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

#include <Bpp/PopGen/SequenceStatistics.h>

Public Member Functions
double	FstHudson92 (const PolymorphismSequenceContainer &psc, size_t id1, size_t id2)
Static Public Member Functions
static size_t	polymorphicSiteNumber (const PolymorphismSequenceContainer &psc, bool gapflag=true, bool ignoreUnknown=true)
	Compute the number of polymorphic site in an alignment.
static size_t	parsimonyInformativeSiteNumber (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Compute the number of parsimony informative sites in an alignment.
static size_t	countSingleton (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Count the number of singleton nucleotides in an alignment.
static size_t	totNumberMutations (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Count the total number of mutations in an alignment.
static size_t	totMutationsExternalBranchs (const PolymorphismSequenceContainer &ing, const PolymorphismSequenceContainer &outg) throw (Exception)
	Count the total number of mutations in external branchs.
static size_t	tripletNumber (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Compute the number of triplet in an alignment.
static double	heterozygosity (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Compute the sum of per site heterozygosity in an alignment.
static double	squaredHeterozygosity (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Compute the sum of per site squared heterozygosity in an alignment.
static double	gcContent (const PolymorphismSequenceContainer &psc)
	Compute the mean GC content in an alignment.
static std::vector< size_t >	gcPolymorphism (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Return the number of GC alleles and the total number of alleles at polymorphic sites only.
static double	watterson75 (const PolymorphismSequenceContainer &psc, bool gapflag=true, bool ignoreUnknown=true)
	Compute diversity estimator Theta of Watterson (1975, Theor Popul Biol, 7 pp256-276)
static double	tajima83 (const PolymorphismSequenceContainer &psc, bool gapflag=true)
	Compute diversity estimator Theta of Tajima (1983, Genetics, 105 pp437-460)
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)
static size_t	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)
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)
static size_t	getNumberOfTransitions (const PolymorphismSequenceContainer &psc)
	Return the number of transitions.
static size_t	getNumberOfTransversions (const PolymorphismSequenceContainer &psc)
	Return the number of transversions.
static double	getTransitionsTransversionsRatio (const PolymorphismSequenceContainer &psc) throw (Exception)
	Return the ratio of transitions/transversions.
static size_t	stopCodonSiteNumber (const PolymorphismSequenceContainer &psc, const GeneticCode &gCode, bool gapflag=true)
	Compute the number of codon sites with stop codon.
static size_t	monoSitePolymorphicCodonNumber (const PolymorphismSequenceContainer &psc, bool stopflag=true, bool gapflag=true)
	Compute the number of polymorphic codon with only one mutated site.
static size_t	synonymousPolymorphicCodonNumber (const PolymorphismSequenceContainer &psc, const GeneticCode &gc)
	Compute the number of synonymous polymorphic codon sites.
static double	watterson75Synonymous (const PolymorphismSequenceContainer &psc, const GeneticCode &gc)
	Compute the Watterson(1975,Theor Popul Biol, 7 pp256-276) estimator for synonymous positions.
static double	watterson75NonSynonymous (const PolymorphismSequenceContainer &psc, const GeneticCode &gc)
	Compute the Watterson(1975, Theor Popul Biol, 7 pp256-276) estimator for non synonymous positions.
static double	piSynonymous (const PolymorphismSequenceContainer &psc, const GeneticCode &gc, bool minchange=false)
	Compute the synonymous nucleotide diversity, pi.
static double	piNonSynonymous (const PolymorphismSequenceContainer &psc, const GeneticCode &gc, bool minchange=false)
	Compute the non-synonymous nucleotide diversity, pi.
static double	meanSynonymousSitesNumber (const PolymorphismSequenceContainer &psc, const GeneticCode &gc, double ratio=1.)
	compute the mean number of synonymous site in an alignment
static double	meanNonSynonymousSitesNumber (const PolymorphismSequenceContainer &psc, const GeneticCode &gc, double ratio=1.)
	compute the mean number of non-synonymous site in an alignment
static size_t	synonymousSubstitutionsNumber (const PolymorphismSequenceContainer &psc, const GeneticCode &gc, double freqmin=0.)
	compute the number of synonymous subsitutions in an alignment
static size_t	nonSynonymousSubstitutionsNumber (const PolymorphismSequenceContainer &psc, const GeneticCode &gc, double freqmin=0.)
	compute the number of non synonymous subsitutions in an alignment
static std::vector< size_t >	fixedDifferences (const PolymorphismSequenceContainer &pscin, const PolymorphismSequenceContainer &pscout, PolymorphismSequenceContainer &psccons, const GeneticCode &gc)
	compute the number of fixed differences between two alignements
static std::vector< size_t >	MKtable (const PolymorphismSequenceContainer &ingroup, const PolymorphismSequenceContainer &outgroup, const GeneticCode &gc, double freqmin=0.)
	return a vector containing Pa, Ps, Da, Ds
