de.jstacs.sequenceScores.statisticalModels.trainable.hmm.transitions.elements

Class DistanceBasedScaledTransitionElement

java.lang.Object

de.jstacs.sequenceScores.statisticalModels.trainable.hmm.transitions.BasicHigherOrderTransition.AbstractTransitionElement

de.jstacs.sequenceScores.statisticalModels.trainable.hmm.transitions.elements.BasicTransitionElement

de.jstacs.sequenceScores.statisticalModels.trainable.hmm.transitions.elements.ReferenceBasedTransitionElement

de.jstacs.sequenceScores.statisticalModels.trainable.hmm.transitions.elements.DistanceBasedScaledTransitionElement

All Implemented Interfaces:

Storable, Cloneable

public class DistanceBasedScaledTransitionElement
extends ReferenceBasedTransitionElement

Distance-based scaled transition element for an HMM with distance-scaled transition matrices (DSHMM).

Author:

Michael Seifert

Field Summary

Fields

Modifier and Type	Field and Description
protected String	arrowOptions The Graphviz options for drawing the arrows.
protected Hashtable<Sequence,double[]>	diagonalWeights Contains the single epsilons of the diagonal elements required for estimating the self-transition probability.
protected double	scalingFactor The maximal scaling factor.
protected double[]	statisticsTransitionProb Represents the summarized epsilons required for estimating the transition probabilities from the context.

Fields inherited from class de.jstacs.sequenceScores.statisticalModels.trainable.hmm.transitions.elements.ReferenceBasedTransitionElement

annotationID, diagElement, ess, probabilities

Fields inherited from class de.jstacs.sequenceScores.statisticalModels.trainable.hmm.transitions.BasicHigherOrderTransition.AbstractTransitionElement

context, descendants, hyperParameters, logNorm, parameters, states, statistic

Constructor Summary

Constructors

Constructor and Description
DistanceBasedScaledTransitionElement(int[] context, int[] states, double[] probabilities, double ess, double scalingFactor, String annotationID) Creates an object representing the transition probabilities of a Hidden Markov TrainableStatisticalModel with scaled transition matrices (SHMM) for the given context.
DistanceBasedScaledTransitionElement(int[] context, int[] states, double[] probabilities, double ess, double scalingFactor, String annotationID, double[] weight) Creates an object representing the transition probabilities of a Hidden Markov TrainableStatisticalModel with scaled transition matrices (SHMM) for the given context.
DistanceBasedScaledTransitionElement(StringBuffer xml) Extracts a distance-base scaled transition element from XML.

Method Summary

Methods

Modifier and Type	Method and Description
void	addToStatistic(int childIdx, double weight, Sequence sequence, int sequencePosition) This method adds a given weight to the sufficient statistic for the parameters.
protected void	appendFurtherInformation(StringBuffer xml) This method appends further information to the XML representation.
protected void	appendTransitions(StringBuffer res, String contextNodeRepresentation, NumberFormat nf, String arrowOption, boolean graphical) This method appends all edges of the transition element to a given Graphviz representation.
DistanceBasedScaledTransitionElement	clone() Clones the object.
void	estimateFromStatistic() This method estimates the parameters from the sufficient statistic.
protected void	extractFurtherInformation(StringBuffer xml) This method extracts further information from the XML representation.
protected double	getIndex(int pos, Sequence seq) Returns the distance integrated into the transition from pos - 1 to pos in sequences seq.
double	getLogScoreFor(int state, Sequence sequence, int sequencePosition) This method returns the score for the transition from the current context to the state with index index.
protected String	getXMLTag() This method returns the xml tag used in BasicHigherOrderTransition.AbstractTransitionElement.toXML().
protected void	init() Basic initialization.
void	resetStatistic() This method resets the sufficient statistic for the parameters.
String	toString(String[] stateNames) Returns a string representation of the transition probabilities.

