Provide methods to compute substitution mappings. More...

#include <Bpp/Phyl/Mapping/SubstitutionMappingTools.h>

Public Member Functions
	SubstitutionMappingTools ()

virtual	~SubstitutionMappingTools ()

Static Public Member Functions

static std::unique_ptr< ProbabilisticSubstitutionMapping >	computeCounts (LikelihoodCalculationSingleProcess &rltc, SubstitutionCountInterface &substitutionCount, short unresolvedOption=UNRESOLVED_ZERO, double threshold=-1, bool verbose=true)
	Methods to compute mapping Trees. More...

static std::unique_ptr< ProbabilisticSubstitutionMapping >	computeCounts (LikelihoodCalculationSingleProcess &rltc, std::shared_ptr< const SubstitutionRegisterInterface > reg, std::shared_ptr< const AlphabetIndex2 > weights=0, std::shared_ptr< const AlphabetIndex2 > distances=0, short unresolvedOption=UNRESOLVED_ZERO, double threshold=-1, bool verbose=true)
	Compute the substitutions tree for a particular dataset. More...

static std::unique_ptr< ProbabilisticSubstitutionMapping >	computeCounts (LikelihoodCalculationSingleProcess &rltc, const std::vector< uint > &speciesIds, SubstitutionCountInterface &substitutionCount, short unresolvedOption=UNRESOLVED_ZERO, double threshold=-1, bool verbose=true)
	Compute the substitutions tree for a particular dataset. More...

static std::unique_ptr< ProbabilisticSubstitutionMapping >	computeCounts (LikelihoodCalculationSingleProcess &rltc, const std::vector< uint > &edgeIds, std::shared_ptr< const SubstitutionRegisterInterface > reg, std::shared_ptr< const AlphabetIndex2 > weights=0, std::shared_ptr< const AlphabetIndex2 > distances=0, short unresolvedOption=UNRESOLVED_ZERO, double threshold=-1, bool verbose=true)
	Compute the substitutions tree for a particular dataset. More...

static std::unique_ptr< ProbabilisticSubstitutionMapping >	computeNormalizations (LikelihoodCalculationSingleProcess &rltc, const std::vector< uint > &edgeIds, std::shared_ptr< const BranchedModelSet > nullModels, std::shared_ptr< const SubstitutionRegisterInterface > reg, std::shared_ptr< const AlphabetIndex2 > distances=0, short unresolvedOption=UNRESOLVED_ZERO, bool verbose=true)
	Compute the normalizations tree due to the models of "null" process on each branch, for each register. More...

static std::unique_ptr< ProbabilisticSubstitutionMapping >	computeNormalizations (LikelihoodCalculationSingleProcess &rltc, std::shared_ptr< const BranchedModelSet > nullModels, std::shared_ptr< const SubstitutionRegisterInterface > reg, std::shared_ptr< const AlphabetIndex2 > distances=0, short unresolvedOption=UNRESOLVED_ZERO, bool verbose=true)
	Compute the normalizations tree due to the models of "null" process on each branch, for each register. More...

static std::unique_ptr< ProbabilisticSubstitutionMapping >	computeNormalizedCounts (LikelihoodCalculationSingleProcess &rltc, const std::vector< uint > &edgeIds, std::shared_ptr< const BranchedModelSet > nullModels, std::shared_ptr< const SubstitutionRegisterInterface > reg, std::shared_ptr< const AlphabetIndex2 > weights=0, std::shared_ptr< const AlphabetIndex2 > distances=0, bool perTimeUnit=false, uint siteSize=1, short unresolvedOption=SubstitutionMappingTools::UNRESOLVED_ZERO, double threshold=-1, bool verbose=true)
	Compute the substitution counts tree, normalized by the models of "null" process on each branch, for each register. More...

static std::unique_ptr< ProbabilisticSubstitutionMapping >	computeNormalizedCounts (const ProbabilisticSubstitutionMapping &counts, const ProbabilisticSubstitutionMapping &factors, const std::vector< uint > &edgeIds, bool perTimeUnit=false, uint siteSize=1)

static std::unique_ptr< ProbabilisticSubstitutionMapping >	computeNormalizedCounts (LikelihoodCalculationSingleProcess &rltc, std::shared_ptr< const BranchedModelSet > nullModels, std::shared_ptr< const SubstitutionRegisterInterface > reg, std::shared_ptr< const AlphabetIndex2 > weights=0, std::shared_ptr< const AlphabetIndex2 > distances=0, bool perTimeUnit=false, uint siteSize=1, short unresolvedOption=SubstitutionMappingTools::UNRESOLVED_ZERO, double threshold=-1, bool verbose=true)

static std::unique_ptr< ProbabilisticSubstitutionMapping >	computeNormalizedCounts (const ProbabilisticSubstitutionMapping &counts, const ProbabilisticSubstitutionMapping &factors, bool perTimeUnit, uint siteSize=1)

static std::unique_ptr< ProbabilisticSubstitutionMapping >	computeOneJumpCounts (LikelihoodCalculationSingleProcess &rltc, bool verbose=true)
	This method computes for each site and for each branch the probability that at least one jump occurred. More...


static std::unique_ptr< PhyloTree >	getTreeForType (const ProbabilisticSubstitutionMapping &counts, size_t type)
	Methods to get trees of counts. These methods can use raw or normalized counting trees (ie computed with computeCounts and computeNormalizedCounts methods). More...

static std::unique_ptr< PhyloTree >	getTreeForType (const ProbabilisticSubstitutionMapping &counts, const ProbabilisticSubstitutionMapping &factors, size_t type)
	Sum all sites substitutions a given type. More...

static VVVdouble	getCountsPerSitePerBranchPerType (const ProbabilisticSubstitutionMapping &counts, const std::vector< uint > &ids=Vuint(0))
	Methods to get std::vectors of counts. More...

