Static class providing methods to compute statistics on sequences data. More...

#include <Bpp/PopGen/SequenceStatistics.h>

Static Public Member Functions
static unsigned int	numberOfPolymorphicSites (const PolymorphismSequenceContainer &psc, bool gapflag=true, bool ignoreUnknown=true)
	Compute the number of polymorphic site in an alignment. More...

static double	frequencyOfPolymorphicSites (const PolymorphismSequenceContainer &psc, bool gapflag=true, bool ignoreUnknown=true)
	Compute the frequency of polymorphic site in an alignment. More...

static unsigned int	numberOfParsimonyInformativeSites (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Compute the number of parsimony informative sites in an alignment. More...

static unsigned int	numberOfSingletons (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Count the number of singleton nucleotides in an alignment. More...

static unsigned int	totalNumberOfMutations (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Count the total number of mutations in an alignment. More...

static unsigned int	totalNumberOfMutationsOnExternalBranches (const PolymorphismSequenceContainer &ing, const PolymorphismSequenceContainer &outg)
	Count the total number of mutations in external branchs. More...

static unsigned int	numberOfTriplets (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Compute the number of triplet in an alignment. More...

static double	heterozygosity (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Compute the sum of per site heterozygosity in an alignment. More...

static double	squaredHeterozygosity (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Compute the sum of per site squared heterozygosity in an alignment. More...

static double	gcContent (const PolymorphismSequenceContainer &psc)
	Compute the mean GC content in an alignment. More...

static std::vector< unsigned int >	gcPolymorphism (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Return the number of GC alleles and the total number of alleles at polymorphic sites only. More...

static double	watterson75 (const PolymorphismSequenceContainer &psc, bool gapflag=true, bool ignoreUnknown=true, bool scaled=false)
	Compute diversity estimator Theta of Watterson (1975, Theor Popul Biol, 7 pp256-276) More...

static double	tajima83 (const PolymorphismSequenceContainer &psc, bool gapflag=true, bool ignoreUnknown=true, bool scaled=false)
	Compute diversity estimator Theta of Tajima (1983, Genetics, 105 pp437-460) More...

static double	fayWu2000 (const PolymorphismSequenceContainer &psc, const Sequence &ancestralSites)
	Compute diversity estimator Theta H (eq. 3) of Fay and Wu (2000, Genetics, 155: 1405-1413) More...

static unsigned int	dvk (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Return the number of haplotype in the sample. Depaulis and Veuille (1998, Mol Biol Evol, 12 pp1788-1790) More...

static double	dvh (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Return the haplotype diversity of a sample. Depaulis and Veuille (1998, Mol Biol Evol, 12 pp1788-1790) More...

static unsigned int	numberOfTransitions (const PolymorphismSequenceContainer &psc)
	Return the number of transitions. More...

static unsigned int	numberOfTransversions (const PolymorphismSequenceContainer &psc)
	Return the number of transversions. More...

static double	ratioOfTransitionsTransversions (const PolymorphismSequenceContainer &psc)
	Return the ratio of transitions/transversions. More...

static unsigned int	numberOfSitesWithStopCodon (const PolymorphismSequenceContainer &psc, const GeneticCode &gCode, bool gapflag=true)
	Compute the number of codon sites with stop codon. More...

static unsigned int	numberOfMonoSitePolymorphicCodons (const PolymorphismSequenceContainer &psc, bool stopflag=true, bool gapflag=true)
	Compute the number of polymorphic codon with only one mutated site. More...

static unsigned int	numberOfSynonymousPolymorphicCodons (const PolymorphismSequenceContainer &psc, const GeneticCode &gc)
	Compute the number of synonymous polymorphic codon sites. More...

static double	watterson75Synonymous (const PolymorphismSequenceContainer &psc, const GeneticCode &gc)
	Compute the Watterson(1975,Theor Popul Biol, 7 pp256-276) estimator for synonymous positions. More...

static double	watterson75NonSynonymous (const PolymorphismSequenceContainer &psc, const GeneticCode &gc)
	Compute the Watterson(1975, Theor Popul Biol, 7 pp256-276) estimator for non synonymous positions. More...

static double	piSynonymous (const PolymorphismSequenceContainer &psc, const GeneticCode &gc, bool minchange=false)
	Compute the synonymous nucleotide diversity, pi. More...

static double	piNonSynonymous (const PolymorphismSequenceContainer &psc, const GeneticCode &gc, bool minchange=false)
	Compute the non-synonymous nucleotide diversity, pi. More...

static double	meanNumberOfSynonymousSites (const PolymorphismSequenceContainer &psc, const GeneticCode &gc, double ratio=1.)
	compute the mean number of synonymous site in an alignment More...

static double	meanNumberOfNonSynonymousSites (const PolymorphismSequenceContainer &psc, const GeneticCode &gc, double ratio=1.)
	compute the mean number of non-synonymous site in an alignment More...

static unsigned int	numberOfSynonymousSubstitutions (const PolymorphismSequenceContainer &psc, const GeneticCode &gc, double freqmin=0.)
	compute the number of synonymous subsitutions in an alignment More...

static unsigned int	numberOfNonSynonymousSubstitutions (const PolymorphismSequenceContainer &psc, const GeneticCode &gc, double freqmin=0.)
	compute the number of non synonymous subsitutions in an alignment More...

static std::vector< unsigned int >	fixedDifferences (const PolymorphismSequenceContainer &pscin, const PolymorphismSequenceContainer &pscout, PolymorphismSequenceContainer &psccons, const GeneticCode &gc)
	compute the number of fixed differences between two alignements More...

static std::vector< unsigned int >	mkTable (const PolymorphismSequenceContainer &ingroup, const PolymorphismSequenceContainer &outgroup, const GeneticCode &gc, double freqmin=0.)
	return a vector containing Pa, Ps, Da, Ds More...

static double	neutralityIndex (const PolymorphismSequenceContainer &ingroup, const PolymorphismSequenceContainer &outgroup, const GeneticCode &gc, double freqmin=0.)
	return the neutrality index NI = (Pa/Ps)/(Da/Ds) (Rand & Kann 1996, Mol. Biol. Evol. 13 pp735-748) More...

static double	tajimaDss (const PolymorphismSequenceContainer &psc, bool gapflag=true, bool ignoreUnknown=true)
	Return the Tajima's D test (Tajima 1989, Genetics 123 pp 585-595). More...

static double	tajimaDtnm (const PolymorphismSequenceContainer &psc, bool gapflag=true, bool ignoreUnknown=true)
	Return the Tajima's D test (Tajima 1989, Genetics 123 pp 585-595). More...

