Utilitary functions dealing with both sites and sequences. More...

#include <Bpp/Seq/SymbolListTools.h>

Inheritance diagram for bpp::SymbolListTools:

Public Member Functions
	SymbolListTools ()

virtual	~SymbolListTools ()

Static Public Member Functions
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	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	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	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	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	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 dealing with both sites and sequences.

Definition at line 22 of file SymbolListTools.h.

Constructor & Destructor Documentation

◆ SymbolListTools()

bpp::SymbolListTools::SymbolListTools ( )

inline

Definition at line 25 of file SymbolListTools.h.

◆ ~SymbolListTools()

virtual bpp::SymbolListTools::~SymbolListTools ( )

inlinevirtual

Definition at line 26 of file SymbolListTools.h.

Member Function Documentation

◆ areSymbolListsIdentical() [1/3]

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

inlinestatic

Definition at line 239 of file SymbolListTools.h.

References areSymbolListsIdentical().

◆ areSymbolListsIdentical() [2/3]

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

static

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 areSymbolListsIdentical().

◆ areSymbolListsIdentical() [3/3]

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

static

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 )

inlinestatic

Definition at line 709 of file SymbolListTools.h.

References changeGapsToUnknownCharacters().

◆ changeGapsToUnknownCharacters() [2/3]

void SymbolListTools::changeGapsToUnknownCharacters ( IntSymbolListInterface & l )

static

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 changeGapsToUnknownCharacters().

◆ changeGapsToUnknownCharacters() [3/3]

void SymbolListTools::changeGapsToUnknownCharacters ( ProbabilisticSymbolListInterface & l )

static

Definition at line 614 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ changeUnresolvedCharactersToGaps() [1/3]

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

inlinestatic

Definition at line 736 of file SymbolListTools.h.

References changeUnresolvedCharactersToGaps().

◆ changeUnresolvedCharactersToGaps() [2/3]

void SymbolListTools::changeUnresolvedCharactersToGaps ( IntSymbolListInterface & l )

static

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 changeUnresolvedCharactersToGaps().

◆ changeUnresolvedCharactersToGaps() [3/3]

void SymbolListTools::changeUnresolvedCharactersToGaps ( ProbabilisticSymbolListInterface & l )

static

Definition at line 623 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ entropy()

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

inlinestatic

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 variabilityShannon().

◆ getCounts() [1/6]

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

inlinestatic

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 getCounts(), and 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
	)

inlinestatic

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 getCounts(), and getCountsResolveUnknowns().

◆ getCounts() [3/6]

template<class count_type >

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

inlinestatic

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 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
	)

inlinestatic

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
	)

inlinestatic

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
	)

inlinestatic

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
	)

inlinestatic

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 getCounts().

◆ getCountsResolveUnknowns() [2/4]

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

static

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
	)

inlinestatic

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
	)

static

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`
	)

static

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`
	)

static

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`
	)

inlinestatic

Definition at line 609 of file SymbolListTools.h.

References getGCContent().

◆ getGCContent() [2/3]

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

static

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 getGCContent().

◆ getGCContent() [3/3]

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

static

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 )

static

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 )

static

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 )

static

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 )

static

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 )

static

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
	)

inlinestatic

Definition at line 646 of file SymbolListTools.h.

References getNumberOfDistinctPositions().

◆ getNumberOfDistinctPositions() [2/3]

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

static

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 getNumberOfDistinctPositions().

◆ getNumberOfDistinctPositions() [3/3]

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

static

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
	)

inlinestatic

Definition at line 682 of file SymbolListTools.h.

References getNumberOfPositionsWithoutGap().

◆ getNumberOfPositionsWithoutGap() [2/3]

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

static

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 getNumberOfPositionsWithoutGap().

◆ getNumberOfPositionsWithoutGap() [3/3]

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

static

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 )

inlinestatic

Definition at line 36 of file SymbolListTools.h.

References hasGap().

◆ hasGap() [2/3]

bool SymbolListTools::hasGap ( const IntSymbolListInterface & site )

static

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(), 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 )

static

Definition at line 33 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ hasSingleton()

bool SymbolListTools::hasSingleton ( const IntSymbolListInterface & list )

static

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 )

inlinestatic

Definition at line 152 of file SymbolListTools.h.

References hasUnknown().

◆ hasUnknown() [2/3]

bool SymbolListTools::hasUnknown ( const IntSymbolListInterface & site )

static

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 hasUnknown().

◆ hasUnknown() [3/3]

bool SymbolListTools::hasUnknown ( const ProbabilisticSymbolListInterface & site )

static

Definition at line 120 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ hasUnresolved()

bool SymbolListTools::hasUnresolved ( const IntSymbolListInterface & site )

static

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 )

static

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 )

inlinestatic

Definition at line 174 of file SymbolListTools.h.