static Vdouble	getCountsForSitePerBranch (const ProbabilisticSubstitutionMapping &counts, size_t site)
	Sum all type of substitutions for each branch of a given position. More...

static Vdouble	getCountsForSitePerBranch (const ProbabilisticSubstitutionMapping &counts, const ProbabilisticSubstitutionMapping &factors, size_t site)

static VVdouble	getCountsPerSitePerBranch (const ProbabilisticSubstitutionMapping &counts, const std::vector< uint > &ids=Vuint(0))
	Sum all type of substitutions for each site for each branch. More...

static VVdouble	getCountsPerSitePerBranch (const ProbabilisticSubstitutionMapping &counts, const ProbabilisticSubstitutionMapping &factors, const std::vector< uint > &ids=Vuint(0))

static Vdouble	getCountsForBranchPerType (const ProbabilisticSubstitutionMapping &counts, uint branchId)
	Sum all sites substitutions for each type of a given branch. More...

static VVdouble	getCountsPerBranchPerType (const ProbabilisticSubstitutionMapping &counts, const std::vector< uint > &ids=Vuint(0))
	Sum all sites substitutions for each branch for each type. More...

static VVdouble	getCountsPerTypePerBranch (const ProbabilisticSubstitutionMapping &counts, const std::vector< uint > &ids=Vuint(0))

static VVdouble	computeCountsPerTypePerBranch (LikelihoodCalculationSingleProcess &rltc, const std::vector< uint > &ids, std::shared_ptr< const SubstitutionRegisterInterface > reg, std::shared_ptr< const AlphabetIndex2 > weights=0, std::shared_ptr< const AlphabetIndex2 > distances=0, short unresolvedOption=UNRESOLVED_ZERO, double threshold=-1, bool verbose=true)
	Compute the sum over all branches of the counts per type per branch. More...


static Vdouble	getCountsForSitePerType (const ProbabilisticSubstitutionMapping &counts, size_t site, const std::vector< uint > &ids=Vuint(0))
	Methods that sum on branches need raw mapping trees, or raw mapping trees and normalization trees (ie computed with computeCounts and computeNormalizations). More...

static Vdouble	getCountsForSitePerType (const ProbabilisticSubstitutionMapping &counts, const ProbabilisticSubstitutionMapping &factors, size_t site, bool perTimeUnit, uint siteSize=1)
	Sum and normalize all type of substitutions for each type of a given position on all nodes. More...

static Vdouble	getCountsForSitePerType (const ProbabilisticSubstitutionMapping &counts, const ProbabilisticSubstitutionMapping &factors, size_t site, const std::vector< uint > &ids, bool perTimeUnit, uint siteSize=1)
	Sum and normalize all type of substitutions for each type of a given position on a set of nodes. More...

static VVdouble	getCountsPerSitePerType (const ProbabilisticSubstitutionMapping &counts, const std::vector< uint > &ids=Vuint(0))
	Sum all type of substitutions for each site for each type. More...

static VVdouble	getCountsPerSitePerType (const ProbabilisticSubstitutionMapping &counts, const ProbabilisticSubstitutionMapping &factors, bool perTimeUnit, uint siteSize=1)
	Sum and normalize all type of substitutions for each site for each type on all nodes. More...

static VVdouble	getCountsPerSitePerType (const ProbabilisticSubstitutionMapping &counts, const ProbabilisticSubstitutionMapping &factors, const std::vector< uint > &ids, bool perTimeUnit, uint siteSize=1)
	Sum and normalize all type of substitutions for each site for each type on a set of nodes. More...

static double	getNormForSite (const ProbabilisticSubstitutionMapping &counts, size_t site)
	Compute the norm of a substitution std::vector for a given position. More...


static void	outputPerSitePerBranch (const std::string &filename, const std::vector< uint > &ids, const AlignmentDataInterface &sites, const VVdouble &counts)
	Outputs of counts. More...

static void	outputPerSitePerType (const std::string &filename, const SubstitutionRegisterInterface &reg, const AlignmentDataInterface &sites, const VVdouble &counts)
	Output Per Site Per Type in SGED format. More...

static void	outputPerType (const std::string &filename, const SubstitutionRegisterInterface &reg, const AlignmentDataInterface &sites, const VVdouble &counts)
	Output Per Type. More...

static void	outputPerSitePerBranchPerType (const std::string &filenamePrefix, const std::vector< uint > &ids, const SubstitutionRegisterInterface &reg, const AlignmentDataInterface &sites, const VVVdouble &counts)
	Output Per Site Per Branch Per Type, one SGED file per type. More...

static void	writeToStream (const ProbabilisticSubstitutionMapping &substitutions, const AlignmentDataInterface &sites, size_t type, std::ostream &out)
	Write the substitutions std::vectors to a stream. More...

static void	readFromStream (std::istream &in, ProbabilisticSubstitutionMapping &substitutions, size_t type)
	Read the substitutions std::vectors from a stream. More...

Static Public Attributes
static const short	UNRESOLVED_ZERO = 0
	Constants describing how unresolved characters are counted: More...

static const short	UNRESOLVED_AVERAGE = 2

static const short	UNRESOLVED_ONE = 1

Detailed Description

Provide methods to compute substitution mappings.

For now, only 4 methods are implemented, and provide probabilistic substitution mappings.

See: Dutheil J, Pupko T, Jean-Marie A, Galtier N. A model-based approach for detecting coevolving positions in a molecule. Mol Biol Evol. 2005 Sep;22(9):1919-28. Epub 2005 Jun 8.

Author: Julien Dutheil

Definition at line 32 of file SubstitutionMappingTools.h.

Constructor & Destructor Documentation

◆ SubstitutionMappingTools()

bpp::SubstitutionMappingTools::SubstitutionMappingTools ( )

inline

Definition at line 52 of file SubstitutionMappingTools.h.