Methods inherited from class de.jstacs.sequenceScores.statisticalModels.trainable.hmm.transitions.elements.ReferenceBasedTransitionElement

determineDiagonalElement, getLogGammaScoreFromStatistic, getLogPriorTerm, initializeRandomly, precompute

Methods inherited from class de.jstacs.sequenceScores.statisticalModels.trainable.hmm.transitions.BasicHigherOrderTransition.AbstractTransitionElement

appendGraphvizDescription, drawParametersFromStatistic, getArrowOption, getChild, getContext, getDescendant, getGraphvizEdgeWeight, getLabel, getLastContextState, getNextContext, getNumberOfChildren, getNumberOfParameters, joinStatistics, setIndexOfDescendantTransitionElement, setParameters, toString, toString, toXML

Methods inherited from class java.lang.Object

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

Field Detail

arrowOptions

protected String arrowOptions

The Graphviz options for drawing the arrows.

scalingFactor

protected double scalingFactor

The maximal scaling factor.

statisticsTransitionProb

protected double[] statisticsTransitionProb

Represents the summarized epsilons required for estimating the transition probabilities from the context.

• statisticsTransitionProb[j]: epsilon( context, states[j] )
• No pseudocounts included.

diagonalWeights

protected Hashtable<Sequence,double[]> diagonalWeights

Contains the single epsilons of the diagonal elements required for estimating the self-transition probability.

• reset should not be necessary after each training step

Constructor Detail

DistanceBasedScaledTransitionElement

public DistanceBasedScaledTransitionElement(int[] context,
                                    int[] states,
                                    double[] probabilities,
                                    double ess,
                                    double scalingFactor,
                                    String annotationID)

Creates an object representing the transition probabilities of a Hidden Markov TrainableStatisticalModel with scaled transition matrices (SHMM) for the given context.

Parameters:

context - context of states

states - states that can be reached from the context

probabilities - transition probabilities from the context to the states

ess - the equivalent sample size (ess)

scalingFactor - scaling factor

annotationID - identifier for decoding transition classes

See Also:

DistanceBasedScaledTransitionElement(int[], int[], double[], double, double, String, double[])

DistanceBasedScaledTransitionElement

public DistanceBasedScaledTransitionElement(int[] context,
                                    int[] states,
                                    double[] probabilities,
                                    double ess,
                                    double scalingFactor,
                                    String annotationID,
                                    double[] weight)

Creates an object representing the transition probabilities of a Hidden Markov TrainableStatisticalModel with scaled transition matrices (SHMM) for the given context.

Parameters:

context - context of states

states - states that can be reached from the context

probabilities - transition probabilities from the context to the states

ess - the equivalent sample size (ess)

scalingFactor - scaling factor

annotationID - identifier for decoding transition classes

weight - the weight for plotting the edge in Graphviz, enables to modify the edge length, larger weights imply shorter edges (default: 1)

DistanceBasedScaledTransitionElement

public DistanceBasedScaledTransitionElement(StringBuffer xml)
                                     throws NonParsableException

Extracts a distance-base scaled transition element from XML.

Parameters:

xml - the XML-representation

Throws:

NonParsableException - if the representation could not be parsed

Method Detail

init

protected void init()

Basic initialization.

Overrides:

init in class ReferenceBasedTransitionElement

clone

public DistanceBasedScaledTransitionElement clone()
                                           throws CloneNotSupportedException

Clones the object.

Overrides:

clone in class ReferenceBasedTransitionElement

Throws:

CloneNotSupportedException

getIndex

protected double getIndex(int pos,
              Sequence seq)

Returns the distance integrated into the transition from pos - 1 to pos in sequences seq.

Parameters:

pos - position in seq

seq - sequences

Returns:

distance

addToStatistic

public void addToStatistic(int childIdx,
                  double weight,
                  Sequence sequence,
                  int sequencePosition)

Description copied from class: BasicHigherOrderTransition.AbstractTransitionElement

This method adds a given weight to the sufficient statistic for the parameters.

Overrides:

addToStatistic in class BasicHigherOrderTransition.AbstractTransitionElement

Parameters:

childIdx - the index of the descendant state

weight - the weight to be added

sequence - the sequence, which might be used to retrieve SequenceAnnotation

sequencePosition - the position within the sequence

See Also:

TransitionWithSufficientStatistic.addToStatistic(int, int, int, double, Sequence, int), BasicHigherOrderTransition.AbstractTransitionElement.statistic, BasicHigherOrderTransition.AbstractTransitionElement.resetStatistic(), BasicHigherOrderTransition.AbstractTransitionElement.estimateFromStatistic(), BasicHigherOrderTransition.AbstractTransitionElement.drawParametersFromStatistic()

resetStatistic

public void resetStatistic()

Description copied from class: BasicHigherOrderTransition.AbstractTransitionElement

This method resets the sufficient statistic for the parameters.