static double	fuLiD (const PolymorphismSequenceContainer &ingroup, const PolymorphismSequenceContainer &outgroup, bool useNbSingletons=true, bool useNbSegregatingSites=false)
	Return the Fu and Li D test (Fu & Li 1993, Genetics, 133 pp693-709). More...

static double	fuLiDStar (const PolymorphismSequenceContainer &group, bool useNbSegregatingSites=false)
	Return the Fu and Li D^* test (Fu & Li 1993, Genetics, 133 pp693-709). More...

static double	fuLiF (const PolymorphismSequenceContainer &ingroup, const PolymorphismSequenceContainer &outgroup, bool useNbSingletons=true, bool useNbSegregatingSites=false)
	Return the Fu and Li F test (Fu & Li 1993, Genetics, 133 pp693-709). More...

static double	fuLiFStar (const PolymorphismSequenceContainer &group, bool useNbSegregatingSites)
	Return the Fu and Li F^* test (Fu & Li 1993, Genetics, 133 pp693-709). More...

static double	fstHudson92 (const PolymorphismSequenceContainer &psc, size_t id1, size_t id2)

static PolymorphismSequenceContainer *	generateLdContainer (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.)
	generate a special PolymorphismSequenceContainer for linkage disequilbrium analysis More...

static Vdouble	pairwiseDistances1 (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.)
	give the vector of the pairwise distances between site positions corresponding to a LD SequencePolymorphismContainer More...

static Vdouble	pairwiseDistances2 (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.)
	give the vector of all mean pairwise distance between two sites to a LD SequencePolymorphismContainer More...

static Vdouble	pairwiseD (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.)
	give the vector of all mean pairwise D value between two sites (Lewontin & Kojima 1964, Evolution 14 pp458-472) More...

static Vdouble	pairwiseDprime (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.)
	give the vector of all mean pairwise D' value between two sites (Lewontin 1964, Genetics 49 pp49-67)) More...

static Vdouble	pairwiseR2 (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.)
	give the vector of all mean pairwise R² value between two sites (Hill & Robertson 1968, Theor. Appl. Genet., 38 pp226-231) More...

static double	meanD (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.)
	give mean D over all pairwise comparisons More...

static double	meanDprime (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.)
	give mean D' over all pairwise comparisons More...

static double	meanR2 (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.)
	give mean R² over all pairwise comparisons More...

static double	meanDistance1 (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.)
	give mean pairwise distances between sites / method 1: differences between sequences are not taken into account More...

static double	meanDistance2 (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.)
	give mean pairwise distances between sites / method 2: differences between sequences are taken into account More...

static double	originRegressionD (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.)
	give the slope of the regression \|D\| = 1+a*distance More...

static double	originRegressionDprime (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.)
	give the slope of the regression \|D'\| = 1+a*distance More...

static double	originRegressionR2 (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.)
	give the slope of the regression R² = 1+a*distance More...

static Vdouble	linearRegressionD (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.)
	give the slope and the origin of the regression \|D\| = a*distance+b More...

static Vdouble	linearRegressionDprime (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.)
	give the slope and the origin of the regression \|D'\| = a*distance+b More...

static Vdouble	linearRegressionR2 (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.)
	give the slope and the origin of the regression R² = a*distance+b More...

static double	inverseRegressionR2 (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.)
	give the slope of the regression R² = 1/(1+a*distance) More...

static double	hudson87 (const PolymorphismSequenceContainer &psc, double precision=0.000001, double cinf=0.001, double csup=10000.)
	give estimate of C=4Nr using Hudson method (Hudson 1987, Genet. Res., 50 pp245-250) More...

static void	testUsefulValues (std::ostream &s, size_t n)
	Test useful values. More...

Static Private Member Functions
static unsigned int	getNumberOfMutations_ (const Site &site)
	Count the number of mutation for a site. More...

static unsigned int	getNumberOfSingletons_ (const Site &site)
	Count the number of singleton for a site. More...

static unsigned	getNumberOfDerivedSingletons_ (const Site &site_in, const Site &site_out)
	Count the number of singleton for a site. More...

static std::map< std::string, double >	getUsefulValues_ (size_t n)
	Get useful values for theta estimators. More...

static double	getVD_ (size_t n, double a1, double a2, double cn)
	Get the vD value of equation (32) in Fu & Li 1993, Genetics, 133 pp693-709) More...

static double	getUD_ (double a1, double vD)
	Get the uD value of equation (32) in Fu & Li 1993, Genetics, 133 pp693-709) More...

static double	getVDstar_ (size_t n, double a1, double a2, double dn)
	Get the vD* value of D* equation in Fu & Li 1993, Genetics, 133 pp693-709) More...

static double	getUDstar_ (size_t n, double a1, double vDs)
	Get the uD* value of D* equation in Fu & Li 1993, Genetics, 133 pp693-709) More...

static double	leftHandHudson_ (const PolymorphismSequenceContainer &psc)
	give the left hand term of equation (4) in Hudson (Hudson 1987, Genet. Res., 50 pp245-250) This term is used in hudson87 More...

static double	rightHandHudson_ (double c, size_t n)
	give the right hand term of equation (4) in Hudson (Hudson 1987, Genet. Res., 50 pp245-250) This term is used in hudson87 More...

Detailed Description

Static class providing methods to compute statistics on sequences data.

Author: Sylvain Gaillard

Definition at line 69 of file SequenceStatistics.h.

Member Function Documentation

◆ dvh()

double SequenceStatistics::dvh	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`
	)

static

Return the haplotype diversity of a sample. Depaulis and Veuille (1998, Mol Biol Evol, 12 pp1788-1790)

Parameters

psc	a PolymorphismSequenceContainer
gapflag	flag set by default to true if you don't want to take gaps into account

Author: Éric Bazin

Todo:

remove unneeded Sequence Container recopy
work on Sequence rather on string

Definition at line 439 of file SequenceStatistics.cpp.

◆ dvk()

unsigned int SequenceStatistics::dvk	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`
	)

static

Return the number of haplotype in the sample. Depaulis and Veuille (1998, Mol Biol Evol, 12 pp1788-1790)

Parameters

psc	a PolymorphismSequenceContainer
gapflag	flag set by default to true if you don't want to take gap into account

Author: Éric Bazin

Todo:

remove unneeded Sequence Container recopy
work on Sequence rather than string

Definition at line 401 of file SequenceStatistics.cpp.

◆ fayWu2000()

double SequenceStatistics::fayWu2000	(	const PolymorphismSequenceContainer &	psc,
		const Sequence &	ancestralSites
	)

static

Compute diversity estimator Theta H (eq. 3) of Fay and Wu (2000, Genetics, 155: 1405-1413)

Parameters

psc	a PolymorphismSequenceContainer
ancestralSites	a Sequence containing the ancestral states (reconstructed independently) to fold the mutation in the psc SequenceContainer.