◆ ~SubstitutionMappingTools()

virtual bpp::SubstitutionMappingTools::~SubstitutionMappingTools ( )

inlinevirtual

Definition at line 54 of file SubstitutionMappingTools.h.

Member Function Documentation

◆ computeCounts() [1/4]

unique_ptr< ProbabilisticSubstitutionMapping > SubstitutionMappingTools::computeCounts	(	LikelihoodCalculationSingleProcess &	rltc,
		const std::vector< uint > &	edgeIds,
		std::shared_ptr< const SubstitutionRegisterInterface >	reg,
		std::shared_ptr< const AlphabetIndex2 >	weights = `0`,
		std::shared_ptr< const AlphabetIndex2 >	distances = `0`,
		short	unresolvedOption = `UNRESOLVED_ZERO`,
		double	threshold = `-1`,
		bool	verbose = `true`
	)

static

Compute the substitutions tree for a particular dataset.

Parameters

rltc	A LikelihoodCalculationSingleProcess object.
edgeIds	The Ids of the nodes the substitutions are counted on. If empty, count substitutions on all nodes.
reg	The SubstitutionRegister to use.
weights	Pointer to AlphabetIndex2 for weights for all substitutions (default: null means no weight),
distances	Pointer to AlphabetIndex2 for distances for all substitutions (default: null means each distance = 1),
unresolvedOption	Describes how unresolved are managed (see above).
threshold	value above which counts are considered saturated (default: -1 means no threshold).
verbose	Print info to screen.

Returns: A tree <PhyloNode, PhyloBranchMapping>

Definition at line 28 of file SubstitutionMappingTools.cpp.

References bpp::LikelihoodCalculationSingleProcess::getNumberOfDistinctSites(), bpp::LikelihoodCalculationSingleProcess::getRootArrayPositions(), bpp::LikelihoodCalculation::isInitialized(), and bpp::LikelihoodCalculationSingleProcess::substitutionProcess().

◆ computeCounts() [2/4]

unique_ptr< ProbabilisticSubstitutionMapping > SubstitutionMappingTools::computeCounts	(	LikelihoodCalculationSingleProcess &	rltc,
		const std::vector< uint > &	speciesIds,
		SubstitutionCountInterface &	substitutionCount,
		short	unresolvedOption = `UNRESOLVED_ZERO`,
		double	threshold = `-1`,
		bool	verbose = `true`
	)

static

Compute the substitutions tree for a particular dataset.

Parameters

rltc	A LikelihoodCalculationSingleProcess object.
speciesIds	The Species Ids of the edges the substitutions are counted on.
substitutionCount	The SubstitutionCount to use.
unresolvedOption	Describes how unresolved are managed (see above).
threshold	value above which counts are considered saturated (default: -1 means no threshold).
verbose	Print info to screen.

Returns: A tree <PhyloNode, PhyloBranchMapping>

Definition at line 57 of file SubstitutionMappingTools.cpp.

◆ computeCounts() [3/4]

static std::unique_ptr<ProbabilisticSubstitutionMapping> bpp::SubstitutionMappingTools::computeCounts	(	LikelihoodCalculationSingleProcess &	rltc,
		std::shared_ptr< const SubstitutionRegisterInterface >	reg,
		std::shared_ptr< const AlphabetIndex2 >	weights = `0`,
		std::shared_ptr< const AlphabetIndex2 >	distances = `0`,
		short	unresolvedOption = `UNRESOLVED_ZERO`,
		double	threshold = `-1`,
		bool	verbose = `true`
	)

inlinestatic

Compute the substitutions tree for a particular dataset.

Parameters

rltc	A LikelihoodCalculationSingleProcess object.
reg	The SubstitutionRegister to use.
weights	Pointer to AlphabetIndex2 for weights for all substitutions (default: null means no weight),
distances	Pointer to AlphabetIndex2 for distances for all substitutions (default: null means each distance = 1),
unresolvedOption	Describes how unresolved are managed (see above).
threshold	value above which counts are considered saturated (default: -1 means no threshold).
verbose	Print info to screen.

Returns: A tree <PhyloNode, PhyloBranchMapping>

Definition at line 103 of file SubstitutionMappingTools.h.

References computeCounts(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), bpp::SubstitutionProcessInterface::parametrizablePhyloTree(), and bpp::LikelihoodCalculationSingleProcess::substitutionProcess().

◆ computeCounts() [4/4]

static std::unique_ptr<ProbabilisticSubstitutionMapping> bpp::SubstitutionMappingTools::computeCounts	(	LikelihoodCalculationSingleProcess &	rltc,
		SubstitutionCountInterface &	substitutionCount,
		short	unresolvedOption = `UNRESOLVED_ZERO`,
		double	threshold = `-1`,
		bool	verbose = `true`
	)

inlinestatic

Methods to compute mapping Trees.

Compute the substitutions tree for a particular dataset

Parameters

rltc	A LikelihoodCalculationSingleProcess object.
substitutionCount	The SubstitutionCount to use.
unresolvedOption	Describes how unresolved are managed (see above).
threshold	value above which counts are considered saturated (default: -1 means no threshold).
verbose	Print info to screen.

Returns: A tree <PhyloNode, PhyloBranchMapping>

Definition at line 74 of file SubstitutionMappingTools.h.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), bpp::SubstitutionProcessInterface::parametrizablePhyloTree(), and bpp::LikelihoodCalculationSingleProcess::substitutionProcess().

Referenced by computeCounts(), bpp::SingleProcessSubstitutionMapping::computeCounts(), bpp::OneProcessSequenceSubstitutionMapping::computeCounts(), and computeOneJumpCounts().

