Hughey, R. & Krogh, A. #1996#. Hidden Markov models for sequence analysis: Extension and analysis of the basic method. CABIOS, 12 #2#, 95# 107. Information on obtaining SAM is available at http:##www.cse.ucsc.edu#research#compbio#sam.html.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....to the problem of grammatical inference as done in [Bengio and Frasconi, 1994b] for the evaluation of the IOHMM and the application to problems in computational biology as DNA sequence analysis. Here the the analysis of the hidden structure is of main interest and HMMs can be used for this task [Hughey and Krogh, 1995]. The difference to time series forecasting is, that the whole sequence is given and information from previous as well as following positions in the sequence can be used in order to determine the hidden states. Several modifications to the current architecture are possible. One interesting ....

Hughey, R. and Krogh, A. (1995). Hidden markov models for sequence analysis: extension and analysis of the basic method. Preprint to appear in CABIOS.

....to select proteins from SCOP according to various criteria. We selected all non redundant proteins from SCOP version 1.53, yielding 4369 entries. For each entry, a hidden Markov model (HMM) was built using the Target99 protocol [20] with the Sequence Alignment and Modeling system (SAM 3. 0) system[21]. Multiple species were included to capture characteristics of both mammalian and non mammalian proteins. Each gene was scored against each SCOP family, yielding an e value. In practice, the e values generated by a model are dependent in part on that model, with shorter models yielding higher ....

Hughey, R. and A. Krogh, Hidden Markov models for sequence analysis: extension and analysis of the basic method. Comput Appl Biosci, 1996. 12(2): p. 95-107.

.... even need the geometric sequence calculation, and the calculation of the coemission probability reduces to a calculation similar to the forward backward calculations [35, Chapter 3] For all left right hidden Markov models, e.g. profile hidden Markov models extended with free insertion modules [15, 69], we can thus use recursions similar to those specified in section 6.3 to compute the co emission probability. With some work the method can even be extended to all hidden Markov models where each state is part of at most one cycle, even if this cycle consists of more than the one state of the ....

R. Hughey and A. Krogh. Hidden Markov models for sequence analysis: Extension and analysis of the basic method. CABIOS, 12(2):95--107, 1996.

.... even need the geometric sequence calculation, and the calculation of the coemission probability reduces to a calculation similar to the forward backward calculations [46, Chapter 3] For all left right hidden Markov models, e.g. profile hidden Markov models extended with free insertion modules [22, 92], we can thus use recursions similar to those specified in Section 6.3 to compute the co emission probability. With some work the method can even be extended to all hidden Markov models where each state is part of at most one cycle, even if this cycle consists of more than the one state of the ....

R. Hughey and A. Krogh. Hidden Markov models for sequence analysis: Extension and analysis of the basic method. Computer Applications in the Biosciences (CABIOS), 12(2):95--107, 1996.

.... not even need the geometric sequence calculation, and the calculation of the co emission probability reduces to a calculation similar to the forward backward calculations [6, Chapter 3] For all leftright hidden Markov models, e.g. pro le hidden Markov models extended with free insertion modules [3, 12], we can thus use recursions similar to those speci ed in section 3 to compute the co emission probability. With some work the method can even be extended to all hidden Markov models where each state is part of at most one cycle, even if this cycle consists of more than the one state of the ....

R. Hughey and A. Krogh. Hidden Markov models for sequence analysis: Extension and analysis of the basic method. CABIOS, 12(2):95-107, 1996.

....of HMMs was developed by Baum et al. 4, 5] in the late 1960s, but only in the last decade it has been extensively applied in a large number of problems. A non exhaustive list of such problems consists of speech recognition [3, 6] handwritten character recognition [7] DNA and protein modelling [8], gesture recognition [9] and, more recently, behavior analysis and synthesis [10] The use of HMM for shape analysis has not been widely addressed. Only a few work have been found to have some similarities with our approach. In the first, He and Kundu [17] utilize HMMs to model shape contours ....