References isComplete().

◆ isComplete() [2/3]

bool SymbolListTools::isComplete ( const IntSymbolListInterface & site )

static

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(), isComplete(), bpp::CompleteTemplateSiteContainerIterator< SiteType, SequenceType, HashType >::nextCompleteSitePosition(), and bpp::CompleteTemplateSiteContainerIterator< SiteType, SequenceType, HashType >::previousCompleteSitePosition().

◆ isComplete() [3/3]

bool SymbolListTools::isComplete ( const ProbabilisticSymbolListInterface & site )

static

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`
	)

inlinestatic

Definition at line 208 of file SymbolListTools.h.

References isConstant().

◆ isConstant() [2/3]

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

static

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(), 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`
	)

static

Definition at line 320 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ isDoubleton()

bool SymbolListTools::isDoubleton ( const IntSymbolListInterface & list )

static

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 )

inlinestatic

Definition at line 64 of file SymbolListTools.h.

References isGapOnly().

◆ isGapOnly() [2/3]

bool SymbolListTools::isGapOnly ( const IntSymbolListInterface & site )

static

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 isGapOnly(), bpp::SiteContainerTools::removeGapOnlySites(), and bpp::SiteContainerTools::removeGapOrUnresolvedOnlySites().

◆ isGapOnly() [3/3]

bool SymbolListTools::isGapOnly ( const ProbabilisticSymbolListInterface & site )

static

Definition at line 71 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ isGapOrUnresolvedOnly() [1/3]

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

inlinestatic

Definition at line 108 of file SymbolListTools.h.

References isGapOrUnresolvedOnly().

◆ isGapOrUnresolvedOnly() [2/3]

bool SymbolListTools::isGapOrUnresolvedOnly ( const IntSymbolListInterface & site )

static

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 isGapOrUnresolvedOnly(), and bpp::SiteContainerTools::removeGapOrUnresolvedOnlySites().

◆ isGapOrUnresolvedOnly() [3/3]

bool SymbolListTools::isGapOrUnresolvedOnly ( const ProbabilisticSymbolListInterface & site )

static

Definition at line 95 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ isParsimonyInformativeSite()

bool SymbolListTools::isParsimonyInformativeSite ( const IntSymbolListInterface & site )

static

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 )

static

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
	)

static

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
	)

static

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 )

inlinestatic

Definition at line 86 of file SymbolListTools.h.

References numberOfGaps().

◆ numberOfGaps() [2/3]

size_t SymbolListTools::numberOfGaps ( const IntSymbolListInterface & site )

static

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 numberOfGaps().

◆ numberOfGaps() [3/3]

size_t SymbolListTools::numberOfGaps ( const ProbabilisticSymbolListInterface & site )

static

Definition at line 172 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ numberOfUnresolved() [1/3]

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

inlinestatic

Definition at line 130 of file SymbolListTools.h.

References numberOfUnresolved().

◆ numberOfUnresolved() [2/3]

size_t SymbolListTools::numberOfUnresolved ( const IntSymbolListInterface & site )

static

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 numberOfUnresolved().

◆ numberOfUnresolved() [3/3]

size_t SymbolListTools::numberOfUnresolved ( const ProbabilisticSymbolListInterface & site )

static

Definition at line 200 of file SymbolListTools.cpp.

References bpp::CruxSymbolListInterface::size().

◆ variabilityFactorial()

double SymbolListTools::variabilityFactorial ( const IntSymbolListInterface & list )

static

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
	)

static

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 entropy().

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

Bpp/Seq/SymbolListTools.h
Bpp/Seq/SymbolListTools.cpp

Public Member Functions

Static Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ SymbolListTools()

◆ ~SymbolListTools()

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()

◆ 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]

◆ hasSingleton()

◆ 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()

◆ isGapOnly() [1/3]

◆ isGapOnly() [2/3]

◆ isGapOnly() [3/3]

◆ isGapOrUnresolvedOnly() [1/3]

◆ isGapOrUnresolvedOnly() [2/3]

◆ isGapOrUnresolvedOnly() [3/3]

◆ isParsimonyInformativeSite()

◆ isTriplet()

◆ jointEntropy()

◆ mutualInformation()

◆ numberOfGaps() [1/3]

◆ numberOfGaps() [2/3]

◆ numberOfGaps() [3/3]

◆ numberOfUnresolved() [1/3]

◆ numberOfUnresolved() [2/3]

◆ numberOfUnresolved() [3/3]

◆ variabilityFactorial()

◆ variabilityShannon()