Author: Benoit Nabholz

Definition at line 354 of file SequenceStatistics.cpp.

References count(), bpp::VectorSiteContainer::getAlphabet(), bpp::Sequence::getChar(), bpp::VectorSiteContainer::getNumberOfSites(), bpp::VectorSiteContainer::getSequence(), bpp::VectorSiteContainer::getSite(), bpp::Sequence::getValue(), and bpp::Sequence::size().

◆ fixedDifferences()

vector< unsigned int > SequenceStatistics::fixedDifferences	(	const PolymorphismSequenceContainer &	pscin,
		const PolymorphismSequenceContainer &	pscout,
		PolymorphismSequenceContainer &	psccons,
		const GeneticCode &	gc
	)

static

compute the number of fixed differences between two alignements

Gaps and unresolved sites are automatically 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

pscin	a PolymorphismSequenceContainer
pscout	a PolymorphismSequenceContainer
psccons	a PolymorphismSequenceContainer
gc	a GeneticCode

Author: Sylvain Glémin

Definition at line 753 of file SequenceStatistics.cpp.

References bpp::Site::getValue().

◆ frequencyOfPolymorphicSites()

double SequenceStatistics::frequencyOfPolymorphicSites	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`,
		bool	ignoreUnknown = `true`
	)

static

Compute the frequency of polymorphic site in an alignment.

The number of polymorphic site is also known as the number of segregating site . This number is devided by the number of callable sites, which dependson the gapflag and ignoreUnknown arguments.

Gaps are consider as mutations so if you want number of polymorphic site without gap, set the gapflag parameter to true.

Parameters

psc	a PolymorphismSequenceContainer
gapflag	a boolean set by default to true if you don't want to take gap into account
ignoreUnknown	a boolean set by default to true to ignore unknown states

Definition at line 92 of file SequenceStatistics.cpp.

◆ fstHudson92()

double SequenceStatistics::fstHudson92	(	const PolymorphismSequenceContainer &	psc,
		size_t	id1,
		size_t	id2
	)

static

Fst of Hudson, Slatkin and Maddison

Taken from eq. 3 of Hudson, Slatkin and Maddison 1992 Genetics 132:153

$F_{st} = 1 - \frac{H_w}{H_b}$

where is mean number of differences between different sequences sampled from the same subpopulation, and is the mean number of differences between sequences sampled from the two different subpopulations sampled.

Parameters

psc	a PolymorphismSequenceContainer will at least two populations
id1	is the id of the population 1
id2	is the id of the population 2

Author: Benoit Nabholz

Definition at line 954 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences(), bpp::VectorSiteContainer::getNumberOfSites(), and bpp::VectorSiteContainer::getSequence().

◆ fuLiD()

double SequenceStatistics::fuLiD	(	const PolymorphismSequenceContainer &	ingroup,
		const PolymorphismSequenceContainer &	outgroup,
		bool	useNbSingletons = `true`,
		bool	useNbSegregatingSites = `false`
	)

static

Return the Fu and Li D test (Fu & Li 1993, Genetics, 133 pp693-709).

Parameters

ingroup	a PolymorphismSequenceContainer
outgroup	a PolymorphismSequenceContainer
useNbSingletons	use the original Fu & Li method based on the number of singletons, otherwise, use the total number of mutations in external branches.
useNbSegregatingSites	use the number of seggregating sites, otherwise use the total number of mutations. These two quantities are identical under the infinite site model, but the number of segregating sites will underestimate the total number of mutations in case of multiple substitutions at the same site.

Exceptions

ZeroDivisionException if eta == 0

Author: Sylvain Gaillard; Khalid Belkhir; Julien Dutheil

If one set original=false then the number of mutations will be used. If the outgroup contains more than one sequence the sites with more than one variant will not be considered for external branch mutations!

Definition at line 842 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

◆ fuLiDStar()

double SequenceStatistics::fuLiDStar	(	const PolymorphismSequenceContainer &	group,
		bool	useNbSegregatingSites = `false`
	)

static

Return the Fu and Li D^* test (Fu & Li 1993, Genetics, 133 pp693-709).

Parameters

group	a PolymorphismSequenceContainer
useNbSegregatingSites	use the number of seggregating sites, otherwise use the total number of mutations. These two quantities are identical under the infinite site model, but the number of segregating sites will underestimate the total number of mutations in case of multiple substitutions at the same site.

Author: Sylvain Gaillard; Julien Dutheil

Definition at line 868 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

◆ fuLiF()

double SequenceStatistics::fuLiF	(	const PolymorphismSequenceContainer &	ingroup,
		const PolymorphismSequenceContainer &	outgroup,
		bool	useNbSingletons = `true`,
		bool	useNbSegregatingSites = `false`
	)

static

Return the Fu and Li F test (Fu & Li 1993, Genetics, 133 pp693-709).

Parameters

ingroup	a PolymorphismSequenceContainer
outgroup	a PolymorphismSequenceContainer external branch.
useNbSingletons	use the original Fu & Li method based on the number of singletons, otherwise, use the total number of mutations in external branches.
useNbSegregatingSites	use the number of seggregating sites, otherwise use the total number of mutations. These two quantities are identical under the infinite site model, but the number of segregating sites will underestimate the total number of mutations in case of multiple substitutions at the same site.

Author: Sylvain Gaillard; Khalid Belkhir; Julien Dutheil

If one set original=false then the number of mutations will be used. If the outgroup contains more than one sequence the sites with more than one variant will not be considered for external branch mutations!

Definition at line 897 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

◆ fuLiFStar()

double SequenceStatistics::fuLiFStar	(	const PolymorphismSequenceContainer &	group,
		bool	useNbSegregatingSites
	)

static

Return the Fu and Li F^* test (Fu & Li 1993, Genetics, 133 pp693-709).

Parameters

group	a PolymorphismSequenceContainer
useNbSegregatingSites	use the number of seggregating sites, otherwise use the total number of mutations. These two quantities are identical under the infinite site model, but the number of segregating sites will underestimate the total number of mutations in case of multiple substitutions at the same site.

Author: Sylvain Gaillard; Julien Dutheil

Definition at line 925 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

◆ gcContent()

double SequenceStatistics::gcContent ( const PolymorphismSequenceContainer & psc )

static

Compute the mean GC content in an alignment.

Parameters

psc	a PolymorphismSequenceContainer

Definition at line 249 of file SequenceStatistics.cpp.

References bpp::Alphabet::charToInt(), and bpp::VectorSiteContainer::getAlphabet().