Hughey, R., Krogh, A.: Hidden Markov Model for sequence analysis: extension and analysis of the basic method. Comp. Appl. in the Biosciences 12 (1996) 95--107.

....low identity, low similarity protein sequences sufficient for maximal recovery of the OSM and MIRs remains a challenge in the field of bioinformatics. The HMM approachtomultiple sequence alignment (Baldi, Chauvin et al. 1994 [2] Krogh, Brown et al. 1994 [8] Eddy 1995 [5] Hughey and Krogh 1996 [6]) provides a flexible method that can incorporate a priori knowledge into the model. Wehave demonstrated that anchoring an OSM in the same position within a set of subclass HMMs creates a series of models that generate better multiple alignments representing highly divergent sequences than a ....

....and Methods All analyses were conducted on SUN Ultras (1 140 and 1 170) or SPARCstations (4, 5 or 10 514MP) running SunOS Release 5.5 or 5.6. Version 2. 0 of Sequence Alignment and Modeling (SAM) was used for all multiple alignment studies (Krogh, Brown et al. 1994 [8] Hughey and Krogh 1996 [6]) 2.1 Biological data The protein family used in this study is the reverse transcriptase (RT) one of the twowell characterized domains of the RNA dependent DNA polymerase (RDDP) The RT domain is found in the amino portion of the RDDP encoded by different viruses (retroviruses, Hepadna , ....

[Article contains additional citation context not shown here]

Hughey, R. and Krogh, A., Hidden Markov models for sequence analysis: extension and analysis of the basic method, CABIOS 12:95--107, 1996.

....low identity, low similarity protein sequences su#cient for maximal recovery of the OSM and MIRs remains a challenge in the field of bioinformatics. The HMM approach to multiple sequence alignment (Baldi, Chauvin et al. 1994 [2] Krogh, Brown et al. 1994 [8] Eddy 1995 [5] Hughey and Krogh 1996 [6]) provides a flexible method that can incorporate a priori knowledge into the model. We have demonstrated that anchoring an OSM in the same position within a set of subclass HMMs creates a series of models that generate better multiple alignments representing highly divergent sequences than a ....

....and Methods All analyses were conducted on SUN Ultras (1 140 and 1 170) or SPARCstations (4, 5 or 10 514MP) running SunOS Release 5.5 or 5.6. Version 2. 0 of Sequence Alignment and Modeling (SAM) was used for all multiple alignment studies (Krogh, Brown et al. 1994 [8] Hughey and Krogh 1996 [6]) 2.1 Biological data The protein family used in this study is the reverse transcriptase (RT) one of the two well characterized domains of the RNA dependent DNA polymerase (RDDP) The RT domain is found in the amino portion of the RDDP encoded by di#erent viruses (retroviruses, Hepadna , ....

[Article contains additional citation context not shown here]

Hughey, R. and Krogh, A., Hidden Markov models for sequence analysis: extension and analysis of the basic method, CABIOS 12:95--107, 1996.

....of phylogenic trees. Two types of algorithms have been used: those which search for the optimal alignment (as exempli ed by the algorithm of Smith and Waterman (1981) and those which identify likely alignments (as exempli ed by the hidden Markov model (HMM) based Sequence Alignment Modules (Hughey Krogh, 1996)) In each case, the quality of the alignment is summarized by an alignment score S; the latter is typically taken to be the logarithm of the total likelihood in the probabilistic approaches. However, such an alignment score is assigned to any pair of 1 related (p)re prints available at ....

Hughey, R., and Krogh, A., 1996. Hidden Markov Models for Sequence Analysis: Extension and Analysis of the Basic Method. CABIOS 12:95-107.

....target class and the sequences in the non target class using an alignment tool such as BLAST [2] One then assigns S to the class containing the sequence best matching S. The second method for protein sequence classification is based on hidden Markov models (HMMs) 24] The HMM method (e.g. SAM [20] and HMMer [14] employs a machine learning algorithm, which uses probabilistic graphical models to describe time series and sequence data. It was originally applied to speech recognition [27] and now is also applied to modeling and analyzing protein superfamilies. It is a generalization of the ....