◆ computeCountsPerTypePerBranch()

VVdouble SubstitutionMappingTools::computeCountsPerTypePerBranch	(	LikelihoodCalculationSingleProcess &	rltc,
		const std::vector< uint > &	ids,
		std::shared_ptr< const SubstitutionRegisterInterface >	reg,
		std::shared_ptr< const AlphabetIndex2 >	weights = `0`,
		std::shared_ptr< const AlphabetIndex2 >	distances = `0`,
		short	unresolvedOption = `UNRESOLVED_ZERO`,
		double	threshold = `-1`,
		bool	verbose = `true`
	)

static

Compute the sum over all branches of the counts per type per branch.

Parameters

rltc	A LikelihoodCalculationSingleProcess object.
ids	The vector of numbers of the nodes of the tree
reg	the Substitution Register If the SubstitutionRegister is a non-stationary CategorySubstitutionRegister, a correction is made.
weights	Pointer to AlphabetIndex2 for weights for all substitutions (default: null means no weight),
distances	Pointer to AlphabetIndex2 for distances for all substitutions (default: null means each distance = 1),
unresolvedOption	Describes how unresolved are managed (see above).
threshold	value above which counts are considered saturated (default: -1 means no threshold).
verbose	Display progress messages.

Definition at line 975 of file SubstitutionMappingTools.cpp.

References bpp::VectorTools::sum().

◆ computeNormalizations() [1/2]

unique_ptr< ProbabilisticSubstitutionMapping > SubstitutionMappingTools::computeNormalizations	(	LikelihoodCalculationSingleProcess &	rltc,
		const std::vector< uint > &	edgeIds,
		std::shared_ptr< const BranchedModelSet >	nullModels,
		std::shared_ptr< const SubstitutionRegisterInterface >	reg,
		std::shared_ptr< const AlphabetIndex2 >	distances = `0`,
		short	unresolvedOption = `UNRESOLVED_ZERO`,
		bool	verbose = `true`
	)

static

Compute the normalizations tree due to the models of "null" process on each branch, for each register.

Parameters

rltc	A LikelihoodCalculationSingleProcess object.
edgeIds	The Ids of the nodes the substitutions are counted on. If empty, count substitutions on all nodes.
nullModels	The "null" models used for normalization
reg	the Substitution Register
distances	Pointer to AlphabetIndex2 for distances for all substitutions (default: null means each distance = 1),
unresolvedOption	Describes how unresolved are managed (see above).
verbose	Display progress messages.

Returns: A tree <PhyloNode, PhyloBranchMapping> of normalization factors.

Definition at line 320 of file SubstitutionMappingTools.cpp.

Referenced by bpp::SingleProcessSubstitutionMapping::computeNormalizations(), bpp::OneProcessSequenceSubstitutionMapping::computeNormalizations(), and computeNormalizations().

◆ computeNormalizations() [2/2]

static std::unique_ptr<ProbabilisticSubstitutionMapping> bpp::SubstitutionMappingTools::computeNormalizations	(	LikelihoodCalculationSingleProcess &	rltc,
		std::shared_ptr< const BranchedModelSet >	nullModels,
		std::shared_ptr< const SubstitutionRegisterInterface >	reg,
		std::shared_ptr< const AlphabetIndex2 >	distances = `0`,
		short	unresolvedOption = `UNRESOLVED_ZERO`,
		bool	verbose = `true`
	)

inlinestatic

Compute the normalizations tree due to the models of "null" process on each branch, for each register.

Parameters

rltc	A LikelihoodCalculationSingleProcess object.
nullModels	The "null" models used for normalization
reg	the Substitution Register
distances	Pointer to AlphabetIndex2 for distances for all substitutions (default: null means each distance = 1),
unresolvedOption	Describes how unresolved are managed (see above).
verbose	Display progress messages.

Returns: A tree <PhyloNode, PhyloBranchMapping> of normalization factors.

Definition at line 211 of file SubstitutionMappingTools.h.

References computeNormalizations(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), bpp::SubstitutionProcessInterface::parametrizablePhyloTree(), and bpp::LikelihoodCalculationSingleProcess::substitutionProcess().

◆ computeNormalizedCounts() [1/4]

static std::unique_ptr<ProbabilisticSubstitutionMapping> bpp::SubstitutionMappingTools::computeNormalizedCounts	(	const ProbabilisticSubstitutionMapping &	counts,
		const ProbabilisticSubstitutionMapping &	factors,
		bool	perTimeUnit,
		uint	siteSize = `1`
	)

inlinestatic

Definition at line 290 of file SubstitutionMappingTools.h.

References computeNormalizedCounts(), and bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes().

◆ computeNormalizedCounts() [2/4]

unique_ptr< ProbabilisticSubstitutionMapping > SubstitutionMappingTools::computeNormalizedCounts	(	const ProbabilisticSubstitutionMapping &	counts,
		const ProbabilisticSubstitutionMapping &	factors,
		const std::vector< uint > &	edgeIds,
		bool	perTimeUnit = `false`,
		uint	siteSize = `1`
	)

static

Definition at line 650 of file SubstitutionMappingTools.cpp.

References bpp::ProbabilisticSubstitutionMapping::clone(), bpp::VectorTools::contains(), bpp::VectorTools::fill(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getEdge(), bpp::ProbabilisticSubstitutionMapping::getNumberOfDistinctSites(), and bpp::AbstractSubstitutionMapping::getNumberOfSubstitutionTypes().

◆ computeNormalizedCounts() [3/4]

unique_ptr< ProbabilisticSubstitutionMapping > SubstitutionMappingTools::computeNormalizedCounts	(	LikelihoodCalculationSingleProcess &	rltc,
		const std::vector< uint > &	edgeIds,
		std::shared_ptr< const BranchedModelSet >	nullModels,
		std::shared_ptr< const SubstitutionRegisterInterface >	reg,
		std::shared_ptr< const AlphabetIndex2 >	weights = `0`,
		std::shared_ptr< const AlphabetIndex2 >	distances = `0`,
		bool	perTimeUnit = `false`,
		uint	siteSize = `1`,
		short	unresolvedOption = `SubstitutionMappingTools::UNRESOLVED_ZERO`,
		double	threshold = `-1`,
		bool	verbose = `true`
	)

static

Compute the substitution counts tree, normalized by the models of "null" process on each branch, for each register.