◆ gcPolymorphism()

std::vector< unsigned int > SequenceStatistics::gcPolymorphism	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`
	)

static

Return the number of GC alleles and the total number of alleles at polymorphic sites only.

G vs C and A vs T polymorphism are not taken into account

Warning: SG 15/03/2010: The code of this method is not clear. See implementation for more details.

Parameters

psc	a PolymorphismSequenceContainer
gapflag	a boolean set by default to true if you don't want to take gap into account

Returns: A std::vector of size 2 containing the number of GC alleles and the total number of alleles.

Definition at line 257 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

◆ generateLdContainer()

PolymorphismSequenceContainer * SequenceStatistics::generateLdContainer	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

generate a special PolymorphismSequenceContainer for linkage disequilbrium analysis

Create a PolymorphismSequenceContainer with only polymorphic site : The value 1 is assigned to the most frequent allele, and 0 to the least frequent. This psc is needed to compute Linkage Disequilibrium Statistics. Should be used before excluding gaps, but sites with gaps are not counted as polymorphic sites. Singleton can be excluded. Polymorphic site with the lowest frequency < threshold can be excluded. Only polymorphic sites with 2 alleles are kept.

Parameters

psc	a PolymorphismSequenceContainer
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Author: Sylvain Glémin

Todo:

To be moved to PolymorphismSequenceContainerTools.

Definition at line 997 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::addSite(), bpp::SiteContainer::getNumberOfSequences(), bpp::VectorSiteContainer::getNumberOfSites(), bpp::SiteContainer::getNumberOfSites(), bpp::VectorSiteContainer::getSite(), bpp::SiteContainer::getSite(), bpp::Site::getValue(), and bpp::Site::setElement().

◆ getNumberOfDerivedSingletons_()

unsigned int SequenceStatistics::getNumberOfDerivedSingletons_	(	const Site &	site_in,
		const Site &	site_out
	)

staticprivate

Count the number of singleton for a site.

will count singletons that are not in site_out (a site in outgroup) site_in is a site from an ingroup

Author: Khalid Belkhir

Definition at line 1542 of file SequenceStatistics.cpp.

◆ getNumberOfMutations_()

unsigned int SequenceStatistics::getNumberOfMutations_ ( const Site & site )

staticprivate

Count the number of mutation for a site.

Definition at line 1512 of file SequenceStatistics.cpp.

◆ getNumberOfSingletons_()

unsigned int SequenceStatistics::getNumberOfSingletons_ ( const Site & site )

staticprivate

Count the number of singleton for a site.

Definition at line 1529 of file SequenceStatistics.cpp.

◆ getUD_()

double SequenceStatistics::getUD_	(	double	a1,
		double	vD
	)

staticprivate

Get the uD value of equation (32) in Fu & Li 1993, Genetics, 133 pp693-709)

Parameters

a1	as describe in getUsefulValues
vD	as provided by getVD_

Returns: the uD value as double

Author: Sylvain Gaillard

Definition at line 1620 of file SequenceStatistics.cpp.

◆ getUDstar_()

double SequenceStatistics::getUDstar_	(	size_t	n,
		double	a1,
		double	vDs
	)

staticprivate

Get the uD* value of D* equation in Fu & Li 1993, Genetics, 133 pp693-709)

Parameters

n	the number of observed sequences
a1	as describe in getUsefulValues
vDs	as provided by getVDstar_

Returns: the uD* value as double

Author: Sylvain Gaillard

Definition at line 1653 of file SequenceStatistics.cpp.

◆ getUsefulValues_()

std::map< std::string, double > SequenceStatistics::getUsefulValues_ ( size_t n )

staticprivate

Get useful values for theta estimators.

Parameters

n	the number of observed sequences

Returns

A map with 11 values. Keys are a1, a2, a1n, b1, b2, c1, c2, cn, dn, e1 and e2. The values are :

$a_1=\sum_{i=1}^{n-1}\frac{1}{i} \qquad a_2=\sum_{i=1}^{n-1}\frac{1}{i^2}$

$a_{1n}=\sum_{i=1}^{n}\frac{1}{i}$

$b_1=\frac{n+1}{3(n-1)} \qquad b_2=\frac{2(n^2+n+3)}{9n(n-1)}$

$c_1=b_1-\frac{1}{a_1} \qquad c_2=b_2-\frac{n+2}{a_1n}+\frac{a_2}{a_1^2}$

$c_n=2\frac{na_1-2(n-1)}{(n-1)(n-2)}$

$d_n=c_n+\frac{n-2}{(n-1)^2}+\frac{2}{n-1}\left(\frac{3}{2}-\frac{2a_{1n}-3}{n-2}-\frac{1}{n}\right)$

$e_1=\frac{c_1}{a_1} \qquad e_2=\frac{c_2}{a_1^2+a_2}$

where

is the number of observed sequences.

Author: Sylvain Gaillard

Definition at line 1564 of file SequenceStatistics.cpp.

◆ getVD_()

double SequenceStatistics::getVD_	(	size_t	n,
		double	a1,
		double	a2,
		double	cn
	)

staticprivate

Get the vD value of equation (32) in Fu & Li 1993, Genetics, 133 pp693-709)

Parameters

n	the number of observed sequences
a1	as describe in getUsefulValues
a2	as describe in getUsefulValues
cn	as describe in getUsefulValues

Returns: the vD value as double

Author: Sylvain Gaillard

Definition at line 1611 of file SequenceStatistics.cpp.

◆ getVDstar_()

double SequenceStatistics::getVDstar_	(	size_t	n,
		double	a1,
		double	a2,
		double	dn
	)

staticprivate

Get the vD* value of D* equation in Fu & Li 1993, Genetics, 133 pp693-709)

Parameters

n	the number of observed sequences
a1	as describe in getUsefulValues
a2	as describe in getUsefulValues
dn	as describe in getUsefulValues

Returns: the vD* value as double

Author: Sylvain Gaillard

Definition at line 1625 of file SequenceStatistics.cpp.

◆ heterozygosity()

double SequenceStatistics::heterozygosity	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`
	)

static

Compute the sum of per site heterozygosity in an alignment.

Parameters

psc	a PolymorphismSequenceContainer
gapflag	a boolean set by default to true if you don't want to take gap into account

Definition at line 210 of file SequenceStatistics.cpp.

◆ hudson87()

double SequenceStatistics::hudson87	(	const PolymorphismSequenceContainer &	psc,
		double	precision = `0.000001`,
		double	cinf = `0.001`,
		double	csup = `10000.`
	)

static

give estimate of C=4Nr using Hudson method (Hudson 1987, Genet. Res., 50 pp245-250)

Parameters

psc	a PolymorphismSequenceContainer
precision	default value = 0.000001
cinf	initial value, by default cinf=0.001
csup	initial value, by default csup = 10000

Author: Sylvain Glémin

Definition at line 1454 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

◆ inverseRegressionR2()

double SequenceStatistics::inverseRegressionR2	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give the slope of the regression R² = 1/(1+a*distance)

To fit the theoretical prediction R² = 1/(1+4Nr) The slope is given in R² per kb

Parameters

psc	a PolymorphismSequenceContainer
distance1	a boolean (true to use distance1, false to use distance2, false by default)
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1437 of file SequenceStatistics.cpp.

◆ leftHandHudson_()

double SequenceStatistics::leftHandHudson_ ( const PolymorphismSequenceContainer & psc )

staticprivate

give the left hand term of equation (4) in Hudson (Hudson 1987, Genet. Res., 50 pp245-250) This term is used in hudson87

Parameters

psc	a PolymorphismSequenceContainer

Definition at line 1668 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

◆ linearRegressionD()

Vdouble SequenceStatistics::linearRegressionD	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give the slope and the origin of the regression |D| = a*distance+b

The slope is given in |D| per kb

Parameters

psc	a PolymorphismSequenceContainer
distance1	a boolean (true to use distance1, false to use distance2, false by default)
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1395 of file SequenceStatistics.cpp.

◆ linearRegressionDprime()

Vdouble SequenceStatistics::linearRegressionDprime	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give the slope and the origin of the regression |D'| = a*distance+b

The slope is given in |D'| per kb

Parameters

psc	a PolymorphismSequenceContainer
distance1	a boolean (true to use distance1, false to use distance2, false by default)
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1409 of file SequenceStatistics.cpp.

◆ linearRegressionR2()

Vdouble SequenceStatistics::linearRegressionR2	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give the slope and the origin of the regression R² = a*distance+b

The slope is given in R² per kb

Parameters

psc	a PolymorphismSequenceContainer
distance1	a boolean (true to use distance1, false to use distance2, false by default)
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1423 of file SequenceStatistics.cpp.

◆ meanD()

double SequenceStatistics::meanD	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give mean D over all pairwise comparisons

Parameters

psc	a PolymorphismSequenceContainer
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1328 of file SequenceStatistics.cpp.

◆ meanDistance1()

double SequenceStatistics::meanDistance1	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give mean pairwise distances between sites / method 1: differences between sequences are not taken into account

Parameters

psc	a PolymorphismSequenceContainer
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites is lower than 2

Author: Sylvain Glémin

Definition at line 1346 of file SequenceStatistics.cpp.

◆ meanDistance2()

double SequenceStatistics::meanDistance2	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give mean pairwise distances between sites / method 2: differences between sequences are taken into account

Parameters

psc	a PolymorphismSequenceContainer
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites is lower than 2

Author: Sylvain Glémin

Definition at line 1352 of file SequenceStatistics.cpp.

◆ meanDprime()

double SequenceStatistics::meanDprime	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give mean D' over all pairwise comparisons

Parameters

psc	a PolymorphismSequenceContainer
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1334 of file SequenceStatistics.cpp.

◆ meanNumberOfNonSynonymousSites()

double SequenceStatistics::meanNumberOfNonSynonymousSites	(	const PolymorphismSequenceContainer &	psc,
		const GeneticCode &	gc,
		double	ratio = `1.`
	)

static

compute the mean number of non-synonymous site in an alignment

A site is x% synonymous if x% of possible mutations are synonymous The transition/transversion can be taken into account (use the variable ratio). Gaps are automatically excluded

Parameters

psc	a PolymorphismSequenceContainer
gc	a GeneticCode
ratio	a double

Author: Éric Bazin

Definition at line 710 of file SequenceStatistics.cpp.

References bpp::ConstSiteIterator::hasMoreSites(), and bpp::ConstSiteIterator::nextSite().

◆ meanNumberOfSynonymousSites()

double SequenceStatistics::meanNumberOfSynonymousSites	(	const PolymorphismSequenceContainer &	psc,
		const GeneticCode &	gc,
		double	ratio = `1.`
	)

static

compute the mean number of synonymous site in an alignment

A site is x% synonymous if x% of possible mutations are synonymous. The transition/transversion can be taken into account (use the variable ratio). Gaps and unresolved sites are automatically excluded.

Parameters

psc	a PolymorphismSequenceContainer
gc	a GeneticCode
ratio	a double

Author: Sylvain Glémin; Éric Bazin

Definition at line 696 of file SequenceStatistics.cpp.

References bpp::ConstSiteIterator::hasMoreSites(), and bpp::ConstSiteIterator::nextSite().

◆ meanR2()

double SequenceStatistics::meanR2	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give mean R² over all pairwise comparisons

Parameters

psc	a PolymorphismSequenceContainer
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1340 of file SequenceStatistics.cpp.

◆ mkTable()

vector< unsigned int > SequenceStatistics::mkTable	(	const PolymorphismSequenceContainer &	ingroup,
		const PolymorphismSequenceContainer &	outgroup,
		const GeneticCode &	gc,
		double	freqmin = `0.`
	)

static

return a vector containing Pa, Ps, Da, Ds

Gaps and unresolved sites are automatically excluded

Parameters

ingroup	a PolymorphismSequenceContainer
outgroup	a PolymorphismSequenceContainer
gc	a GeneticCode
freqmin	a double, to exclude snp in frequency strictly lower than freqmin

Author: Sylvain Glémin

Definition at line 778 of file SequenceStatistics.cpp.

References bpp::PolymorphismSequenceContainer::addSequence(), bpp::VectorSiteContainer::getAlphabet(), bpp::VectorSiteContainer::getNumberOfSequences(), bpp::VectorSiteContainer::getSequence(), and bpp::PolymorphismSequenceContainer::setAsOutgroupMember().

◆ neutralityIndex()

double SequenceStatistics::neutralityIndex	(	const PolymorphismSequenceContainer &	ingroup,
		const PolymorphismSequenceContainer &	outgroup,
		const GeneticCode &	gc,
		double	freqmin = `0.`
	)

static

return the neutrality index NI = (Pa/Ps)/(Da/Ds) (Rand & Kann 1996, Mol. Biol. Evol. 13 pp735-748)

Return -1 if Ps or Da are zero Gaps and unresolved sites are automatically excluded

Parameters

ingroup	a PolymorphismSequenceContainer
outgroup	a PolymorphismSequenceContainer
gc	a GeneticCode
freqmin	a double, to exclude snp in frequency strictly lower than freqmin

Author: Sylvain Glémin

Definition at line 803 of file SequenceStatistics.cpp.

◆ numberOfMonoSitePolymorphicCodons()

unsigned int SequenceStatistics::numberOfMonoSitePolymorphicCodons	(	const PolymorphismSequenceContainer &	psc,
		bool	stopflag = `true`,
		bool	gapflag = `true`
	)

static

Compute the number of polymorphic codon with only one mutated site.

Parameters

psc	a PolymorphismSequenceContainer
stopflag	a boolean set by default to true if you don't want to take stop codon neither undefined sites into account
gapflag	a boolean set by default to true if you don't want to take gaps into account

Author: Sylvain Glémin

Definition at line 611 of file SequenceStatistics.cpp.

◆ numberOfNonSynonymousSubstitutions()

unsigned int SequenceStatistics::numberOfNonSynonymousSubstitutions	(	const PolymorphismSequenceContainer &	psc,
		const GeneticCode &	gc,
		double	freqmin = `0.`
	)

static

compute the number of non synonymous subsitutions in an alignment

Gaps and unresolved sites are automatically 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

psc	a PolymorphismSequenceContainer
gc	a GeneticCode
freqmin	a double, to exclude snp in frequency strictly lower than freqmin

Definition at line 740 of file SequenceStatistics.cpp.

◆ numberOfParsimonyInformativeSites()

unsigned int SequenceStatistics::numberOfParsimonyInformativeSites	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`
	)

static

Compute the number of parsimony informative sites in an alignment.

Parameters

psc	a PolymorphicSequenceContainer
gapflag	a boolean set by default to true if you don't want to take gap into account

Definition at line 114 of file SequenceStatistics.cpp.

◆ numberOfPolymorphicSites()

unsigned int SequenceStatistics::numberOfPolymorphicSites	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`,
		bool	ignoreUnknown = `true`
	)

static

Compute the number of polymorphic site in an alignment.

The number of polymorphic site is also known as the number of segregating site .

Gaps are consider as mutations so if you want number of polymorphic site without gap, set the gapflag parameter to true.

Parameters

psc	a PolymorphismSequenceContainer
gapflag	a boolean set by default to true if you don't want to take gap into account
ignoreUnknown	a boolean set by default to true to ignore unknown states

Definition at line 72 of file SequenceStatistics.cpp.

◆ numberOfSingletons()

unsigned int SequenceStatistics::numberOfSingletons	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`
	)

static

Count the number of singleton nucleotides in an alignment.

Parameters

psc	a PolymorphismSequenceContainer
gapflag	a boolean set by default to true if you don't want to take gap into account

Author: Sylvain Gaillard

Definition at line 134 of file SequenceStatistics.cpp.

◆ numberOfSitesWithStopCodon()

unsigned int SequenceStatistics::numberOfSitesWithStopCodon	(	const PolymorphismSequenceContainer &	psc,
		const GeneticCode &	gCode,
		bool	gapflag = `true`
	)

static

Compute the number of codon sites with stop codon.

Parameters

psc	a PolymorphismSequenceContainer
gCode	the genetic code to use
gapflag	a boolean set by default to true if you don't want to take gaps into account

Author: Sylvain Glémin

Definition at line 586 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getAlphabet().

◆ numberOfSynonymousPolymorphicCodons()

unsigned int SequenceStatistics::numberOfSynonymousPolymorphicCodons	(	const PolymorphismSequenceContainer &	psc,
		const GeneticCode &	gc
	)

static

Compute the number of synonymous polymorphic codon sites.

Gaps and unresolved sites are automatically excluded

Parameters

psc	a PolymorphismSequenceContainer
gc	a GeneticCode

Author: Sylvain Glémin; Éric Bazin

Definition at line 634 of file SequenceStatistics.cpp.

◆ numberOfSynonymousSubstitutions()

unsigned int SequenceStatistics::numberOfSynonymousSubstitutions	(	const PolymorphismSequenceContainer &	psc,
		const GeneticCode &	gc,
		double	freqmin = `0.`
	)

static

compute the number of synonymous subsitutions in an alignment

Gaps and unresolved sites are automatically 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

psc	a PolymorphismSequenceContainer
gc	a GeneticCode
freqmin	a double, to exclude snp in frequency strictly lower than freqmin

Definition at line 726 of file SequenceStatistics.cpp.

◆ numberOfTransitions()

unsigned int SequenceStatistics::numberOfTransitions ( const PolymorphismSequenceContainer & psc )

static

Return the number of transitions.

Parameters

psc	a PolymorphismSequenceContainer

Author: Éric Bazin

Definition at line 486 of file SequenceStatistics.cpp.

References bpp::Site::size().

◆ numberOfTransversions()

unsigned int SequenceStatistics::numberOfTransversions ( const PolymorphismSequenceContainer & psc )

static

Return the number of transversions.

Parameters

psc	a PolymorphismSequenceContainer

Author: Éric Bazin

Definition at line 516 of file SequenceStatistics.cpp.

References bpp::Site::size().

◆ numberOfTriplets()

unsigned int SequenceStatistics::numberOfTriplets	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`
	)

static

Compute the number of triplet in an alignment.

Parameters

psc	a PolymorphismSequenceContainer
gapflag	a boolean set by default to true if you don't want to take gap into account

Author: Sylvain Glémin

Definition at line 151 of file SequenceStatistics.cpp.

◆ originRegressionD()

double SequenceStatistics::originRegressionD	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give the slope of the regression |D| = 1+a*distance

The slope is given in |D| per kb

Parameters

psc	a PolymorphismSequenceContainer
distance1	a boolean (true to use distance1, false to use distance2, false by default)
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1362 of file SequenceStatistics.cpp.

◆ originRegressionDprime()

double SequenceStatistics::originRegressionDprime	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give the slope of the regression |D'| = 1+a*distance

The slope is given in |D'| per kb

Parameters

psc	a PolymorphismSequenceContainer
distance1	a boolean (true to use distance1, false to use distance2, false by default)
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1373 of file SequenceStatistics.cpp.

◆ originRegressionR2()

double SequenceStatistics::originRegressionR2	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give the slope of the regression R² = 1+a*distance

The slope is given in R² per kb

Parameters

psc	a PolymorphismSequenceContainer
distance1	a boolean (true to use distance1, false to use distance2, false by default)
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1384 of file SequenceStatistics.cpp.

◆ pairwiseD()

Vdouble SequenceStatistics::pairwiseD	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give the vector of all mean pairwise D value between two sites (Lewontin & Kojima 1964, Evolution 14 pp458-472)

Parameters

psc	a PolymorphismSequenceContainer
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1201 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences(), bpp::VectorSiteContainer::getNumberOfSites(), bpp::VectorSiteContainer::getSite(), and bpp::Site::getValue().

