de.jstacs.sequenceScores.statisticalModels.differentiable.mixture

Class MixtureDiffSM

java.lang.Object

de.jstacs.sequenceScores.differentiable.AbstractDifferentiableSequenceScore

de.jstacs.sequenceScores.statisticalModels.differentiable.AbstractDifferentiableStatisticalModel

de.jstacs.sequenceScores.statisticalModels.differentiable.mixture.AbstractMixtureDiffSM

de.jstacs.sequenceScores.statisticalModels.differentiable.mixture.MixtureDiffSM

All Implemented Interfaces:

MotifDiscoverer, MutableMotifDiscoverer, DifferentiableSequenceScore, SequenceScore, DifferentiableStatisticalModel, SamplingDifferentiableStatisticalModel, StatisticalModel, Storable, Cloneable

Direct Known Subclasses:

VariableLengthMixtureDiffSM

public class MixtureDiffSM
extends AbstractMixtureDiffSM
implements MutableMotifDiscoverer

This class implements a real mixture model.

Author:

Jens Keilwagen

Nested Class Summary

Nested classes/interfaces inherited from interface de.jstacs.motifDiscovery.MotifDiscoverer

MotifDiscoverer.KindOfProfile

Field Summary

Fields inherited from class de.jstacs.sequenceScores.statisticalModels.differentiable.mixture.AbstractMixtureDiffSM

componentScore, dList, freeParams, function, hiddenParameter, hiddenPotential, iList, logGammaSum, logHiddenNorm, logHiddenPotential, norm, optimizeHidden, paramRef, partNorm

Fields inherited from class de.jstacs.sequenceScores.differentiable.AbstractDifferentiableSequenceScore

alphabets, length, r

Fields inherited from interface de.jstacs.sequenceScores.differentiable.DifferentiableSequenceScore

UNKNOWN

Constructor Summary

Constructors

Constructor and Description
MixtureDiffSM(int starts, boolean plugIn, DifferentiableStatisticalModel... component) This constructor creates a new MixtureDiffSM.
MixtureDiffSM(StringBuffer xml) This is the constructor for the interface Storable.

Method Summary

Modifier and Type	Method and Description
void	adjustHiddenParameters(int index, DataSet[] data, double[][] weights) Adjusts all hidden parameters including duration and mixture parameters according to the current values of the remaining parameters.
MixtureDiffSM	clone() Creates a clone (deep copy) of the current DifferentiableSequenceScore instance.
DataSet	emitDataSet(int numberOfSequences, int... seqLength) This method returns a DataSet object containing artificial sequence(s).
protected void	fillComponentScores(Sequence seq, int start) Fills the internal array AbstractMixtureDiffSM.componentScore with the logarithmic scores of the components given a Sequence.
double	getESS() Returns the equivalent sample size (ess) of this model, i.e.
int	getGlobalIndexOfMotifInComponent(int component, int motif) Returns the global index of the motif used in component.
double	getHyperparameterForHiddenParameter(int index) This method returns the hyperparameter for the hidden parameter with index index.
int	getIndexOfMaximalComponentFor(Sequence sequence) Returns the index of the component with the maximal score for the sequence sequence.
String	getInstanceName() Should return a short instance name such as iMM(0), BN(2), ...
protected double	getLogNormalizationConstantForComponent(int i) Computes the logarithm of the normalization constant for the component i.
double	getLogPartialNormalizationConstant(int parameterIndex) Returns the logarithm of the partial normalization constant for the parameter with index parameterIndex.
double	getLogScoreAndPartialDerivation(Sequence seq, int start, IntList indices, DoubleList partialDer) Returns the logarithmic score for a Sequence beginning at position start in the Sequence and fills lists with the indices and the partial derivations.
int	getMotifLength(int motif) This method returns the length of the motif with index motif .
int	getNumberOfMotifs() Returns the number of motifs for this MotifDiscoverer.
int	getNumberOfMotifsInComponent(int component) Returns the number of motifs that are used in the component component of this MotifDiscoverer.
double[]	getProfileOfScoresFor(int component, int motif, Sequence sequence, int startpos, MotifDiscoverer.KindOfProfile kind) Returns the profile of the scores for component component and motif motif at all possible start positions of the motif in the sequence sequence beginning at startpos.
double[]	getStrandProbabilitiesFor(int component, int motif, Sequence sequence, int startpos) This method returns the probabilities of the strand orientations for a given subsequence if it is considered as site of the motif model in a specific component.
void	initializeMotif(int motifIndex, DataSet data, double[] weights) This method allows to initialize the model of a motif manually using a weighted data set.
void	initializeMotifRandomly(int motif) This method initializes the motif with index motif randomly using for instance DifferentiableSequenceScore.initializeFunctionRandomly(boolean).
protected void	initializeUsingPlugIn(int index, boolean freeParams, DataSet[] data, double[][] weights) This method initializes the functions using the data in some way.
boolean	modifyMotif(int motifIndex, int offsetLeft, int offsetRight) Manually modifies the motif model with index motifIndex.
String	toString(NumberFormat nf) This method returns a String representation of the instance.