Overrides:

resetStatistic in class BasicHigherOrderTransition.AbstractTransitionElement

See Also:

BasicHigherOrderTransition.AbstractTransitionElement.statistic, BasicHigherOrderTransition.AbstractTransitionElement.estimateFromStatistic(), BasicHigherOrderTransition.AbstractTransitionElement.drawParametersFromStatistic(), BasicHigherOrderTransition.AbstractTransitionElement.addToStatistic(int, double, Sequence, int), TransitionWithSufficientStatistic.resetStatistic()

estimateFromStatistic

public void estimateFromStatistic()

Description copied from class: BasicHigherOrderTransition.AbstractTransitionElement

This method estimates the parameters from the sufficient statistic.

Overrides:

estimateFromStatistic in class BasicHigherOrderTransition.AbstractTransitionElement

See Also:

BasicHigherOrderTransition.AbstractTransitionElement.statistic, BasicHigherOrderTransition.AbstractTransitionElement.resetStatistic(), BasicHigherOrderTransition.AbstractTransitionElement.addToStatistic(int, double, Sequence, int), TrainableTransition.estimateFromStatistic()

getLogScoreFor

public double getLogScoreFor(int state,
                    Sequence sequence,
                    int sequencePosition)

Description copied from class: BasicHigherOrderTransition.AbstractTransitionElement

This method returns the score for the transition from the current context to the state with index index.

Overrides:

getLogScoreFor in class BasicHigherOrderTransition.AbstractTransitionElement

Parameters:

state - the index of the child

sequence - the sequence, which might be used to retrieve SequenceAnnotation

sequencePosition - the position within the sequence

Returns:

the score for the transition from the current context to the state with index index

appendTransitions

protected void appendTransitions(StringBuffer res,
                     String contextNodeRepresentation,
                     NumberFormat nf,
                     String arrowOption,
                     boolean graphical)

Description copied from class: BasicHigherOrderTransition.AbstractTransitionElement

This method appends all edges of the transition element to a given Graphviz representation.

Overrides:

appendTransitions in class BasicHigherOrderTransition.AbstractTransitionElement

Parameters:

res - the current Graphviz representation

contextNodeRepresentation - the String representation of the context node(s)

nf - the NumberFormat used for the probabilities, if null no probabilities will we written

arrowOption - this parameter gives the possibility to set some arrow option

graphical - represent transition probabilities as thickness of edges instead of textual output

See Also:

BasicHigherOrderTransition.AbstractTransitionElement.appendGraphvizDescription(StringBuffer, NumberFormat, String, boolean), BasicHigherOrderTransition.AbstractTransitionElement.getArrowOption(NumberFormat, double, double, String, boolean)

appendFurtherInformation

protected void appendFurtherInformation(StringBuffer xml)

Description copied from class: BasicHigherOrderTransition.AbstractTransitionElement

This method appends further information to the XML representation. It allows subclasses to save further parameters that are not defined in the superclass.

Overrides:

appendFurtherInformation in class ReferenceBasedTransitionElement

Parameters:

xml - the XML representation

extractFurtherInformation

protected void extractFurtherInformation(StringBuffer xml)
                                  throws NonParsableException

Description copied from class: BasicHigherOrderTransition.AbstractTransitionElement

This method extracts further information from the XML representation. It allows subclasses to cast further parameters that are not defined in the superclass.

Overrides:

extractFurtherInformation in class ReferenceBasedTransitionElement

Parameters:

xml - the XML representation

Throws:

NonParsableException - if the information could not be reconstructed out of the StringBuffer xml

getXMLTag

protected String getXMLTag()

Description copied from class: BasicHigherOrderTransition.AbstractTransitionElement

This method returns the xml tag used in BasicHigherOrderTransition.AbstractTransitionElement.toXML().

Overrides:

getXMLTag in class BasicHigherOrderTransition.AbstractTransitionElement

Returns:

the xml tag used in BasicHigherOrderTransition.AbstractTransitionElement.toXML()

toString

public String toString(String[] stateNames)

Returns a string representation of the transition probabilities.

Parameters:

stateNames - the names of the states

Returns:

representation of transition probabilities