◆ pairwiseDistances1()

Vdouble SequenceStatistics::pairwiseDistances1	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give the vector of the pairwise distances between site positions corresponding to a LD SequencePolymorphismContainer

Assume that all sequences have the same length

Parameters

psc	a PolymorphismSequenceContainer
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites is lower than 2

Author: Sylvain Glémin

Definition at line 1067 of file SequenceStatistics.cpp.

References bpp::Site::getAlphabet(), bpp::VectorSiteContainer::getNumberOfSites(), bpp::VectorSiteContainer::getSite(), and bpp::Alphabet::getSize().

◆ pairwiseDistances2()

Vdouble SequenceStatistics::pairwiseDistances2	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give the vector of all mean pairwise distance between two sites to a LD SequencePolymorphismContainer

pairwise distances are computed for each sequence separately, excluding gaps. Then the mean is taken over all the sequences.

Parameters

psc	a PolymorphismSequenceContainer
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites is lower than 2

Author: Sylvain Glémin

Definition at line 1123 of file SequenceStatistics.cpp.

References bpp::Site::getAlphabet(), bpp::VectorSiteContainer::getNumberOfSequences(), bpp::VectorSiteContainer::getNumberOfSites(), bpp::VectorSiteContainer::getSequence(), bpp::VectorSiteContainer::getSite(), bpp::Alphabet::getSize(), and bpp::Sequence::getValue().

◆ pairwiseDprime()

Vdouble SequenceStatistics::pairwiseDprime	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give the vector of all mean pairwise D' value between two sites (Lewontin 1964, Genetics 49 pp49-67))

Parameters

psc	a PolymorphismSequenceContainer
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1234 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences(), bpp::VectorSiteContainer::getNumberOfSites(), bpp::VectorSiteContainer::getSite(), and bpp::Site::getValue().

◆ pairwiseR2()

Vdouble SequenceStatistics::pairwiseR2	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)

static

give the vector of all mean pairwise R² value between two sites (Hill & Robertson 1968, Theor. Appl. Genet., 38 pp226-231)

Parameters

psc	a PolymorphismSequenceContainer
keepsingleton	a boolean (true by default, false to exclude singleton)
freqmin	a float (to exlude site with the lowest allele frequency less than the threshold given by freqmin, 0 by default)

Exceptions

DimensionException if the number of sites or the number of sequences is lower than 2

Author: Sylvain Glémin

Definition at line 1290 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences(), bpp::VectorSiteContainer::getNumberOfSites(), bpp::VectorSiteContainer::getSite(), and bpp::Site::getValue().

◆ piNonSynonymous()

double SequenceStatistics::piNonSynonymous	(	const PolymorphismSequenceContainer &	psc,
		const GeneticCode &	gc,
		bool	minchange = `false`
	)

static

Compute the non-synonymous nucleotide diversity, pi.

Gaps and unresolved sites are automatically excluded 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

psc	a PolymorphismSequenceContainer
gc	a GeneticCode
minchange	a boolean set by default to false

Author: Sylvain Glémin; Éric Bazin

Definition at line 682 of file SequenceStatistics.cpp.

References bpp::ConstSiteIterator::hasMoreSites(), and bpp::ConstSiteIterator::nextSite().

◆ piSynonymous()

double SequenceStatistics::piSynonymous	(	const PolymorphismSequenceContainer &	psc,
		const GeneticCode &	gc,
		bool	minchange = `false`
	)

static

Compute the synonymous nucleotide diversity, pi.

Gaps and unresolved sites are automatically excluded 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

psc	a PolymorphismSequenceContainer
gc	a GeneticCode
minchange	a boolean set to false

Author: Sylvain Glémin; Éric Bazin

Definition at line 668 of file SequenceStatistics.cpp.

References bpp::ConstSiteIterator::hasMoreSites(), and bpp::ConstSiteIterator::nextSite().

◆ ratioOfTransitionsTransversions()

double SequenceStatistics::ratioOfTransitionsTransversions ( const PolymorphismSequenceContainer & psc )

static

Return the ratio of transitions/transversions.

Parameters

psc	a PolymorphismSequenceContainer

Author: Éric Bazin

Definition at line 546 of file SequenceStatistics.cpp.

References count().

◆ rightHandHudson_()

double SequenceStatistics::rightHandHudson_	(	double	c,
		size_t	n
	)

staticprivate

give the right hand term of equation (4) in Hudson (Hudson 1987, Genet. Res., 50 pp245-250) This term is used in hudson87

Definition at line 1694 of file SequenceStatistics.cpp.

◆ squaredHeterozygosity()

double SequenceStatistics::squaredHeterozygosity	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`
	)

static

Compute the sum of per site squared heterozygosity in an alignment.

Parameters

psc	a PolymorphismSequenceContainer
gapflag	a boolean set by default to true if you don't want to take gap into account

Definition at line 227 of file SequenceStatistics.cpp.

◆ tajima83()

double SequenceStatistics::tajima83	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`,
		bool	ignoreUnknown = `true`,
		bool	scaled = `false`
	)

static

Compute diversity estimator Theta of Tajima (1983, Genetics, 105 pp437-460)

$\hat{\theta}_\pi = \sum_{i=1}^{S} \left(1-\sum_{j=1}^{4} \frac{k_{j,i}\times\left(k_{j,i}-1\right)} {n_i\times\left(n_i-1\right)}\right) \qquad \textrm{with }k_{j,i}>0$

where $k_{j,i}$ is the count of the j^th state at the i^th site, the number of nucleotides and the number of polymorphic sites.

Parameters

psc	a PolymorphismSequenceContainer
gapflag	flag set by default to true if you don't want to take gap into account
ignoreUnknown	a boolean set by default to true to ignore unknown states
scaled	Tell if theta should be normalized per nucleotide (divided by the length of the sequence).

Author: Sylvain Gaillard, Julien Dutheil

Definition at line 312 of file SequenceStatistics.cpp.

References count(), bpp::VectorSiteContainer::getAlphabet(), and bpp::Alphabet::getSize().

◆ tajimaDss()

double SequenceStatistics::tajimaDss	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`,
		bool	ignoreUnknown = `true`
	)

static

Return the Tajima's D test (Tajima 1989, Genetics 123 pp 585-595).

Calculation using the number of polymorphic (segregating) sites.