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)
static double	tajimaDSS (const PolymorphismSequenceContainer &psc, bool gapflag=true) throw (ZeroDivisionException)
	Return the Tajima's D test (Tajima 1989, Genetics 123 pp 585-595).
static double	tajimaDTNM (const PolymorphismSequenceContainer &psc, bool gapflag=true) throw (ZeroDivisionException)
	Return the Tajima's D test (Tajima 1989, Genetics 123 pp 585-595).
static double	fuliD (const PolymorphismSequenceContainer &ingroup, const PolymorphismSequenceContainer &outgroup, bool original=true) throw (ZeroDivisionException)
	Return the Fu and Li D test (Fu & Li 1993, Genetics, 133 pp693-709).
static double	fuliDstar (const PolymorphismSequenceContainer &group) throw (ZeroDivisionException)
	Return the Fu and Li D^* test (Fu & Li 1993, Genetics, 133 pp693-709).
static double	fuliF (const PolymorphismSequenceContainer &ingroup, const PolymorphismSequenceContainer &outgroup, bool original=true) throw (ZeroDivisionException)
	Return the Fu and Li F test (Fu & Li 1993, Genetics, 133 pp693-709).
static double	fuliFstar (const PolymorphismSequenceContainer &group) throw (ZeroDivisionException)
	Return the Fu and Li F^* test (Fu & Li 1993, Genetics, 133 pp693-709).
static PolymorphismSequenceContainer *	generateLDContainer (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.)
	generate a special PolymorphismSequenceContainer for linkage disequilbrium analysis
static Vdouble	pairwiseDistances1 (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give the vector of the pairwise distances between site positions corresponding to a LD SequencePolymorphismContainer
static Vdouble	pairwiseDistances2 (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give the vector of all mean pairwise distance between two sites to a LD SequencePolymorphismContainer
static Vdouble	pairwiseD (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give the vector of all mean pairwise D value between two sites (Lewontin & Kojima 1964, Evolution 14 pp458-472)
static Vdouble	pairwiseDprime (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give the vector of all mean pairwise D' value between two sites (Lewontin 1964, Genetics 49 pp49-67))
static Vdouble	pairwiseR2 (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give the vector of all mean pairwise R² value between two sites (Hill & Robertson 1968, Theor. Appl. Genet., 38 pp226-231)
static double	meanD (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give mean D over all pairwise comparisons
static double	meanDprime (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give mean D' over all pairwise comparisons
static double	meanR2 (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give mean R² over all pairwise comparisons
static double	meanDistance1 (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give mean pairwise distances between sites / method 1: differences between sequences are not taken into account
static double	meanDistance2 (const PolymorphismSequenceContainer &psc, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give mean pairwise distances between sites / method 2: differences between sequences are taken into account
static double	originRegressionD (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give the slope of the regression \|D\| = 1+a*distance
static double	originRegressionDprime (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give the slope of the regression \|D'\| = 1+a*distance
static double	originRegressionR2 (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give the slope of the regression R² = 1+a*distance
static Vdouble	linearRegressionD (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give the slope and the origin of the regression \|D\| = a*distance+b
static Vdouble	linearRegressionDprime (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give the slope and the origin of the regression \|D'\| = a*distance+b
static Vdouble	linearRegressionR2 (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give the slope and the origin of the regression R² = a*distance+b
static double	inverseRegressionR2 (const PolymorphismSequenceContainer &psc, bool distance1=false, bool keepsingleton=true, double freqmin=0.) throw (DimensionException)
	give the slope of the regression R² = 1/(1+a*distance)
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)
static void	testUsefullValues (std::ostream &s, size_t n)
	Test usefull values.
Static Private Member Functions
static size_t	getMutationNumber_ (const Site &site)
	Count the number of mutation for a site.
static size_t	getSingletonNumber_ (const Site &site)
	Count the number of singleton for a site.
static size_t	getDerivedSingletonNumber_ (const Site &site_in, const Site &site_out)
	Count the number of singleton for a site.
static std::map< std::string, double >	getUsefullValues_ (size_t n)
	Get usefull values for theta estimators.
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)
static double	getUD_ (double a1, double vD)
	Get the uD value of equation (32) in Fu & Li 1993, Genetics, 133 pp693-709)
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)
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)
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
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

