Utilitary functions for codon sites. More...

#include <Bpp/Seq/CodonSiteTools.h>

Inheritance diagram for bpp::CodonSiteTools:

Collaboration diagram for bpp::CodonSiteTools:

Public Member Functions
	CodonSiteTools ()

virtual	~CodonSiteTools ()

Static Public Member Functions
static bool	hasGapOrStop (const Site &site, const GeneticCode &gCode)
	Method to know if a codon site contains gap(s) or stop codons. More...

static bool	hasStop (const Site &site, const GeneticCode &gCode)
	Method to know if a codon site contains stop codon or not. More...

static bool	isMonoSitePolymorphic (const Site &site)
	Method to know if a polymorphic codon site is polymorphic at only one site. More...

static bool	isSynonymousPolymorphic (const Site &site, const GeneticCode &gCode)
	Method to know if polymorphism at a codon site is synonymous. More...

static std::unique_ptr< Site >	generateCodonSiteWithoutRareVariant (const Site &site, const GeneticCode &gCode, double freqmin)
	generate a codon site without rare variants More...

static size_t	numberOfDifferences (int i, int j, const CodonAlphabet &ca)
	Compute the number of differences between two codons. More...

static double	numberOfSynonymousDifferences (int i, int j, const GeneticCode &gCode, bool minchange=false)
	Compute the number of synonymous differences between two codons. More...

static double	piSynonymous (const Site &site, const GeneticCode &gCode, bool minchange=false)
	Compute the synonymous pi per codon site. More...

static double	piNonSynonymous (const Site &site, const GeneticCode &gCode, bool minchange=false)
	Compute the non-synonymous pi per codon site. More...

static double	numberOfSynonymousPositions (int i, const GeneticCode &gCode, double ratio=1.0)
	Return the number of synonymous positions of a codon. More...

static double	meanNumberOfSynonymousPositions (const Site &site, const GeneticCode &gCode, double ratio=1)
	Return the mean number of synonymous positions per codon site. More...

static size_t	numberOfSubstitutions (const Site &site, const GeneticCode &gCode, double freqmin=0.)
	Return the number of substitutions per codon site. More...

static size_t	numberOfNonSynonymousSubstitutions (const Site &site, const GeneticCode &gCode, double freqmin=0.)
	Return the number of Non Synonymous substitutions per codon site. More...

static std::vector< size_t >	fixedDifferences (const Site &siteIn, const Site &siteOut, int i, int j, const GeneticCode &gCode)
	Return a vector with the number of fixed synonymous and non-synonymous differences per codon site. More...

static bool	isFourFoldDegenerated (const Site &site, const GeneticCode &gCode)

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...

Detailed Description

Utilitary functions for codon sites.

Definition at line 24 of file CodonSiteTools.h.

Constructor & Destructor Documentation

◆ CodonSiteTools()

bpp::CodonSiteTools::CodonSiteTools ( )

inline

Definition at line 28 of file CodonSiteTools.h.

◆ ~CodonSiteTools()

virtual bpp::CodonSiteTools::~CodonSiteTools ( )

inlinevirtual

Definition at line 29 of file CodonSiteTools.h.

Member Function Documentation

◆ 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().

◆ 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().

◆ 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().

◆ fixedDifferences()

vector< size_t > CodonSiteTools::fixedDifferences	(	const Site &	siteIn,
		const Site &	siteOut,
		int	i,
		int	j,
		const GeneticCode &	gCode
	)

static

Return a vector with the number of fixed synonymous and non-synonymous differences per codon site.

Compute the number of synonymous and non-synonymous differences between the consensus codon of SiteIn (i) and SiteOut (j), which are fixed within each alignment. Example:

SiteIn
 ATT
 ATT
 ATC

SiteOut
 CTA
 CTA
 CTA

Here, the first position is non-synonymous different and fixed, the third position is synonymous different but not fixed (polymorphic in SiteIn). The return vector is thus [0,1]. In case of complex codon, the path that gives the minimum number of non-synonymous changes is chosen. The argument minchange=true is sent to numberOfSynonymousDifferences used in this method. Otherwise, a non-integer number could be return.

Rare variants (<= freqmin) can be excluded.

Parameters

siteIn	a Site
siteOut	a Site
i	an integer
j	an integer
gCode	a GeneticCode

Definition at line 661 of file CodonSiteTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::alphabet(), bpp::Alphabet::equals(), bpp::AbstractTemplateSymbolList< T >::getAlphabet(), bpp::GeneticCode::getCodonAlphabet(), bpp::AlphabetTools::isCodonAlphabet(), bpp::SymbolListTools::isConstant(), bpp::AbstractTemplateSymbolList< T >::size(), and bpp::GeneticCode::sourceAlphabet().

◆ generateCodonSiteWithoutRareVariant()

unique_ptr< Site > CodonSiteTools::generateCodonSiteWithoutRareVariant	(	const Site &	site,
		const GeneticCode &	gCode,
		double	freqmin
	)

static

generate a codon site without rare variants

Rare variants are replaced by the most frequent allele. This method is used to exclude rare variants in some analyses as in McDonald-Kreitman Test (McDonald & Kreitman, 1991, Nature 351 pp652-654). For an application, see for example (Fay et al. 2001, Genetics 158 pp 1227-1234).

Parameters

site	a Site
gCode	The genetic code according to which stop codons are specified.
freqmin	a double, allele in frequency strictly lower than freqmin are replaced

Definition at line 129 of file CodonSiteTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::alphabet(), bpp::AbstractTemplateSymbolList< T >::getAlphabet(), bpp::SymbolListTools::getFrequencies(), bpp::AbstractTemplateSymbolList< T >::getValue(), bpp::AlphabetTools::isCodonAlphabet(), bpp::SymbolListTools::isConstant(), bpp::GeneticCode::isStop(), and bpp::AbstractTemplateSymbolList< T >::size().

Referenced by numberOfSubstitutions().

◆ 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(), isSynonymousPolymorphic(), and 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 generateCodonSiteWithoutRareVariant(), bpp::SiteContainerTools::getConsensus(), meanNumberOfSynonymousPositions(), piNonSynonymous(), 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().

◆ 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().

◆ 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 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().

◆ 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(), numberOfNonSynonymousSubstitutions(), 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().

◆ hasGapOrStop()

bool CodonSiteTools::hasGapOrStop	(	const Site &	site,
		const GeneticCode &	gCode
	)

static

Method to know if a codon site contains gap(s) or stop codons.

Parameters

site	a Site
gCode	The genetic code according to which stop codons are specified.

Definition at line 26 of file CodonSiteTools.cpp.

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

◆ hasStop()

bool CodonSiteTools::hasStop	(	const Site &	site,
		const GeneticCode &	gCode
	)

static

Method to know if a codon site contains stop codon or not.

Parameters

site	a Site
gCode	The genetic code according to which stop codons are specified.

Definition at line 41 of file CodonSiteTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::alphabet(), bpp::AbstractTemplateSymbolList< T >::getAlphabet(), bpp::AlphabetTools::isCodonAlphabet(), bpp::GeneticCode::isStop(), and bpp::AbstractTemplateSymbolList< T >::size().

Referenced by bpp::SiteContainerTools::getSitesWithoutStopCodon(), and bpp::SiteContainerTools::removeSitesWithStopCodon().

◆ 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().

◆ 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 fixedDifferences(), generateCodonSiteWithoutRareVariant(), bpp::SymbolListTools::isConstant(), isFourFoldDegenerated(), isMonoSitePolymorphic(), isSynonymousPolymorphic(), numberOfNonSynonymousSubstitutions(), numberOfSubstitutions(), piNonSynonymous(), and 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().

◆ isFourFoldDegenerated()

bool CodonSiteTools::isFourFoldDegenerated	(	const Site &	site,
		const GeneticCode &	gCode
	)

static

Returns: True if all sequences have a fourfold degenerated codon in the site (that is, if a mutation in the fourth position does not change the aminoacid).

Author: Benoit Nabholz, Annabelle Haudry

Parameters

site	The site to analyze.
gCode	The genetic code to use.

If non-synonymous mutation

Definition at line 792 of file CodonSiteTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::getValue(), bpp::SymbolListTools::isConstant(), bpp::GeneticCode::isFourFoldDegenerated(), isSynonymousPolymorphic(), and bpp::AbstractTemplateSymbolList< T >::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().

◆ isMonoSitePolymorphic()

bool CodonSiteTools::isMonoSitePolymorphic ( const Site & site )

static

Method to know if a polymorphic codon site is polymorphic at only one site.

Parameters

site a Site

Definition at line 56 of file CodonSiteTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::alphabet(), bpp::AbstractTemplateSymbolList< T >::getAlphabet(), bpp::AlphabetTools::isCodonAlphabet(), bpp::SymbolListTools::isConstant(), and bpp::AbstractTemplateSymbolList< T >::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().

◆ isSynonymousPolymorphic()

bool CodonSiteTools::isSynonymousPolymorphic	(	const Site &	site,
		const GeneticCode &	gCode
	)

static

Method to know if polymorphism at a codon site is synonymous.

Parameters

site	a Site
gCode	a GeneticCode

Definition at line 94 of file CodonSiteTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::alphabet(), bpp::Alphabet::equals(), bpp::AbstractTemplateSymbolList< T >::getAlphabet(), bpp::SymbolListTools::getCounts(), bpp::GeneticCode::getSourceAlphabet(), bpp::AlphabetTools::isCodonAlphabet(), bpp::SymbolListTools::isConstant(), bpp::AbstractTemplateSymbolList< T >::size(), bpp::GeneticCode::sourceAlphabet(), and bpp::GeneticCode::translate().

Referenced by isFourFoldDegenerated().

◆ 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().

◆ meanNumberOfSynonymousPositions()

double CodonSiteTools::meanNumberOfSynonymousPositions	(	const Site &	site,
		const GeneticCode &	gCode,
		double	ratio = `1`
	)

static

Return the mean number of synonymous positions per codon site.

A site is consider as x% synonymous if x% of the possible mutations are synonymous Transition/transversion ratio can be taken into account (use the variable ratio) The mean is computed over the VectorSite.

Unresolved and stop codons are counted as 0.

Parameters

site	a Site
gCode	a GeneticCode
ratio	a double, set by default to 1

Definition at line 537 of file CodonSiteTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::alphabet(), bpp::Alphabet::equals(), bpp::AbstractTemplateSymbolList< T >::getAlphabet(), bpp::GeneticCode::getCodonAlphabet(), bpp::SymbolListTools::getFrequencies(), bpp::AlphabetTools::isCodonAlphabet(), bpp::AbstractTemplateSymbolList< T >::size(), and bpp::GeneticCode::sourceAlphabet().

◆ 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().

◆ numberOfDifferences()

size_t CodonSiteTools::numberOfDifferences	(	int	i,
		int	j,
		const CodonAlphabet &	ca
	)

static

Compute the number of differences between two codons.

Parameters

i	a int
j	a int
ca	a CodonAlphabet

Definition at line 191 of file CodonSiteTools.cpp.

References bpp::CodonAlphabet::getFirstPosition(), bpp::CodonAlphabet::getSecondPosition(), and bpp::CodonAlphabet::getThirdPosition().

◆ 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().

◆ numberOfNonSynonymousSubstitutions()

size_t CodonSiteTools::numberOfNonSynonymousSubstitutions	(	const Site &	site,
		const GeneticCode &	gCode,
		double	freqmin = `0.`
	)

static

Return the number of Non Synonymous substitutions per codon site.

It is assumed that the path linking amino acids only involved one substitution by step.

Rare variants (<= freqmin) can be excluded. In case of complex codon, the path that gives the minimum number of non-synonymous changes is chosen. The argument minchange=true is sent to numberOfSynonymousDifferences used in this method. Otherwise, a non-integer number could be return.

Parameters

site	a Site
gCode	a GeneticCode
freqmin	a double To exclude snp in frequency strictly lower than freqmin (by default freqmin = 0).

Definition at line 614 of file CodonSiteTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::alphabet(), count(), bpp::Alphabet::equals(), bpp::AbstractTemplateSymbolList< T >::getAlphabet(), bpp::GeneticCode::getCodonAlphabet(), bpp::SymbolListTools::getCounts(), bpp::SymbolListTools::hasGap(), bpp::AlphabetTools::isCodonAlphabet(), bpp::SymbolListTools::isConstant(), bpp::AbstractTemplateSymbolList< T >::size(), and bpp::GeneticCode::sourceAlphabet().