$D=\frac{\hat{\theta}_\pi-\hat{\theta}_S}{\sqrt{\textrm{V}\left(\hat{\theta}_\pi-\hat{\theta}_S\right)}} =\frac{\hat{\theta}_\pi-\hat{\theta}_S}{\sqrt{e_1S+e_2S(S-1)}}$

Parameters

psc	a PolymorphismSequenceContainer
gapflag	flag set by default to true if you don't want to take gap into account
ignoreUnknown	a boolean set by default to true to ignore unknown states

Exceptions

ZeroDivisionException if S == 0

Author: Sylvain Gaillard

Definition at line 816 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

◆ tajimaDtnm()

double SequenceStatistics::tajimaDtnm	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`,
		bool	ignoreUnknown = `true`
	)

static

Return the Tajima's D test (Tajima 1989, Genetics 123 pp 585-595).

Calculation using the total number of mutation.

$D=\frac{\hat{\theta}_\pi-\frac{\eta}{a_1}}{\sqrt{e_1\eta+e_2\eta(\eta-1)}}$

Parameters

psc	a PolymorphismSequenceContainer
gapflag	flag set by default to true if you don't want to take gap into account
ignoreUnknown	a boolean set by default to true to ignore unknown states

Exceptions

ZeroDivisionException if eta == 0

Author: Sylvain Gaillard

Definition at line 829 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

◆ testUsefulValues()

void SequenceStatistics::testUsefulValues	(	std::ostream &	s,
		size_t	n
	)

static

Test useful values.

Parameters

s	a ostream where write the values
n	then number of observed sequences

Author: Sylvain Gaillard

Definition at line 1482 of file SequenceStatistics.cpp.

◆ totalNumberOfMutations()

unsigned int SequenceStatistics::totalNumberOfMutations	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`
	)

static

Count the total number of mutations in an alignment.

This count is assumed to be under an infinite site model.

Parameters

psc	a PolymorphismSequenceContainer
gapflag	a boolean set by default to true if you don't want to take gap into account

Author: Sylvain Gaillard

Definition at line 171 of file SequenceStatistics.cpp.

◆ totalNumberOfMutationsOnExternalBranches()

unsigned int SequenceStatistics::totalNumberOfMutationsOnExternalBranches	(	const PolymorphismSequenceContainer &	ing,
		const PolymorphismSequenceContainer &	outg
	)

static

Count the total number of mutations in external branchs.

This is counted as the number of distinct singleton nucleotide in the ingroup that are not shared with the outgroup. A site is ignored if it contains more than one variant in the outgroup. A site is ignored if it contains unresolved variants or gaps.

Parameters

ing	a PolymorphismSequenceContainer the ingroup alignement
outg	a PolymorphismSequenceContainer the outgroup alignement

Author: Khalid Belkhir

Definition at line 188 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSites().

◆ watterson75()

double SequenceStatistics::watterson75	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`,
		bool	ignoreUnknown = `true`,
		bool	scaled = `false`
	)

static

Compute diversity estimator Theta of Watterson (1975, Theor Popul Biol, 7 pp256-276)

$\hat{\theta}_S=\frac{S}{a_1}$

where is the number of polymorphic sites and is describe in SequenceStatistics::getUsefulValues_().

Parameters

psc	a PolymorphismSequenceContainer
gapflag	flag set by default to true if you don't want to take gap into account
ignoreUnknown	a boolean set by default to true to ignore unknown states
scaled	Tell if theta should be normalized per nucleotide (divided by the length of the sequence).

Author: Sylvain Gaillard, Julien Dutheil

Definition at line 298 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

◆ watterson75NonSynonymous()

double SequenceStatistics::watterson75NonSynonymous	(	const PolymorphismSequenceContainer &	psc,
		const GeneticCode &	gc
	)

static

Compute the Watterson(1975, Theor Popul Biol, 7 pp256-276) estimator for non synonymous positions.

Gaps and unresolved sites are automatically 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

psc	a PolymorphismSequenceContainer
gc	a GeneticCode

Author: Sylvain Glémin

Definition at line 658 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

◆ watterson75Synonymous()

double SequenceStatistics::watterson75Synonymous	(	const PolymorphismSequenceContainer &	psc,
		const GeneticCode &	gc
	)

static

Compute the Watterson(1975,Theor Popul Biol, 7 pp256-276) estimator for synonymous positions.

Gaps and unresolved sites are automatically 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

psc	a PolymorphismSequenceContainer
gc	a GeneticCode

Author: Sylvain Glémin

Definition at line 648 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

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

Bpp/PopGen/SequenceStatistics.h
Bpp/PopGen/SequenceStatistics.cpp

Static Public Member Functions

Static Private Member Functions

Detailed Description

Member Function Documentation

◆ dvh()

◆ dvk()

◆ fayWu2000()

◆ fixedDifferences()

◆ frequencyOfPolymorphicSites()

◆ fstHudson92()

◆ fuLiD()

◆ fuLiDStar()

◆ fuLiF()

◆ fuLiFStar()

◆ gcContent()

◆ gcPolymorphism()

◆ generateLdContainer()

◆ getNumberOfDerivedSingletons_()

◆ getNumberOfMutations_()

◆ getNumberOfSingletons_()

◆ getUD_()

◆ getUDstar_()

◆ getUsefulValues_()

◆ getVD_()

◆ getVDstar_()

◆ heterozygosity()

◆ hudson87()

◆ inverseRegressionR2()

◆ leftHandHudson_()

◆ linearRegressionD()

◆ linearRegressionDprime()

◆ linearRegressionR2()

◆ meanD()

◆ meanDistance1()

◆ meanDistance2()

◆ meanDprime()

◆ meanNumberOfNonSynonymousSites()

◆ meanNumberOfSynonymousSites()

◆ meanR2()

◆ mkTable()

◆ neutralityIndex()

◆ numberOfMonoSitePolymorphicCodons()

◆ numberOfNonSynonymousSubstitutions()

◆ numberOfParsimonyInformativeSites()

◆ numberOfPolymorphicSites()

◆ numberOfSingletons()

◆ numberOfSitesWithStopCodon()

◆ numberOfSynonymousPolymorphicCodons()

◆ numberOfSynonymousSubstitutions()

◆ numberOfTransitions()

◆ numberOfTransversions()

◆ numberOfTriplets()

◆ originRegressionD()

◆ originRegressionDprime()

◆ originRegressionR2()

◆ pairwiseD()

◆ pairwiseDistances1()

◆ pairwiseDistances2()

◆ pairwiseDprime()

◆ pairwiseR2()

◆ piNonSynonymous()

◆ piSynonymous()

◆ ratioOfTransitionsTransversions()

◆ rightHandHudson_()

◆ squaredHeterozygosity()

◆ tajima83()

◆ tajimaDss()

◆ tajimaDtnm()

◆ testUsefulValues()

◆ totalNumberOfMutations()

◆ totalNumberOfMutationsOnExternalBranches()

◆ watterson75()

◆ watterson75NonSynonymous()

◆ watterson75Synonymous()