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

size_t SequenceStatistics::countSingleton	(	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 114 of file SequenceStatistics.cpp.

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

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 426 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences(), bpp::PolymorphismSequenceContainer::getSequenceCount(), and bpp::VectorSiteContainer::toString().

size_t 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 on string

Definition at line 387 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences(), and bpp::VectorSiteContainer::toString().

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 340 of file SequenceStatistics.cpp.

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

vector< size_t > 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 751 of file SequenceStatistics.cpp.

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

double SequenceStatistics::FstHudson92	(	const PolymorphismSequenceContainer &	psc,
		size_t	id1,
		size_t	id2
	)

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 $H_w$ is mean number of differences between different sequences sampled from the same subpopulation, and $H_b$ 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 944 of file SequenceStatistics.cpp.

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

double SequenceStatistics::fuliD	(	const PolymorphismSequenceContainer &	ingroup,
		const PolymorphismSequenceContainer &	outgroup,
		bool	original = `true`
	)		throw (ZeroDivisionException) `[static]`

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

Parameters:

ingroup	a PolymorphismSequenceContainer
outgroup	a PolymorphismSequenceContainer
original	true: use the Fu & Li methode, false: use mutations in external branch.

Exceptions:

ZeroDivisionException if eta == 0

Author:: Sylvain Gaillard; Khalid Belkhir

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 864 of file SequenceStatistics.cpp.

double SequenceStatistics::fuliDstar ( const PolymorphismSequenceContainer & group ) throw (ZeroDivisionException) [static]

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

Parameters:

group a PolymorphismSequenceContainer

Author:: Sylvain Gaillard

Definition at line 881 of file SequenceStatistics.cpp.

double SequenceStatistics::fuliF	(	const PolymorphismSequenceContainer &	ingroup,
		const PolymorphismSequenceContainer &	outgroup,
		bool	original = `true`
	)		throw (ZeroDivisionException) `[static]`

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

Parameters:

ingroup	a PolymorphismSequenceContainer
outgroup	a PolymorphismSequenceContainer
original	true: use the Fu & Li methode, false: use mutations in external branch.

Author:: Sylvain Gaillard; Khalid Belkhir

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 903 of file SequenceStatistics.cpp.

double SequenceStatistics::fuliFstar ( const PolymorphismSequenceContainer & group ) throw (ZeroDivisionException) [static]

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

Parameters:

group a PolymorphismSequenceContainer

Author:: Sylvain Gaillard

Definition at line 922 of file SequenceStatistics.cpp.

double SequenceStatistics::gcContent ( const PolymorphismSequenceContainer & psc ) [static]

Compute the mean GC content in an alignment.

Parameters:

psc	a PolymorphismSequenceContainer

Definition at line 239 of file SequenceStatistics.cpp.

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

std::vector< size_t > 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 247 of file SequenceStatistics.cpp.

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

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 987 of file SequenceStatistics.cpp.

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

size_t SequenceStatistics::getDerivedSingletonNumber_	(	const Site &	site_in,
		const Site &	site_out
	)		`[static, private]`

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 1608 of file SequenceStatistics.cpp.

size_t SequenceStatistics::getMutationNumber_ ( const Site & site ) [static, private]

Count the number of mutation for a site.

Definition at line 1579 of file SequenceStatistics.cpp.

size_t SequenceStatistics::getNumberOfTransitions ( const PolymorphismSequenceContainer & psc ) [static]

Return the number of transitions.

Parameters:

psc	a PolymorphismSequenceContainer

Author:: Éric Bazin

Definition at line 474 of file SequenceStatistics.cpp.