Methods inherited from class de.jstacs.sequenceScores.statisticalModels.differentiable.mixture.AbstractMixtureDiffSM

addGradientOfLogPriorTerm, cloneFunctions, computeHiddenParameter, computeLogGammaSum, determineIsNormalized, extractFurtherInformation, fromXML, getAPrioriMixtureProbabilities, getComponentScores, getCurrentParameterValues, getDifferentiableStatisticalModels, getFunction, getFunctions, getFurtherInformation, getIndexOfMaximalComponentFor, getIndices, getLogNormalizationConstant, getLogPriorTerm, getLogScoreFor, getNumberOfComponents, getNumberOfParameters, getNumberOfRecommendedStarts, getProbsForComponent, getSamplingGroups, getSizeOfEventSpaceForRandomVariablesOfParameter, getXMLTag, init, initializeFunction, initializeFunctionRandomly, initializeHiddenPotentialRandomly, initializeHiddenUniformly, initWithLength, isInitialized, isNormalized, precomputeNorm, setHiddenParameters, setParameters, setParametersForFunction, toXML

Methods inherited from class de.jstacs.sequenceScores.statisticalModels.differentiable.AbstractDifferentiableStatisticalModel

getInitialClassParam, getLogProbFor, getLogProbFor, getLogProbFor, getLogScoreFor, getLogScoreFor, getMaximalMarkovOrder, isNormalized

Methods inherited from class de.jstacs.sequenceScores.differentiable.AbstractDifferentiableSequenceScore

getAlphabetContainer, getCharacteristics, getLength, getLogScoreAndPartialDerivation, getLogScoreAndPartialDerivation, getLogScoreFor, getLogScoreFor, getNumberOfStarts, getNumericalCharacteristics, toString

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface de.jstacs.motifDiscovery.MotifDiscoverer

getNumberOfComponents

Methods inherited from interface de.jstacs.Storable

toXML

Methods inherited from interface de.jstacs.sequenceScores.differentiable.DifferentiableSequenceScore

getInitialClassParam, getLogScoreAndPartialDerivation, getLogScoreAndPartialDerivation

Methods inherited from interface de.jstacs.sequenceScores.statisticalModels.StatisticalModel

getLogProbFor, getLogProbFor, getLogProbFor, getMaximalMarkovOrder

Methods inherited from interface de.jstacs.sequenceScores.SequenceScore

getAlphabetContainer, getCharacteristics, getLength, getLogScoreFor, getLogScoreFor, getLogScoreFor, getLogScoreFor, getNumericalCharacteristics

Constructor Detail

MixtureDiffSM

public MixtureDiffSM(int starts,
                     boolean plugIn,
                     DifferentiableStatisticalModel... component)
              throws CloneNotSupportedException

This constructor creates a new MixtureDiffSM. The first component determines the length of the sequences that can be modeled.