R. Hughey and A. Krogh. Hidden Markov models for sequence analysis: Extension and analysis of the basic method. Computer Applications in the Biosciences 12(2), 95--107, 1996.

....combine the amino acid frequencies observed in the column with Dirichlet mixture densities [18] which encode prior information about typical amino acid distributions. Using this form of prior has been shown to improve the generalization capacity of statistical models such as hidden Markov models [9] and phylogenetic trees [17] We adapted its use for design of patterns in [10] and [12] ii) Choose the column with lowest entropy, and make an initial pattern consisting of a single element which includes the symbols from this column. iii) In order of increasing entropy, incrementally add ....

R. Hughey and A. Krogh. Hidden Markov models for sequence analysis: extension and analysis of the basic method. Computer Applications in the Biosciences, 12(2):95--107, 1996.

....by a number of transitions with associated probabilities T (q i jq i 1 ) If the two states do not have a direct connection, the transition probability can be derived by lling in the intermediate delete states. Given this notation, the probability of 2 We here use the same notation as in [15], but due to lack of space we have made some simpli cations. For full details, consult [26] 20] and [15] 10 a particular alignment of the sequence to the model can be expressed as [15] P(x 1 ; x L ; q 1 ; q L ) L Y i=1 T (q i jq i 1 )P(x i jq i ) In order to determine how ....

....have a direct connection, the transition probability can be derived by lling in the intermediate delete states. Given this notation, the probability of 2 We here use the same notation as in [15] but due to lack of space we have made some simpli cations. For full details, consult [26] 20] and [15] 10 a particular alignment of the sequence to the model can be expressed as [15] P(x 1 ; x L ; q 1 ; q L ) L Y i=1 T (q i jq i 1 )P(x i jq i ) In order to determine how likely a model is to produce a particular sequence, we generally want to sum the probabilities of all paths ....

[Article contains additional citation context not shown here]

R. Hughey and A. Krogh, Hidden Markov models for sequence analysis: extension and analysis of the basic method, Computer Applications in the Biosciences, 12:2, (1996), 95-107.

.... [27] In addition to the speech recognition, HMMs have been widely used for other types of pattern recognition, e.g. ECG signal recognition [21] and text recognition [23] 19] In the area of molecular biology, HMMs have been used successfully for example in DNA and protein modeling [11] 22] [17], 12] 14] 28] In the applications of the HMM, likelihood functions and estimates of the model parameters have been routinely computed. However the statistical inference, like condence intervals, have been ignored almost in every application. As an exception, Klein et al. 20] have computed ....

Hughey, R., and Krogh, A. (1996), "Hidden Markov Models for Sequence Analysis: Extension and Analysis of the Basic Method ", Computer Applications in the Biosciences, 12, 95-107.

....model so that the sum of scores of sequences in the family is optimized. Search for sequences. The searching process should allow us to distinguish between the sequences, that belong to the family and sequences, which do not. Topology of HMM. Commonly used HMM topology [Krogh et al. 1994, Hughey and Krogh, 1996] for sequence analysis is depicted in Figure 4. The model consists of three types of states. Match states model conserved parts of the sequences (motifs) Match states specify probability distribution of characters on each conserved position. There can be any number of match states in the model, ....

....States M 1 , M 5 are match states, I 1 , I E are insertion states, and D 1 , D 5 are deletion states. Length of the sequence score NLL Figure 5: NLL score versus sequence length. Sequences from the domain, on which learning have been applied, are denoted by . [Hughey and Krogh, 1996] global optimum. It can happen that the algorithm will iterate to a local minimum. This depends on initial parameter settings. Search for sequences. Search for the pattern in the form of HMM is more complicated, than in the case of simpler patterns. Given a sequence, we can compute the most ....

