Extraction of hidden Markov model representations of signal patterns in DNA sequences.

Tetsushi Yada; Masato Ishikawa; H. Tanaka; Kiyoshi Asai

Abstract

We have developed a method to extract the signal patterns in DNA sequences. In this method, the Genetic Algorithm (GA) and Baum-Welch algorithm are used to obtain the best Hidden Markov Model (HMM) representations of the signal patterns in DNA sequences. The GA is used to search the best network shapes and the initial parameters of the HMMs. Baum-Welch algorithm is used to optimize the HMM parameters for the given network shapes. Akaike Information Criterion (AIC), which gives a criterion for the balance of adaptation and complexity of a model, is applied in the HMM evaluation. We have applied the method to the extraction of the signal patterns in human promoters and 5' ends of yeast introns. As a result, we obtained HMM representations of characteristic features in these sequences. To validate the efficiency of the method, we have performed promoter recognition using obtained HMMs. Two entries including nine promoters are selected from GenBank 76.0, and it is observed that the HMM can predicts eight promoters correctly. These results imply that the method is efficient to design preferable HMM networks, and provides reliable models for the recognition of the signal patterns.

Keywords

Hidden Markov modelAkaike information criterionPattern recognition (psychology)Computer scienceSIGNAL (programming language)Artificial intelligenceAlgorithmGenetic algorithmMathematicsSpeech recognitionMachine learning

Related Publications

Profile hidden Markov models.

Sean R. Eddy

Abstract The recent literature on profile hidden Markov model (profile HMM) methods and software is reviewed. Profile HMMs turn a multiple sequence alignment into a position-spe...

1998 Bioinformatics 5657 citations

An Introduction to the Application of the Theory of Probabilistic Functions of a Markov Process to Automatic Speech Recognition

S. Levinson , L. R. Rabiner , M. M. Sondhi

In this paper we present several of the salient theoretical and practical issues associated with modeling a speech signal as a probabilistic function of a (hidden) Markov chain....

1983 Bell System Technical Journal 979 citations

Global optimization of a neural network-hidden Markov model hybrid

Yoshua Bengio , Renato De Mori , Giovanni Flammia +1 more

An original method for integrating artificial neural networks (ANN) with hidden Markov models (HMM) is proposed. ANNs are suitable for performing phonetic classification, wherea...

2002 18 citations

Accelerated Profile HMM Searches

Sean R. Eddy

Profile hidden Markov models (profile HMMs) and probabilistic inference methods have made important contributions to the theory of sequence database homology search. However, pr...

2011 PLoS Computational Biology 6891 citations

Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling

Brian Kingsbury

Acoustic models used in hidden Markov model/neural-network (HMM/NN) speech recognition systems are usually trained with a frame-based cross-entropy error criterion. In contrast,...

2009 238 citations

Publication Info

Year: 1996
Type: article
Pages: 686-96
Citations: 15
Access: Closed

External Links

Citation Metrics

OpenAlex

Cite This

APA Style

                            
                                    Tetsushi Yada, 
                                
                                    Masato Ishikawa, 
                                
                                    H. Tanaka
                                
                                et al.
                            
                            (1996). 
                            Extraction of hidden Markov model representations of signal patterns in DNA sequences.. 
                            PubMed
                            
                            , 686-96.