AbstractTemplateSymbolList< T >::getAlphabet(), and bpp::AlphabetTools::isRNAAlphabet().

◆ RNYslice() [1/2]

unique_ptr< Sequence > SequenceTools::RNYslice ( const SequenceInterface & sequence )

static

Get the RNY decomposition of a DNA sequence.

This function gives the alternative succession in phases 1, 2 and 3.

Returns: sequence A new sequence object with the transcription sequence.

Parameters

sequence The sequence to transcript.

Exceptions

AlphabetException If the sequence is not a DNA sequence.

Author: Laurent Guéguen

Definition at line 569 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::alphabet(), bpp::CruxSymbolListInterface::getAlphabet(), bpp::Commentable::getComments(), bpp::CoreSequenceInterface::getName(), bpp::AlphabetTools::isDNAAlphabet(), and bpp::CruxSymbolListInterface::size().

◆ RNYslice() [2/2]

unique_ptr< Sequence > SequenceTools::RNYslice	(	const SequenceInterface &	sequence,
		int	ph
	)

static

Get the RNY decomposition of a DNA sequence.

This function gives the decomposition in the given phase. In phase 1, the first triplet is centered on the first character.

Returns: sequence A new sequence object with the transcription sequence.

Parameters

sequence	The sequence to transcript.
ph	The phase to use (1,2 or 3).

Exceptions

AlphabetException If the sequence is not a DNA sequence.

Author: Laurent Guéguen

Definition at line 527 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::alphabet(), bpp::CruxSymbolListInterface::getAlphabet(), bpp::Commentable::getComments(), bpp::CoreSequenceInterface::getName(), bpp::AlphabetTools::isDNAAlphabet(), bpp::CruxSymbolListInterface::size(), and bpp::TextTools::toString().

Referenced by bpp::SequenceApplicationTools::getProbabilisticSiteContainer(), and bpp::SequenceApplicationTools::getSiteContainer().

◆ subseq() [1/2]

template<class SequenceTypeOut >

static std::unique_ptr<SequenceTypeOut> bpp::SequenceTools::subseq	(	const SequenceInterface &	sequence,
		size_t	begin,
		size_t	end
	)

inlinestatic

Get a sub-sequence.

Parameters

sequence	The sequence to trunc.
begin	The first position of the subsequence.
end	The last position of the subsequence.

Returns: A new sequence object with the given subsequence.

Definition at line 112 of file SequenceTools.h.

References bpp::CruxSymbolListInterface::getAlphabet(), bpp::Commentable::getComments(), bpp::CoreSequenceInterface::getName(), and subseq().

◆ subseq() [2/2]

static void bpp::SequenceTools::subseq	(	const SequenceInterface &	sequence,
		size_t	begin,
		size_t	end,
		SequenceInterface &	output
	)

inlinestatic

Get a sub-sequence.

Parameters

sequence	The sequence to trunc.
begin	The first position of the subsequence.
end	The last position of the subsequence (included).
output	A sequence object to be appended with the given subsequence.

Definition at line 91 of file SequenceTools.h.

References bpp::SequenceInterface::append(), bpp::CruxSymbolListInterface::size(), and bpp::TextTools::toString().

Referenced by subseq().

◆ subtractHaplotype()

unique_ptr< Sequence > SequenceTools::subtractHaplotype	(	const SequenceInterface &	s,
		const SequenceInterface &	h,
		std::string	name = `""`,
		unsigned int	level = `1`
	)

static

Subtract haplotype from an heterozygous sequence.

Subtract an haplotype (i.e. a fully resolved sequence) from an heterozygous sequence to get the other haplotype. The new haplotype could be an unresolved sequence if unresolved characters in the sequence code for more than 2 states.

For example:

>heterozygous sequence
ATTCGGGKWTATRYRM
>haplotype
ATTCGGGTATATGCAA
>subtracted haplotype
ATTCGGGGTTATATGC

Parameters

s	The heterozygous sequence.
h	The haplotype to subtract.
name	The name of the new computed haplotype.
level	The number of states from which the site is set to fully unresolved.

Exceptions

SequenceNotAlignedException if s and h don't have the same size.

Author: Sylvain Gaillard

Definition at line 489 of file SequenceTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), bpp::CoreSequenceInterface::getName(), bpp::TemplateCoreSymbolListInterface< T >::getValue(), and bpp::CruxSymbolListInterface::size().

◆ transcript()

unique_ptr< Sequence > SequenceTools::transcript ( const Sequence & sequence )

static

Get the transcription sequence of a DNA sequence.

Translate DNA sequence into RNA sequence.

See also: DNAReplication

Returns: sequence A new sequence object with the transcription sequence.

Parameters

sequence The sequence to transcript.

Exceptions

AlphabetException If the sequence is not a DNA sequence.

Definition at line 95 of file SequenceTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::alphabet(), bpp::AbstractTemplateSymbolList< T >::getAlphabet(), and bpp::AlphabetTools::isDNAAlphabet().

◆ variabilityFactorial()

double SymbolListTools::variabilityFactorial ( const IntSymbolListInterface & list )

staticinherited

Compute the factorial diversity index of a site.

$F = \frac{log\left(\left(\sum_x p_x\right)!\right)}{\sum_x \log(p_x)!}$

where is the number of times state is observed in the site.

Author: J. Dutheil

Parameters

list A list.

Returns: The factorial diversity index of this list.

Definition at line 744 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ variabilityShannon()

double SymbolListTools::variabilityShannon	(	const CruxSymbolListInterface &	list,
		bool	resolveUnknowns
	)

staticinherited

Compute the Shannon entropy index of a SymbolList.

$I = - \sum_x f_x\cdot \ln(f_x)$

where is the frequency of state .

Author: J. Dutheil

Parameters

list	A list.
resolveUnknowns	Tell is unknown characters must be resolved.

Returns: The Shannon entropy index of this list.

Definition at line 632 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::getAlphabet(), and bpp::CruxSymbolListInterface::size().

Referenced by bpp::SymbolListTools::entropy().

Member Data Documentation

◆ DNARep_

NucleicAcidsReplication SequenceTools::DNARep_

staticprivate

Definition at line 67 of file SequenceTools.h.

◆ RNARep_

NucleicAcidsReplication SequenceTools::RNARep_

staticprivate

Definition at line 68 of file SequenceTools.h.

◆ RNY_

shared_ptr< RNY > SequenceTools::RNY_

staticprivate

Definition at line 66 of file SequenceTools.h.

◆ transc_

NucleicAcidsReplication SequenceTools::transc_

staticprivate

Definition at line 69 of file SequenceTools.h.

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

Bpp/Seq/SequenceTools.h
Bpp/Seq/SequenceTools.cpp

Public Member Functions

Static Public Member Functions

Static Private Attributes

Detailed Description

Constructor & Destructor Documentation

◆ SequenceTools()

◆ ~SequenceTools()

Member Function Documentation

◆ areSequencesIdentical()

◆ areSymbolListsIdentical() [1/3]

◆ areSymbolListsIdentical() [2/3]

◆ areSymbolListsIdentical() [3/3]

◆ bowkerTest()

◆ changeGapsToUnknownCharacters() [1/3]

◆ changeGapsToUnknownCharacters() [2/3]

◆ changeGapsToUnknownCharacters() [3/3]

◆ changeUnresolvedCharactersToGaps() [1/3]

◆ changeUnresolvedCharactersToGaps() [2/3]

◆ changeUnresolvedCharactersToGaps() [3/3]

◆ combineSequences()

◆ complement()

◆ concatenate()

◆ entropy()

◆ findFirstOf()

◆ getCDS()

◆ getComplement()

◆ getCounts() [1/6]

◆ getCounts() [2/6]

◆ getCounts() [3/6]

◆ getCounts() [4/6]

◆ getCounts() [5/6]

◆ getCounts() [6/6]

◆ getCountsResolveUnknowns() [1/4]

◆ getCountsResolveUnknowns() [2/4]

◆ getCountsResolveUnknowns() [3/4]

◆ getCountsResolveUnknowns() [4/4]

◆ getFrequencies() [1/2]

◆ getFrequencies() [2/2]

◆ getGCContent() [1/3]

◆ getGCContent() [2/3]

◆ getGCContent() [3/3]

◆ getInvert()

◆ getMajorAllele()

◆ getMajorAlleleFrequency()

◆ getMinorAllele()

◆ getMinorAlleleFrequency()

◆ getNumberOfCompleteSites()

◆ getNumberOfDistinctCharacters()

◆ getNumberOfDistinctPositions() [1/3]

◆ getNumberOfDistinctPositions() [2/3]

◆ getNumberOfDistinctPositions() [3/3]

◆ getNumberOfPositionsWithoutGap() [1/3]

◆ getNumberOfPositionsWithoutGap() [2/3]

◆ getNumberOfPositionsWithoutGap() [3/3]

◆ getNumberOfSites()

◆ getNumberOfUnresolvedSites()

◆ getPercentIdentity()

◆ getPutativeHaplotypes()

◆ getRandomSequence()

◆ getSequenceWithCompleteSites()

◆ getSequenceWithoutGaps()

◆ getSequenceWithoutStops()

◆ hasGap() [1/3]

◆ hasGap() [2/3]

◆ hasGap() [3/3]

◆ hasSingleton()

◆ hasUnknown() [1/3]

◆ hasUnknown() [2/3]

◆ hasUnknown() [3/3]

◆ hasUnresolved()

◆ heterozygosity()

◆ invert()

◆ invertComplement()

◆ isComplete() [1/3]

◆ isComplete() [2/3]

◆ isComplete() [3/3]

◆ isConstant() [1/3]

◆ isConstant() [2/3]

◆ isConstant() [3/3]

◆ isDoubleton()