[Article contains additional citation context not shown here]

Hughey, R. and Krogh, A. (1996). Hidden Markov models for sequence analysis: extension and analysis of the basic method. Computer Applications in the Biosciences, 12(2):95--107.

No context found.

Hughey, R. & Krogh, A. #1996#. Hidden Markov models for sequence analysis: Extension and analysis of the basic method. CABIOS, 12 #2#, 95# 107. Information on obtaining SAM is available at http:##www.cse.ucsc.edu#research#compbio#sam.html.

No context found.

Hughey, R., & Krogh, A. (1996). Hidden Markov models for sequence analysis: Extension and analysis of the basic method. CABIOS, 12 (2), 95-107.

No context found.

Hughey, Richard and Krogh, Anders 1996. Hidden Markov models for sequence analysis: Extension and analysis of the basic method. CABIOS 12#2#:95#107.

No context found.

Richard Hughey and Anders Krogh. Hidden Markov models for sequence analysis: Extension and analysis of the basic method. CABIOS, 12(2):95-107, 1996. Information on obtaining SAM is available at http://www.cse.ucsc.edu/research/compbio/sam.html.

.... 1 Introduction One method of protein sequence analysis is the identi cation of homologous proteins proteins that share a common evolutionary history and have similar overall structure and function [5] Here we report on the use of SAM T98 [11, 16] a newly developed hidden Markov model (hmm) [13, 9] method for recognition of homologs with low sequence similarity, and how it fared in the foldrecognition section of the CASP3 experiment. Hmms combine the best aspects of weight matrices and local sequence alignment methods, and can be used to assign probabilities to proteins in database search ....

....95064 USA. Phone: 1 831 4594250, Fax: 1 831 459 4829. Mail to other authors may be similarly addressed. A prediction server using the SAM T98 method discussed here is available on the World Wide Web , as is documentation and licensing information for the SAM hidden Markov model software suite [9]. 2 Methods Since the SAM T98 method is fully described elsewhere [11] it will only be described brie y here. The method is purely sequence based and does not employ any structural information. The method iterates through the following steps several times (four for template library, six or ....

R. Hughey and A. Krogh. Hidden Markov models for sequence analysis: Extension and analysis of the basic method. CABIOS, 12(2):95-107, 1996. Information on obtaining SAM is available at http://www.cse.ucsc.edu/ research/compbio/sam.html.

.... Bioinformatics at UCSC UC Santa Cruz is well known in the field of bioinformatics for pioneering work on applications of hidden Markov models (HMMs) and stochastic context free grammars to biological sequence data and for the development of software tools for sequence analysis [4] 5] [6], 7] Our efforts include participation in the international Human Genome Project [8] development of the gene finding software chosen to annotate the human and Drosophila (fly) genomes [9] success in international protein structure prediction contests [10] 11] and creation of a SIMD ....

Richard Hughey and Anders Krogh, "Hidden Markov models for sequence analysis: Extension and analysis of the basic method," CABIOS, vol. 12, no. 2, pp. 95--107, 1996, Information on obtaining SAM is available at http://www.cse.ucsc.edu/research/ compbio/sam.html.

No context found.

Hughey, R. and Krogh, A. (1996). Hidden Markov models for sequence analysis: Extension and analysis of the basic method. CABIOS, 12(2):95--107.

No context found.

R. Hughey and A. Krogh. Hidden Markov models for sequence analysis: Extension and analysis of the basic method. Computer Applications in the Biosciences, 12:95--107, 1996.

No context found.

R. Hughey, A. Krogh, Hidden Markov models for sequence analysis: extension and analysis of the basic method. Comput. Appl. Biosci., 12(2) :95-107, 1996.

No context found.

Hughey, R., Krogh, A.: Hidden Markov Model for sequence analysis: extension and analysis of the basic method. Comp. Appl. in the Biosciences 12 (1996) 95--107.

No context found.

Hughey,R. and Krogh,A. (1996) Hidden Markov models for sequence analysis: Extension and analysis of the basic method. Comput. Applic. Biosci., 12, 95--107.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC