|
|||||||||
PREV PACKAGE NEXT PACKAGE | FRAMES NO FRAMES |
See:
Description
Interface Summary | |
DotState | A Dot state. |
DPMatrix | |
EmissionState | A state in a markov process that has an emission spectrum. |
MarkovModel | A markov model. |
ModelInState | A state that contains an entire sub-model. |
ModelTrainer | Encapsulates the training of an entire model. |
State | A state in a markov process. |
StatePath | Extends the Alignment interface so that it is explicitly used to represent a state path through an HMM, and the associated emitted sequence and likelyhoods. |
StoppingCriteria | |
Trainable | Flags an object as being able to register itself with a model trainer. |
TrainingAlgorithm | |
TransitionListener | |
TransitionTrainer | An object that can be used to train the transitions within a MarkovModel. |
WeightMatrix | A log odds weight matrix. |
Class Summary | |
AbstractTrainer | |
BaumWelchSampler | |
BaumWelchTrainer | |
DP | |
DP.ReverseIterator | |
DPFactory | |
MagicalState | Start/end state for HMMs. |
ModelChangeEvent | |
ModelView | A model that exposes some translated view of another model. |
PairDPMatrix | Storage structure for intermediate values from a pairwise dynamic programming run. |
PairwiseDP | Algorithms for dynamic programming (alignments) between pairs of SymbolLists. |
ProfileHMM | |
SimpleDotState | A Dot state that you can make and use. |
SimpleEmissionState | |
SimpleMarkovModel | |
SimpleModelInState | |
SimpleModelTrainer | |
SimpleStatePath | A no-frills implementation of StatePath. |
SimpleTransitionTrainer | A simple implementation of a TransitionTrainer. |
SimpleWeightMatrix | |
TrainerTransition | This is a small and ugly class for storing a trainer and a transition. |
Transition | This is a small and ugly class for storing a transition. |
TransitionEvent | |
WeightMatrixAnnotator | Annotates a sequence with hits to a weight-matrix. |
WMAsMM | Wraps a weight matrix up so that it appears to be a very simple hmm. |
XmlMarkovModel |
Exception Summary | |
IllegalTransitionException | This exception indicates that there is no transition between two states. |
ModelVetoException |
HMM and Dynamic Programming Algorithms.
This package deals with dynamic programming. It uses the same notions of sequences, alphabets and alignments as org.biojava.bio.seq, and extends them to encorporate HMMs, HMM states and state paths. As far as possible, the implementation detail is hidden from the casual observer, so that these objects can be used as black-boxes. Alternatively, there is scope for you to implement your own efficient representations of states and dynamic programming algorithms.
HMMs are defined by a finite set of states and a finite set of transitions. The states are encapsulated as subinterfaces of Symbols, so that we can re-use alphabets and SymbolList to stoor legal states and sequences of states. States that emit residues must implement EmissionState. They define a probability distribution over an alphabet. Other states may contain entire HMMs, or be non-emitting states which make the model easier to wire. An HMM contains an alphabet of states and a set of transitions with scores. They realy resemble directed weighted graphs with the nodes being the states and the arcs being the transitions.
A simple HMM can be aligned to a single sequence at a time. This effectively finds the most likely way that the HMM could have emitted that sequence. Mode complex algorithms may align more than one sequence to a model symultaneously. For example, Smith-Waterman is a three-state model that aligns two sequences to each other and to the model. These more complex models can still be represented as producing a single sequence, but in this case the sequence is an alignment of the two input sequences against one-another (including gap characters where apropreate).
|
|||||||||
PREV PACKAGE NEXT PACKAGE | FRAMES NO FRAMES |