◆ numberOfSubstitutions()

size_t CodonSiteTools::numberOfSubstitutions	(	const Site &	site,
		const GeneticCode &	gCode,
		double	freqmin = `0.`
	)

static

Return the number of substitutions per codon site.

No recombination is assumed, that is in complex codon homoplasy is assumed. Example:

ATT
ATT
ATT
ATC
ATC
AGT
AGT
AGC

Here, 3 substitutions are counted. Assuming that the last codon (AGC) is a recombinant between ATC and AGT would have lead to counting only 2 substitutions.

Rare variants (<= freqmin) can be excluded.

Parameters

site	a Site
gCode	a GeneticCode
freqmin	a double To exclude snp in frequency strictly lower than freqmin (by default freqmin = 0)

Definition at line 571 of file CodonSiteTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::alphabet(), generateCodonSiteWithoutRareVariant(), bpp::AbstractTemplateSymbolList< T >::getAlphabet(), bpp::SymbolListTools::getNumberOfDistinctCharacters(), bpp::SymbolListTools::hasGap(), bpp::AlphabetTools::isCodonAlphabet(), bpp::SymbolListTools::isConstant(), and bpp::AbstractTemplateSymbolList< T >::size().

◆ numberOfSynonymousDifferences()

double CodonSiteTools::numberOfSynonymousDifferences	(	int	i,
		int	j,
		const GeneticCode &	gCode,
		bool	minchange = `false`
	)

static

Compute the number of synonymous differences between two codons.

For complex codon: If minchange = false (default option) the different paths are equally weighted. If minchange = true the path with the minimum number of non-synonymous change is chosen. Paths included stop codons are excluded.

Parameters

i	a int
j	a int
gCode	a GeneticCode
minchange	a boolean set by default to false

Definition at line 205 of file CodonSiteTools.cpp.

References bpp::GeneticCode::areSynonymous(), bpp::GeneticCode::getCodonAlphabet(), bpp::GeneticCode::isStop(), bpp::VectorTools::max(), and bpp::VectorTools::sum().

◆ numberOfSynonymousPositions()

double CodonSiteTools::numberOfSynonymousPositions	(	int	i,
		const GeneticCode &	gCode,
		double	ratio = `1.0`
	)

static

Return the number of synonymous positions of a codon.

A site is consider as x% synonymous if x% of the possible mutations are synonymous Transition/transversion ratio can be taken into account (use the variable ratio)

Unresolved codons and stop codon will return a value of 0.

Parameters

i	a int
gCode	a GeneticCode
ratio	a double set by default to 1

Definition at line 496 of file CodonSiteTools.cpp.

References bpp::GeneticCode::getCodonAlphabet(), bpp::GeneticCode::isStop(), and bpp::GeneticCode::translate().

◆ 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().

◆ piNonSynonymous()

double CodonSiteTools::piNonSynonymous	(	const Site &	site,
		const GeneticCode &	gCode,
		bool	minchange = `false`
	)

static

Compute the non-synonymous pi per codon site.

The following formula is used:

$pi = \frac{n}{n-1}\sum_{i,j}x_{i}x_{j}P_{ij}$

where n is the number of sequence, and the frequencies of each codon type occurring at the site $P_{i,j}$ the number of nonsynonymous difference between these codons. Be careful: here, pi is not normalized by the number of non-synonymous sites. If minchange = false (default option) the different paths are equally weighted. If minchange = true the path with the minimum number of non-synonymous change is chosen.

Parameters

site	a Site
gCode	a GeneticCode
minchange	a boolean set by default to false

Definition at line 459 of file CodonSiteTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::alphabet(), bpp::Alphabet::equals(), bpp::AbstractTemplateSymbolList< T >::getAlphabet(), bpp::GeneticCode::getCodonAlphabet(), bpp::SymbolListTools::getFrequencies(), bpp::AlphabetTools::isCodonAlphabet(), bpp::SymbolListTools::isConstant(), bpp::AbstractTemplateSymbolList< T >::size(), and bpp::GeneticCode::sourceAlphabet().