Parameters:

starts - the number of starts that should be done in an optimization

plugIn - indicates whether the initial parameters for an optimization should be related to the data or randomly drawn

component - the DifferentiableStatisticalModels

Throws:

CloneNotSupportedException - if an element of component could not be cloned

MixtureDiffSM

public MixtureDiffSM(StringBuffer xml)
              throws NonParsableException

This is the constructor for the interface Storable. Creates a new MixtureDiffSM out of a StringBuffer.

Parameters:

xml - the XML representation as StringBuffer

Throws:

NonParsableException - if the XML representation could not be parsed

Method Detail

clone

public MixtureDiffSM clone()
                    throws CloneNotSupportedException

Description copied from interface: DifferentiableSequenceScore

Creates a clone (deep copy) of the current DifferentiableSequenceScore instance.

Specified by:

clone in interface MotifDiscoverer

Specified by:

clone in interface DifferentiableSequenceScore

Specified by:

clone in interface SequenceScore

Overrides:

clone in class AbstractMixtureDiffSM

Returns:

the cloned instance of the current DifferentiableSequenceScore

Throws:

CloneNotSupportedException - if something went wrong while cloning the DifferentiableSequenceScore

See Also:

Cloneable

getLogNormalizationConstantForComponent

protected double getLogNormalizationConstantForComponent(int i)

Description copied from class: AbstractMixtureDiffSM

Computes the logarithm of the normalization constant for the component i.

Specified by:

getLogNormalizationConstantForComponent in class AbstractMixtureDiffSM

Parameters:

i - the index of the component

Returns:

the logarithm of the normalization constant of the component

getLogPartialNormalizationConstant

public double getLogPartialNormalizationConstant(int parameterIndex)
                                          throws Exception

Description copied from interface: DifferentiableStatisticalModel

Returns the logarithm of the partial normalization constant for the parameter with index parameterIndex. This is the logarithm of the partial derivation of the normalization constant for the parameter with index parameterIndex,

.

Specified by:

getLogPartialNormalizationConstant in interface DifferentiableStatisticalModel

Parameters:

parameterIndex - the index of the parameter

Returns:

the logarithm of the partial normalization constant

Throws:

Exception - if something went wrong with the normalization

See Also:

DifferentiableStatisticalModel.getLogNormalizationConstant()

getHyperparameterForHiddenParameter

public double getHyperparameterForHiddenParameter(int index)

Description copied from class: AbstractMixtureDiffSM

This method returns the hyperparameter for the hidden parameter with index index.

Specified by:

getHyperparameterForHiddenParameter in class AbstractMixtureDiffSM

Parameters:

index - the index of the hidden parameter

Returns:

the hyperparameter for the hidden parameter

getESS

public double getESS()

Description copied from interface: DifferentiableStatisticalModel

Returns the equivalent sample size (ess) of this model, i.e. the equivalent sample size for the class or component that is represented by this model.

Specified by:

getESS in interface DifferentiableStatisticalModel

Returns:

the equivalent sample size.

initializeUsingPlugIn

protected void initializeUsingPlugIn(int index,
                                     boolean freeParams,
                                     DataSet[] data,
                                     double[][] weights)
                              throws Exception

Description copied from class: AbstractMixtureDiffSM

This method initializes the functions using the data in some way.

Specified by:

initializeUsingPlugIn in class AbstractMixtureDiffSM

Parameters:

index - the class index

freeParams - if true, the (reduced) parameterization is used

data - the data

weights - the weights for the data

Throws:

Exception - if the initialization could not be done

See Also:

DifferentiableSequenceScore.initializeFunction(int, boolean, DataSet[], double[][])

adjustHiddenParameters

public void adjustHiddenParameters(int index,
                                   DataSet[] data,
                                   double[][] weights)
                            throws Exception

Adjusts all hidden parameters including duration and mixture parameters according to the current values of the remaining parameters.

Specified by:

adjustHiddenParameters in interface MutableMotifDiscoverer

Parameters:

index - the index of the class of this instance

data - the array of data for all classes

weights - the weights for all sequences in data

Throws:

Exception - thrown if the hidden parameters could not be adjusted

getInstanceName

public String getInstanceName()

Description copied from interface: SequenceScore

Should return a short instance name such as iMM(0), BN(2), ...

Specified by:

getInstanceName in interface SequenceScore

Returns:

a short instance name

fillComponentScores

protected void fillComponentScores(Sequence seq,
                                   int start)

Description copied from class: AbstractMixtureDiffSM

Fills the internal array AbstractMixtureDiffSM.componentScore with the logarithmic scores of the components given a Sequence.

Specified by:

fillComponentScores in class AbstractMixtureDiffSM

Parameters:

seq - the sequence

start - the start position in seq

getLogScoreAndPartialDerivation

public double getLogScoreAndPartialDerivation(Sequence seq,
                                              int start,
                                              IntList indices,
                                              DoubleList partialDer)

Description copied from interface: DifferentiableSequenceScore

Returns the logarithmic score for a Sequence beginning at position start in the Sequence and fills lists with the indices and the partial derivations.

Specified by:

getLogScoreAndPartialDerivation in interface DifferentiableSequenceScore

Parameters:

seq - the Sequence

start - the start position in the Sequence

indices - an IntList of indices, after method invocation the list should contain the indices i where is not zero

partialDer - a DoubleList of partial derivations, after method invocation the list should contain the corresponding that are not zero

Returns:

the logarithmic score for the Sequence

toString

public String toString(NumberFormat nf)

Description copied from interface: SequenceScore

This method returns a String representation of the instance.

Specified by:

toString in interface SequenceScore

Parameters:

nf - the NumberFormat for the String representation of parameters or probabilities

Returns:

a String representation of the instance

initializeMotif

public void initializeMotif(int motifIndex,
                            DataSet data,
                            double[] weights)
                     throws Exception

Description copied from interface: MutableMotifDiscoverer

This method allows to initialize the model of a motif manually using a weighted data set.

Specified by:

initializeMotif in interface MutableMotifDiscoverer

Parameters:

motifIndex - the index of the motif in the motif discoverer

data - the data set of sequences

weights - either null or an array of length data.getNumberofElements() with non-negative weights.

Throws:

Exception - if initialize was not possible

initializeMotifRandomly

public void initializeMotifRandomly(int motif)
                             throws Exception

Description copied from interface: MutableMotifDiscoverer

This method initializes the motif with index motif randomly using for instance DifferentiableSequenceScore.initializeFunctionRandomly(boolean). Furthermore, if available, it also initializes the positional distribution.

Specified by:

initializeMotifRandomly in interface MutableMotifDiscoverer

Parameters:

motif - the index of the motif

Throws:

Exception - either if the index is wrong or if it is thrown by the method DifferentiableSequenceScore.initializeFunctionRandomly(boolean)

modifyMotif

public boolean modifyMotif(int motifIndex,
                           int offsetLeft,
                           int offsetRight)
                    throws Exception

Description copied from interface: MutableMotifDiscoverer

Manually modifies the motif model with index motifIndex. The two offsets offsetLeft and offsetRight define how many positions the left or right border positions shall be moved. Negative numbers indicate moves to the left while positive numbers correspond to moves to the right. The distribution for sequences to the left and right side of the motif shall be computed internally.

Specified by:

modifyMotif in interface MutableMotifDiscoverer

Parameters:

motifIndex - the index of the motif in the motif discoverer

offsetLeft - the offset on the left side

offsetRight - the offset on the right side

Returns:

true if the motif model was modified otherwise false

Throws:

Exception - if some unexpected error occurred during the modification

See Also:

MutableMotifDiscoverer.modifyMotif(int, int, int), Mutable.modify(int, int)

getGlobalIndexOfMotifInComponent

public int getGlobalIndexOfMotifInComponent(int component,
                                            int motif)

Description copied from interface: MotifDiscoverer

Returns the global index of the motif used in component. The index returned must be at least 0 and less than MotifDiscoverer.getNumberOfMotifs().

Specified by:

getGlobalIndexOfMotifInComponent in interface MotifDiscoverer

Parameters:

component - the component index

motif - the motif index in the component

Returns:

the global index of the motif in component

getIndexOfMaximalComponentFor

public int getIndexOfMaximalComponentFor(Sequence sequence)
                                  throws Exception

Description copied from interface: MotifDiscoverer

Returns the index of the component with the maximal score for the sequence sequence.

Specified by:

getIndexOfMaximalComponentFor in interface MotifDiscoverer

Parameters:

sequence - the given sequence

Returns:

the index of the component with the maximal score for the given sequence

Throws:

Exception - if the index could not be computed for any reasons

getMotifLength

public int getMotifLength(int motif)

Description copied from interface: MotifDiscoverer

This method returns the length of the motif with index motif .

Specified by:

getMotifLength in interface MotifDiscoverer

Parameters:

motif - the index of the motif

Returns:

the length of the motif with index motif

getNumberOfMotifs

public int getNumberOfMotifs()

Description copied from interface: MotifDiscoverer

Returns the number of motifs for this MotifDiscoverer.

Specified by:

getNumberOfMotifs in interface MotifDiscoverer

Returns:

the number of motifs

getNumberOfMotifsInComponent

public int getNumberOfMotifsInComponent(int component)

Description copied from interface: MotifDiscoverer

Returns the number of motifs that are used in the component component of this MotifDiscoverer.

Specified by:

getNumberOfMotifsInComponent in interface MotifDiscoverer

Parameters:

component - the component of the MotifDiscoverer

Returns:

the number of motifs

getProfileOfScoresFor

public double[] getProfileOfScoresFor(int component,
                                      int motif,
                                      Sequence sequence,
                                      int startpos,
                                      MotifDiscoverer.KindOfProfile kind)
                               throws Exception

Description copied from interface: MotifDiscoverer

Returns the profile of the scores for component component and motif motif at all possible start positions of the motif in the sequence sequence beginning at startpos. This array should be of length
sequence.length() - startpos - motifs[motif].getLength() + 1.
A high score should encode for a probable start position.

Specified by:

getProfileOfScoresFor in interface MotifDiscoverer

Parameters:

component - the component index

motif - the index of the motif in the component

sequence - the given sequence

startpos - the start position in the sequence

kind - indicates the kind of profile

Returns:

the profile of scores

Throws:

Exception - if the score could not be computed for any reasons

getStrandProbabilitiesFor

public double[] getStrandProbabilitiesFor(int component,
                                          int motif,
                                          Sequence sequence,
                                          int startpos)
                                   throws Exception

Description copied from interface: MotifDiscoverer

This method returns the probabilities of the strand orientations for a given subsequence if it is considered as site of the motif model in a specific component.

Specified by:

getStrandProbabilitiesFor in interface MotifDiscoverer

Parameters:

component - the component index

motif - the index of the motif in the component

sequence - the given sequence

startpos - the start position in the sequence

Returns:

the probabilities of the strand orientations

Throws:

Exception - if the strand could not be computed for any reasons

emitDataSet

public DataSet emitDataSet(int numberOfSequences,
                           int... seqLength)
                    throws NotTrainedException,
                           Exception

Description copied from interface: StatisticalModel

This method returns a DataSet object containing artificial sequence(s).

There are two different possibilities to create a data set for a model with length 0 (homogeneous models).

1. emitDataSet( int n, int l ) should return a data set with n sequences of length l.
2. emitDataSet( int n, int[] l ) should return a data set with n sequences which have a sequence length corresponding to the entry in the given array l.

There are two different possibilities to create a data set for a model with length greater than 0 (inhomogeneous models).
emitDataSet( int n ) and emitDataSet( int n, null ) should return a data set with n sequences of length of the model ( SequenceScore.getLength()).

The standard implementation throws an Exception.

Specified by:

emitDataSet in interface StatisticalModel

Overrides:

emitDataSet in class AbstractDifferentiableStatisticalModel

Parameters:

numberOfSequences - the number of sequences that should be contained in the returned data set

seqLength - the length of the sequences for a homogeneous model; for an inhomogeneous model this parameter should be null or an array of size 0.

Returns:

a DataSet containing the artificial sequence(s)

Throws:

NotTrainedException - if the model is not trained yet

Exception - if the emission did not succeed

See Also:

DataSet