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

size_t SequenceStatistics::getNumberOfTransversions ( const PolymorphismSequenceContainer & psc ) [static]

Return the number of transversions.

Parameters:

psc	a PolymorphismSequenceContainer

Author:: Éric Bazin

Definition at line 506 of file SequenceStatistics.cpp.

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

size_t SequenceStatistics::getSingletonNumber_ ( const Site & site ) [static, private]

Count the number of singleton for a site.

Definition at line 1595 of file SequenceStatistics.cpp.

double SequenceStatistics::getTransitionsTransversionsRatio ( const PolymorphismSequenceContainer & psc ) throw (Exception) [static]

Return the ratio of transitions/transversions.

Parameters:

psc	a PolymorphismSequenceContainer

Author:: Éric Bazin

Definition at line 538 of file SequenceStatistics.cpp.

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

double SequenceStatistics::getUD_	(	double	a1,
		double	vD
	)		`[static, private]`

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

Parameters:

a1	as describe in getUsefullValues
vD	as provided by getVD_

Returns:: the uD value as double

Author:: Sylvain Gaillard

Definition at line 1686 of file SequenceStatistics.cpp.

double SequenceStatistics::getUDstar_	(	size_t	n,
		double	a1,
		double	vDs
	)		`[static, private]`

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 getUsefullValues
vDs	as provided by getVDstar_

Returns:: the uD* value as double

Author:: Sylvain Gaillard

Definition at line 1719 of file SequenceStatistics.cpp.

std::map< std::string, double > SequenceStatistics::getUsefullValues_ ( size_t n ) [static, private]

Get usefull 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 1630 of file SequenceStatistics.cpp.

double SequenceStatistics::getVD_	(	size_t	n,
		double	a1,
		double	a2,
		double	cn
	)		`[static, private]`

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 getUsefullValues
a2	as describe in getUsefullValues
cn	as describe in getUsefullValues

Returns:: the vD value as double

Author:: Sylvain Gaillard

Definition at line 1677 of file SequenceStatistics.cpp.

double SequenceStatistics::getVDstar_	(	size_t	n,
		double	a1,
		double	a2,
		double	dn
	)		`[static, private]`

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 getUsefullValues
a2	as describe in getUsefullValues
dn	as describe in getUsefullValues

Returns:: the vD* value as double

Author:: Sylvain Gaillard

Definition at line 1691 of file SequenceStatistics.cpp.

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 198 of file SequenceStatistics.cpp.

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

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 1521 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

double SequenceStatistics::inverseRegressionR2	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1497 of file SequenceStatistics.cpp.

double SequenceStatistics::leftHandHudson_ ( const PolymorphismSequenceContainer & psc ) [static, private]

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 1734 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

Vdouble SequenceStatistics::linearRegressionD	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1434 of file SequenceStatistics.cpp.

Vdouble SequenceStatistics::linearRegressionDprime	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1455 of file SequenceStatistics.cpp.

Vdouble SequenceStatistics::linearRegressionR2	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1476 of file SequenceStatistics.cpp.

double SequenceStatistics::meanD	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1318 of file SequenceStatistics.cpp.

double SequenceStatistics::meanDistance1	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1350 of file SequenceStatistics.cpp.

double SequenceStatistics::meanDistance2	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1363 of file SequenceStatistics.cpp.

double SequenceStatistics::meanDprime	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1324 of file SequenceStatistics.cpp.

double SequenceStatistics::meanNonSynonymousSitesNumber	(	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 706 of file SequenceStatistics.cpp.

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

double SequenceStatistics::meanR2	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1337 of file SequenceStatistics.cpp.

double SequenceStatistics::meanSynonymousSitesNumber	(	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 692 of file SequenceStatistics.cpp.

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

vector< size_t > 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 779 of file SequenceStatistics.cpp.

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

size_t SequenceStatistics::monoSitePolymorphicCodonNumber	(	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 605 of file SequenceStatistics.cpp.

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

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 825 of file SequenceStatistics.cpp.

size_t SequenceStatistics::nonSynonymousSubstitutionsNumber	(	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 737 of file SequenceStatistics.cpp.