Parameters

rltc	A LikelihoodCalculationSingleProcess object.
edgeIds	The Ids of the nodes the substitutions are counted on. If empty, count substitutions on all nodes.
nullModels	The "null" models used for normalization
reg	the Substitution Register
weights	Pointer to AlphabetIndex2 for weights for all substitutions (default: null means no weight),
distances	Pointer to AlphabetIndex2 for distances for all substitutions (default: null means each distance = 1),
perTimeUnit	If true, normalized counts are per unit of time (otherwise they are multiplied by the length of the branches) (default: false).
siteSize	The length of a site, as considered as a counting unit (default = 1)
unresolvedOption	Describes how unresolved are managed (see above).
threshold	value above which non-normalized counts are considered saturated (default: -1 means no threshold).
verbose	Display progress messages.

Returns: A tree <PhyloNode, PhyloBranchMapping> of normalized counts..

Definition at line 630 of file SubstitutionMappingTools.cpp.

Referenced by computeNormalizedCounts().

◆ computeNormalizedCounts() [4/4]

static std::unique_ptr<ProbabilisticSubstitutionMapping> bpp::SubstitutionMappingTools::computeNormalizedCounts	(	LikelihoodCalculationSingleProcess &	rltc,
		std::shared_ptr< const BranchedModelSet >	nullModels,
		std::shared_ptr< const SubstitutionRegisterInterface >	reg,
		std::shared_ptr< const AlphabetIndex2 >	weights = `0`,
		std::shared_ptr< const AlphabetIndex2 >	distances = `0`,
		bool	perTimeUnit = `false`,
		uint	siteSize = `1`,
		short	unresolvedOption = `SubstitutionMappingTools::UNRESOLVED_ZERO`,
		double	threshold = `-1`,
		bool	verbose = `true`
	)

inlinestatic

Definition at line 274 of file SubstitutionMappingTools.h.

References computeNormalizedCounts(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), bpp::SubstitutionProcessInterface::parametrizablePhyloTree(), and bpp::LikelihoodCalculationSingleProcess::substitutionProcess().

◆ computeOneJumpCounts()

static std::unique_ptr<ProbabilisticSubstitutionMapping> bpp::SubstitutionMappingTools::computeOneJumpCounts	(	LikelihoodCalculationSingleProcess &	rltc,
		bool	verbose = `true`
	)

inlinestatic

This method computes for each site and for each branch the probability that at least one jump occurred.

Here 'jump' refer to a change in the model state. Depending on the model, this might not be the same as a substitution (an alphabet state change).

Definition at line 309 of file SubstitutionMappingTools.h.

References computeCounts(), and bpp::LikelihoodCalculationSingleProcess::getStateMap().

◆ getCountsForBranchPerType()

Vdouble SubstitutionMappingTools::getCountsForBranchPerType	(	const ProbabilisticSubstitutionMapping &	counts,
		uint	branchId
	)

static

Sum all sites substitutions for each type of a given branch.

Parameters

counts	The substitution map to use.
branchId	The id of the branch of the substitution tree for which the counts should be computed.

Returns: A std::vector will all counts summed for each type of substitutions.

Definition at line 908 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::getEdge(), bpp::AbstractMapping::getNumberOfSites(), bpp::AbstractSubstitutionMapping::getNumberOfSubstitutionTypes(), and bpp::ProbabilisticSubstitutionMapping::getSiteIndex().

Referenced by getCountsPerBranchPerType(), and getCountsPerTypePerBranch().

◆ getCountsForSitePerBranch() [1/2]

Vdouble SubstitutionMappingTools::getCountsForSitePerBranch	(	const ProbabilisticSubstitutionMapping &	counts,
		const ProbabilisticSubstitutionMapping &	factors,
		size_t	site
	)

static

Definition at line 830 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::allEdgesIterator(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getEdge(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getEdgeIndex(), bpp::ProbabilisticSubstitutionMapping::getNumberOfBranches(), bpp::ProbabilisticSubstitutionMapping::getSiteIndex(), and bpp::VectorTools::sum().

◆ getCountsForSitePerBranch() [2/2]

Vdouble SubstitutionMappingTools::getCountsForSitePerBranch	(	const ProbabilisticSubstitutionMapping &	counts,
		size_t	site
	)

static

Sum all type of substitutions for each branch of a given position.

Parameters

counts	The substitution map to use.
site	The site for which the counts should be computed.

Returns: A std::vector will all counts for all types of substitutions summed.

Definition at line 814 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::allEdgesIterator(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getEdgeIndex(), bpp::ProbabilisticSubstitutionMapping::getNumberOfBranches(), bpp::ProbabilisticSubstitutionMapping::getSiteIndex(), and bpp::VectorTools::sum().

Referenced by getCountsPerSitePerBranch().

◆ getCountsForSitePerType() [1/3]

Vdouble SubstitutionMappingTools::getCountsForSitePerType	(	const ProbabilisticSubstitutionMapping &	counts,
		const ProbabilisticSubstitutionMapping &	factors,
		size_t	site,
		bool	perTimeUnit,
		uint	siteSize = `1`
	)

static

Sum and normalize all type of substitutions for each type of a given position on all nodes.

Parameters

counts	The substitution map to use.
factors	The substitution normalization to use.
site	The site for which the counts should be computed.
perTimeUnit	If true, normalized counts are per unit of time (otherwise they are multiplied by the length of the branches).
siteSize	The length of a site, as considered as a counting unit (default = 1)

Returns: A std::vector will all counts for all types of substitutions summed.

Definition at line 1050 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::allEdgesIterator(), bpp::AbstractSubstitutionMapping::getNumberOfSubstitutionTypes(), and bpp::ProbabilisticSubstitutionMapping::getSiteIndex().

◆ getCountsForSitePerType() [2/3]

Vdouble SubstitutionMappingTools::getCountsForSitePerType	(	const ProbabilisticSubstitutionMapping &	counts,
		const ProbabilisticSubstitutionMapping &	factors,
		size_t	site,
		const std::vector< uint > &	ids,
		bool	perTimeUnit,
		uint	siteSize = `1`
	)

static

Sum and normalize all type of substitutions for each type of a given position on a set of nodes.

Parameters

counts	The substitution map to use.
factors	The substitution normalization to use.
site	The site for which the counts should be computed.
ids	The ids of the branches where the the substitutions are counted (default : all ids)
perTimeUnit	If true, normalized counts are per unit of time (otherwise they are multiplied by the length of the branches).
siteSize	The length of a site, as considered as a counting unit (default = 1)

Returns: A std::vector will all counts for all types of substitutions summed.

Definition at line 1096 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getEdge(), bpp::AbstractSubstitutionMapping::getNumberOfSubstitutionTypes(), and bpp::ProbabilisticSubstitutionMapping::getSiteIndex().

◆ getCountsForSitePerType() [3/3]

Vdouble SubstitutionMappingTools::getCountsForSitePerType	(	const ProbabilisticSubstitutionMapping &	counts,
		size_t	site,
		const std::vector< uint > &	ids = `Vuint(0)`
	)

static

Methods that sum on branches need raw mapping trees, or raw mapping trees and normalization trees (ie computed with computeCounts and computeNormalizations).

Sum all type of substitutions for each type of a given position.

Parameters

counts	The substitution map to use.
site	The site for which the counts should be computed.
ids	The ids of the branches where the the substitutions are counted (default : all ids)

Returns: A std::vector will all counts for all types of substitutions summed.

Definition at line 1027 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getEdge(), bpp::AbstractSubstitutionMapping::getNumberOfSubstitutionTypes(), and bpp::ProbabilisticSubstitutionMapping::getSiteIndex().

Referenced by getCountsPerSitePerType().

◆ getCountsPerBranchPerType()

VVdouble SubstitutionMappingTools::getCountsPerBranchPerType	(	const ProbabilisticSubstitutionMapping &	counts,
		const std::vector< uint > &	ids = `Vuint(0)`
	)

static

Sum all sites substitutions for each branch for each type.

Parameters

counts	The substitution map to use.
ids	The ids of the branches where the the substitutions are counted (default : all ids)

Returns: A std::vector will all counts for all branches for all types of substitutions summed.

Definition at line 930 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), and getCountsForBranchPerType().

◆ getCountsPerSitePerBranch() [1/2]

VVdouble SubstitutionMappingTools::getCountsPerSitePerBranch	(	const ProbabilisticSubstitutionMapping &	counts,
		const ProbabilisticSubstitutionMapping &	factors,
		const std::vector< uint > &	ids = `Vuint(0)`
	)

static

Definition at line 880 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), getCountsForSitePerBranch(), bpp::AbstractMapping::getNumberOfSites(), and bpp::VectorTools::resize2().

◆ getCountsPerSitePerBranch() [2/2]

VVdouble SubstitutionMappingTools::getCountsPerSitePerBranch	(	const ProbabilisticSubstitutionMapping &	counts,
		const std::vector< uint > &	ids = `Vuint(0)`
	)

static

Sum all type of substitutions for each site for each branch.

Parameters

counts	The substitution map to use.
ids	The ids of the branches where the the substitutions are counted (default : all ids)

Returns: A std::vector will all counts for all types of substitutions summed.

Definition at line 855 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), getCountsForSitePerBranch(), bpp::AbstractMapping::getNumberOfSites(), and bpp::VectorTools::resize2().

◆ getCountsPerSitePerBranchPerType()

VVVdouble SubstitutionMappingTools::getCountsPerSitePerBranchPerType	(	const ProbabilisticSubstitutionMapping &	counts,
		const std::vector< uint > &	ids = `Vuint(0)`
	)

static

Methods to get std::vectors of counts.

PER BRANCH methods can use raw or normalized counting trees (ie computed with computeCounts and computeNormalizedCounts methods).

Sum all type of substitutions for each site for each branch for each type.

Parameters

counts	The substitution map to use.
ids	The ids of the branches where the the substitutions are counted (default : all ids)

Returns: A std::vector will all counts for all types of substitutions.

Definition at line 778 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), bpp::AbstractMapping::getNumberOfSites(), bpp::AbstractSubstitutionMapping::getNumberOfSubstitutionTypes(), bpp::ProbabilisticSubstitutionMapping::getSiteIndex(), and bpp::VectorTools::resize3().

◆ getCountsPerSitePerType() [1/3]

VVdouble SubstitutionMappingTools::getCountsPerSitePerType	(	const ProbabilisticSubstitutionMapping &	counts,
		const ProbabilisticSubstitutionMapping &	factors,
		bool	perTimeUnit,
		uint	siteSize = `1`
	)

static

Sum and normalize all type of substitutions for each site for each type on all nodes.

Parameters

counts	The substitution map to use.
factors	The substitution normalization to use.
perTimeUnit	If true, normalized counts are per unit of time (otherwise they are multiplied by the length of the branches).
siteSize	The length of a site, as considered as a counting unit (default = 1)

Returns: A std::vector will all counts for all types of substitutions summed.

Definition at line 1145 of file SubstitutionMappingTools.cpp.

References getCountsForSitePerType(), bpp::AbstractMapping::getNumberOfSites(), bpp::AbstractSubstitutionMapping::getNumberOfSubstitutionTypes(), and bpp::VectorTools::resize2().

◆ getCountsPerSitePerType() [2/3]

VVdouble SubstitutionMappingTools::getCountsPerSitePerType	(	const ProbabilisticSubstitutionMapping &	counts,
		const ProbabilisticSubstitutionMapping &	factors,
		const std::vector< uint > &	ids,
		bool	perTimeUnit,
		uint	siteSize = `1`
	)

static

Sum and normalize all type of substitutions for each site for each type on a set of nodes.

Parameters

counts	The substitution map to use.
factors	The substitution normalization to use.
ids	The ids of the branches where the the substitutions are counted (default: all ids)
perTimeUnit	If true, normalized counts are per unit of time (otherwise they are multiplied by the length of the branches).
siteSize	The length of a site, as considered as a counting unit (default = 1)

Returns: A std::vector will all counts for all types of substitutions summed.

Definition at line 1185 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), getCountsForSitePerType(), bpp::AbstractMapping::getNumberOfSites(), bpp::AbstractSubstitutionMapping::getNumberOfSubstitutionTypes(), and bpp::VectorTools::resize2().

◆ getCountsPerSitePerType() [3/3]

VVdouble SubstitutionMappingTools::getCountsPerSitePerType	(	const ProbabilisticSubstitutionMapping &	counts,
		const std::vector< uint > &	ids = `Vuint(0)`
	)

static

Sum all type of substitutions for each site for each type.

Parameters

counts	The substitution map to use.
ids	The ids of the branches where the the substitutions are counted (default: all ids)

Returns: A std::vector will all counts for all types of substitutions summed.

Definition at line 1166 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), getCountsForSitePerType(), bpp::AbstractMapping::getNumberOfSites(), bpp::AbstractSubstitutionMapping::getNumberOfSubstitutionTypes(), and bpp::VectorTools::resize2().

◆ getCountsPerTypePerBranch()

VVdouble SubstitutionMappingTools::getCountsPerTypePerBranch	(	const ProbabilisticSubstitutionMapping &	counts,
		const std::vector< uint > &	ids = `Vuint(0)`
	)

static

Definition at line 947 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::getAllEdgesIndexes(), getCountsForBranchPerType(), bpp::AbstractSubstitutionMapping::getNumberOfSubstitutionTypes(), and bpp::VectorTools::resize2().

◆ getNormForSite()

double SubstitutionMappingTools::getNormForSite	(	const ProbabilisticSubstitutionMapping &	counts,
		size_t	site
	)

static

Compute the norm of a substitution std::vector for a given position.

The norm is computed as: $N_i = \sqrt{\left(\sum_l {\left(\sum_t n_{l, i, t}\right)}^2\right)}$ , where $n_{l, i, t}$ is the number of substitutions of type t on site i on branch l, obtained using the () operator for the SubstitutionMapping object.

Parameters

counts	The substitution map to use.
site	The position for which the norm should be computed.

Returns: The norm of the substitution std::vector.

Definition at line 1209 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::allEdgesIterator(), bpp::AbstractSubstitutionMapping::getNumberOfSubstitutionTypes(), and bpp::ProbabilisticSubstitutionMapping::getSiteIndex().

◆ getTreeForType() [1/2]

unique_ptr< PhyloTree > SubstitutionMappingTools::getTreeForType	(	const ProbabilisticSubstitutionMapping &	counts,
		const ProbabilisticSubstitutionMapping &	factors,
		size_t	type
	)

static

Sum all sites substitutions a given type.

Parameters

counts	The substitution map to use.
factors	The substitution normalization to use.
type	The number of the type

Returns: A PhyloTree where branch lengths carry the branch counts.

Definition at line 744 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::allEdgesIterator(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getEdge(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getEdgeIndex(), bpp::AbstractMapping::getNumberOfSites(), and bpp::ProbabilisticSubstitutionMapping::getSiteIndex().

◆ getTreeForType() [2/2]

unique_ptr< PhyloTree > SubstitutionMappingTools::getTreeForType	(	const ProbabilisticSubstitutionMapping &	counts,
		size_t	type
	)

static

Methods to get trees of counts. These methods can use raw or normalized counting trees (ie computed with computeCounts and computeNormalizedCounts methods).

Sum all sites substitutions a given type.

Parameters

counts	The substitution map to use.
type	The number of the type

Returns: A PhyloTree where branch lengths carry the branch counts.

Definition at line 717 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::allEdgesIterator(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getEdgeIndex(), bpp::AbstractMapping::getNumberOfSites(), and bpp::ProbabilisticSubstitutionMapping::getSiteIndex().

◆ outputPerSitePerBranch()

void SubstitutionMappingTools::outputPerSitePerBranch	(	const std::string &	filename,
		const std::vector< uint > &	ids,
		const AlignmentDataInterface &	sites,
		const VVdouble &	counts
	)

static

Outputs of counts.

Output Per Site Per Branch in SGED format.

Definition at line 1235 of file SubstitutionMappingTools.cpp.

References bpp::CoreSiteInterface::getCoordinate(), and bpp::TemplateAlignmentDataInterface< class >::site().

◆ outputPerSitePerBranchPerType()

void SubstitutionMappingTools::outputPerSitePerBranchPerType	(	const std::string &	filenamePrefix,
		const std::vector< uint > &	ids,
		const SubstitutionRegisterInterface &	reg,
		const AlignmentDataInterface &	sites,
		const VVVdouble &	counts
	)

static

Output Per Site Per Branch Per Type, one SGED file per type.

Definition at line 1342 of file SubstitutionMappingTools.cpp.

References bpp::ApplicationTools::displayResult(), bpp::CoreSiteInterface::getCoordinate(), bpp::SubstitutionRegisterInterface::getTypeName(), bpp::TemplateAlignmentDataInterface< class >::site(), and bpp::TextTools::toString().

◆ outputPerSitePerType()

void SubstitutionMappingTools::outputPerSitePerType	(	const std::string &	filename,
		const SubstitutionRegisterInterface &	reg,
		const AlignmentDataInterface &	sites,
		const VVdouble &	counts
	)

static

Output Per Site Per Type in SGED format.