◆ piSynonymous()

double CodonSiteTools::piSynonymous	(	const Site &	site,
		const GeneticCode &	gCode,
		bool	minchange = `false`
	)

static

Compute the synonymous pi per codon site.

The following formula is used:

$pi = \frac{n}{n-1}\sum_{i,j}x_{i}x_{j}P_{ij}$

where n is the number of sequence, and the frequencies of each codon type occurring at the site $P_{i,j}$ the number of synonymous difference between these codons. Be careful: here, pi is not normalized by the number of synonymous sites.

If minchange = false (default option) the different paths are equally weighted. If minchange = true the path with the minimum number of non-synonymous change is chosen.

Parameters

site	a Site
gCode	a GeneticCode
minchange	a boolean set by default to false

Definition at line 427 of file CodonSiteTools.cpp.

References bpp::AbstractTemplateSymbolList< T >::alphabet(), bpp::Alphabet::equals(), bpp::AbstractTemplateSymbolList< T >::getAlphabet(), bpp::GeneticCode::getCodonAlphabet(), bpp::SymbolListTools::getFrequencies(), bpp::AlphabetTools::isCodonAlphabet(), bpp::SymbolListTools::isConstant(), bpp::AbstractTemplateSymbolList< T >::size(), and bpp::GeneticCode::sourceAlphabet().

◆ 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().

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

Bpp/Seq/CodonSiteTools.h
Bpp/Seq/CodonSiteTools.cpp

Public Member Functions

Static Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ CodonSiteTools()

◆ ~CodonSiteTools()

Member Function Documentation

◆ areSymbolListsIdentical() [1/3]

◆ areSymbolListsIdentical() [2/3]

◆ areSymbolListsIdentical() [3/3]

◆ changeGapsToUnknownCharacters() [1/3]

◆ changeGapsToUnknownCharacters() [2/3]

◆ changeGapsToUnknownCharacters() [3/3]

◆ changeUnresolvedCharactersToGaps() [1/3]

◆ changeUnresolvedCharactersToGaps() [2/3]

◆ changeUnresolvedCharactersToGaps() [3/3]

◆ entropy()

◆ fixedDifferences()

◆ generateCodonSiteWithoutRareVariant()

◆ 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]

◆ getMajorAllele()

◆ getMajorAlleleFrequency()

◆ getMinorAllele()

◆ getMinorAlleleFrequency()

◆ getNumberOfDistinctCharacters()

◆ getNumberOfDistinctPositions() [1/3]

◆ getNumberOfDistinctPositions() [2/3]

◆ getNumberOfDistinctPositions() [3/3]

◆ getNumberOfPositionsWithoutGap() [1/3]

◆ getNumberOfPositionsWithoutGap() [2/3]

◆ getNumberOfPositionsWithoutGap() [3/3]

◆ hasGap() [1/3]

◆ hasGap() [2/3]

◆ hasGap() [3/3]

◆ hasGapOrStop()

◆ hasSingleton()

◆ hasStop()

◆ hasUnknown() [1/3]

◆ hasUnknown() [2/3]

◆ hasUnknown() [3/3]

◆ hasUnresolved()

◆ heterozygosity()

◆ isComplete() [1/3]

◆ isComplete() [2/3]

◆ isComplete() [3/3]

◆ isConstant() [1/3]

◆ isConstant() [2/3]

◆ isConstant() [3/3]

◆ isDoubleton()

◆ isFourFoldDegenerated()

◆ isGapOnly() [1/3]

◆ isGapOnly() [2/3]

◆ isGapOnly() [3/3]

◆ isGapOrUnresolvedOnly() [1/3]

◆ isGapOrUnresolvedOnly() [2/3]

◆ isGapOrUnresolvedOnly() [3/3]

◆ isMonoSitePolymorphic()

◆ isParsimonyInformativeSite()

◆ isSynonymousPolymorphic()

◆ isTriplet()

◆ jointEntropy()

◆ meanNumberOfSynonymousPositions()

◆ mutualInformation()

◆ numberOfDifferences()

◆ numberOfGaps() [1/3]

◆ numberOfGaps() [2/3]