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

double SequenceStatistics::originRegressionD	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1380 of file SequenceStatistics.cpp.

double SequenceStatistics::originRegressionDprime	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1398 of file SequenceStatistics.cpp.

double SequenceStatistics::originRegressionR2	(	const PolymorphismSequenceContainer &	psc,
		bool	distance1 = `false`,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1416 of file SequenceStatistics.cpp.

Vdouble SequenceStatistics::pairwiseD	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1191 of file SequenceStatistics.cpp.

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

Vdouble SequenceStatistics::pairwiseDistances1	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1057 of file SequenceStatistics.cpp.

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

Vdouble SequenceStatistics::pairwiseDistances2	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1113 of file SequenceStatistics.cpp.

References bpp::Site::getAlphabet(), bpp::Alphabet::getSize(), and bpp::Sequence::getValue().

Vdouble SequenceStatistics::pairwiseDprime	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1224 of file SequenceStatistics.cpp.

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

Vdouble SequenceStatistics::pairwiseR2	(	const PolymorphismSequenceContainer &	psc,
		bool	keepsingleton = `true`,
		double	freqmin = `0.`
	)		throw (DimensionException) `[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 1280 of file SequenceStatistics.cpp.

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

size_t SequenceStatistics::parsimonyInformativeSiteNumber	(	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 93 of file SequenceStatistics.cpp.

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

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 678 of file SequenceStatistics.cpp.

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

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 664 of file SequenceStatistics.cpp.

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

size_t SequenceStatistics::polymorphicSiteNumber	(	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 $S$ .

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.

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

double SequenceStatistics::rightHandHudson_	(	double	c,
		size_t	n
	)		`[static, private]`

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 1760 of file SequenceStatistics.cpp.

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 216 of file SequenceStatistics.cpp.

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

size_t SequenceStatistics::stopCodonSiteNumber	(	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 579 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getAlphabet().

size_t SequenceStatistics::synonymousPolymorphicCodonNumber	(	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 629 of file SequenceStatistics.cpp.

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

size_t SequenceStatistics::synonymousSubstitutionsNumber	(	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 722 of file SequenceStatistics.cpp.

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

double SequenceStatistics::tajima83	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`
	)		`[static]`

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

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

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

Author:: Sylvain Gaillard

Definition at line 299 of file SequenceStatistics.cpp.

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

double SequenceStatistics::tajimaDSS	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`
	)		throw (ZeroDivisionException) `[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

Exceptions:

ZeroDivisionException if S == 0

Author:: Sylvain Gaillard

Definition at line 838 of file SequenceStatistics.cpp.

double SequenceStatistics::tajimaDTNM	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`
	)		throw (ZeroDivisionException) `[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

Exceptions:

ZeroDivisionException if eta == 0

Author:: Sylvain Gaillard

Definition at line 852 of file SequenceStatistics.cpp.

void SequenceStatistics::testUsefullValues	(	std::ostream &	s,
		size_t	n
	)		`[static]`

Test usefull values.

Parameters:

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

Author:: Sylvain Gaillard

Definition at line 1549 of file SequenceStatistics.cpp.

size_t SequenceStatistics::totMutationsExternalBranchs	(	const PolymorphismSequenceContainer &	ing,
		const PolymorphismSequenceContainer &	outg
	)		throw (Exception) `[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

Exceptions:

Exception if ing and outg are not of the same size (site number)

Author:: Khalid Belkhir

Definition at line 172 of file SequenceStatistics.cpp.

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

size_t SequenceStatistics::totNumberMutations	(	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 154 of file SequenceStatistics.cpp.

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

size_t SequenceStatistics::tripletNumber	(	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 132 of file SequenceStatistics.cpp.

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

double SequenceStatistics::watterson75	(	const PolymorphismSequenceContainer &	psc,
		bool	gapflag = `true`,
		bool	ignoreUnknown = `true`
	)		`[static]`

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

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

where $S$ is the number of polymorphic sites and $a_1$ is describe in SequenceStatistics::_getUsefullValues().

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

Author:: Sylvain Gaillard

Definition at line 289 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

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 654 of file SequenceStatistics.cpp.

References bpp::VectorSiteContainer::getNumberOfSequences().

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 644 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

Public Member Functions

Static Public Member Functions

Static Private Member Functions

Detailed Description

Member Function Documentation