Definition at line 1273 of file SubstitutionMappingTools.cpp.

References bpp::CoreSiteInterface::getCoordinate(), bpp::SubstitutionRegisterInterface::getTypeName(), and bpp::TemplateAlignmentDataInterface< class >::site().

◆ outputPerType()

void SubstitutionMappingTools::outputPerType	(	const std::string &	filename,
		const SubstitutionRegisterInterface &	reg,
		const AlignmentDataInterface &	sites,
		const VVdouble &	counts
	)

static

Output Per Type.

Definition at line 1310 of file SubstitutionMappingTools.cpp.

References bpp::SubstitutionRegisterInterface::getTypeName().

◆ readFromStream()

void SubstitutionMappingTools::readFromStream	(	std::istream &	in,
		ProbabilisticSubstitutionMapping &	substitutions,
		size_t	type
	)

static

Read the substitutions std::vectors from a stream.

Parameters

in	The input stream where to read the std::vectors.
substitutions	The mapping object to fill.
type	The type of substitutions that are read. Should be in supported by the substitution count object associated to the mapping, if any.

Exceptions

IOException If an input error happens.

Definition at line 1432 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::allEdgesIterator(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getEdgeIndex(), bpp::DataTable::read(), bpp::ProbabilisticSubstitutionMapping::setNumberOfSites(), bpp::AbstractMapping::setSitePosition(), bpp::TextTools::toDouble(), and bpp::Exception::what().

◆ writeToStream()

void SubstitutionMappingTools::writeToStream	(	const ProbabilisticSubstitutionMapping &	substitutions,
		const AlignmentDataInterface &	sites,
		size_t	type,
		std::ostream &	out
	)

static

Write the substitutions std::vectors to a stream.

Parameters

substitutions	The substitutions std::vectors to write.
sites	The dataset associated to the std::vectors (needed to know the position of each site in the dataset).
type	The type of substitutions to be output. See SubstitutionCount class. Only one type of substitution can be output at a time.
out	The output stream where to write the std::vectors.

Exceptions

IOException If an output error happens.

Definition at line 1397 of file SubstitutionMappingTools.cpp.

References bpp::AssociationTreeGraphImplObserver< class, class, class >::allEdgesIterator(), bpp::CoreSiteInterface::getCoordinate(), bpp::AssociationTreeGraphImplObserver< class, class, class >::getEdgeIndex(), bpp::AbstractMapping::getNumberOfSites(), bpp::ProbabilisticSubstitutionMapping::getSiteIndex(), and bpp::TemplateAlignmentDataInterface< class >::site().

Member Data Documentation

◆ UNRESOLVED_AVERAGE

const short bpp::SubstitutionMappingTools::UNRESOLVED_AVERAGE = 2

static

Definition at line 48 of file SubstitutionMappingTools.h.

Referenced by computeCounts(), computeNormalizations(), and bpp::RewardMappingTools::computeRewardVectors().

◆ UNRESOLVED_ONE

const short bpp::SubstitutionMappingTools::UNRESOLVED_ONE = 1

static

Definition at line 49 of file SubstitutionMappingTools.h.

◆ UNRESOLVED_ZERO

const short bpp::SubstitutionMappingTools::UNRESOLVED_ZERO = 0

static

Constants describing how unresolved characters are counted:

UNRESOLVED_ZERO: Considered as gaps, so no counted (default). UNRESOLVED_AVERAGE: Considered as unresolved, so all matching states share a uniform probability in conditioned likelihood vector. UNRESOLVED_ONE: Considered as whateverunresolved, so all matching states have probability 1 in conditioned likelihood vector.

Definition at line 47 of file SubstitutionMappingTools.h.

Referenced by computeCounts(), computeNormalizations(), and bpp::RewardMappingTools::computeRewardVectors().

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

Bpp/Phyl/Mapping/SubstitutionMappingTools.h
Bpp/Phyl/Mapping/SubstitutionMappingTools.cpp

Public Member Functions

Static Public Member Functions

Static Public Attributes

Detailed Description

Constructor & Destructor Documentation

◆ SubstitutionMappingTools()

◆ ~SubstitutionMappingTools()

Member Function Documentation

◆ computeCounts() [1/4]

◆ computeCounts() [2/4]

◆ computeCounts() [3/4]

◆ computeCounts() [4/4]

◆ computeCountsPerTypePerBranch()

◆ computeNormalizations() [1/2]

◆ computeNormalizations() [2/2]

◆ computeNormalizedCounts() [1/4]

◆ computeNormalizedCounts() [2/4]

◆ computeNormalizedCounts() [3/4]

◆ computeNormalizedCounts() [4/4]

◆ computeOneJumpCounts()

◆ getCountsForBranchPerType()

◆ getCountsForSitePerBranch() [1/2]

◆ getCountsForSitePerBranch() [2/2]

◆ getCountsForSitePerType() [1/3]

◆ getCountsForSitePerType() [2/3]

◆ getCountsForSitePerType() [3/3]

◆ getCountsPerBranchPerType()

◆ getCountsPerSitePerBranch() [1/2]

◆ getCountsPerSitePerBranch() [2/2]

◆ getCountsPerSitePerBranchPerType()

◆ getCountsPerSitePerType() [1/3]

◆ getCountsPerSitePerType() [2/3]

◆ getCountsPerSitePerType() [3/3]

◆ getCountsPerTypePerBranch()

◆ getNormForSite()

◆ getTreeForType() [1/2]

◆ getTreeForType() [2/2]

◆ outputPerSitePerBranch()

◆ outputPerSitePerBranchPerType()

◆ outputPerSitePerType()

◆ outputPerType()

◆ readFromStream()

◆ writeToStream()

Member Data Documentation

◆ UNRESOLVED_AVERAGE

◆ UNRESOLVED_ONE

◆ UNRESOLVED_ZERO