An HMM posterior decoder for sequence feature prediction that includes homology information

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

An HMM posterior decoder for sequence feature prediction that includes homology information. / Käll, Lukas; Krogh, Anders Stærmose; Sonnhammer, Erik L. L.

I: Bioinformatics, Bind 21, Nr. 1, 2005, s. i251 - i257.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Käll, L, Krogh, AS & Sonnhammer, ELL 2005, 'An HMM posterior decoder for sequence feature prediction that includes homology information', Bioinformatics, bind 21, nr. 1, s. i251 - i257. https://doi.org/10.1093/bioinformatics/bti1014

APA

Käll, L., Krogh, A. S., & Sonnhammer, E. L. L. (2005). An HMM posterior decoder for sequence feature prediction that includes homology information. Bioinformatics, 21(1), i251 - i257. https://doi.org/10.1093/bioinformatics/bti1014

Vancouver

Käll L, Krogh AS, Sonnhammer ELL. An HMM posterior decoder for sequence feature prediction that includes homology information. Bioinformatics. 2005;21(1):i251 - i257. https://doi.org/10.1093/bioinformatics/bti1014

Author

Käll, Lukas ; Krogh, Anders Stærmose ; Sonnhammer, Erik L. L. / An HMM posterior decoder for sequence feature prediction that includes homology information. I: Bioinformatics. 2005 ; Bind 21, Nr. 1. s. i251 - i257.

Bibtex

@article{4f65aed06c3611dcbee902004c4f4f50,
title = "An HMM posterior decoder for sequence feature prediction that includes homology information",
abstract = "Motivation: When predicting sequence features like transmembrane topology, signal peptides, coil-coil structures, protein secondary structure or genes, extra support can be gained from homologs. Results: We present here a general hidden Markov model (HMM) decoding algorithm that combines probabilities for sequence features of homologs by considering the average of the posterior label probability of each position in a global sequence alignment. The algorithm is an extension of the previously described {\textquoteleft}optimal accuracy' decoder, allowing homology information to be used. It was benchmarked using an HMM for transmembrane topology and signal peptide prediction, Phobius. We found that the performance was substantially increased when incorporating information from homologs. Availability: A prediction server for transmembrane topology and signal peptides that uses the algorithm is available at http://phobius.cgb.ki.se/poly.html. An implementation of the algorithm is available on request from the authors. ",
author = "Lukas K{\"a}ll and Krogh, {Anders St{\ae}rmose} and Sonnhammer, {Erik L. L.}",
year = "2005",
doi = "10.1093/bioinformatics/bti1014",
language = "English",
volume = "21",
pages = "i251 -- i257",
journal = "Computer Applications in the Biosciences",
issn = "1471-2105",
publisher = "Oxford University Press",
number = "1",

}

RIS

TY - JOUR

T1 - An HMM posterior decoder for sequence feature prediction that includes homology information

AU - Käll, Lukas

AU - Krogh, Anders Stærmose

AU - Sonnhammer, Erik L. L.

PY - 2005

Y1 - 2005

N2 - Motivation: When predicting sequence features like transmembrane topology, signal peptides, coil-coil structures, protein secondary structure or genes, extra support can be gained from homologs. Results: We present here a general hidden Markov model (HMM) decoding algorithm that combines probabilities for sequence features of homologs by considering the average of the posterior label probability of each position in a global sequence alignment. The algorithm is an extension of the previously described ‘optimal accuracy' decoder, allowing homology information to be used. It was benchmarked using an HMM for transmembrane topology and signal peptide prediction, Phobius. We found that the performance was substantially increased when incorporating information from homologs. Availability: A prediction server for transmembrane topology and signal peptides that uses the algorithm is available at http://phobius.cgb.ki.se/poly.html. An implementation of the algorithm is available on request from the authors.

AB - Motivation: When predicting sequence features like transmembrane topology, signal peptides, coil-coil structures, protein secondary structure or genes, extra support can be gained from homologs. Results: We present here a general hidden Markov model (HMM) decoding algorithm that combines probabilities for sequence features of homologs by considering the average of the posterior label probability of each position in a global sequence alignment. The algorithm is an extension of the previously described ‘optimal accuracy' decoder, allowing homology information to be used. It was benchmarked using an HMM for transmembrane topology and signal peptide prediction, Phobius. We found that the performance was substantially increased when incorporating information from homologs. Availability: A prediction server for transmembrane topology and signal peptides that uses the algorithm is available at http://phobius.cgb.ki.se/poly.html. An implementation of the algorithm is available on request from the authors.

U2 - 10.1093/bioinformatics/bti1014

DO - 10.1093/bioinformatics/bti1014

M3 - Journal article

C2 - 15961464

VL - 21

SP - i251 - i257

JO - Computer Applications in the Biosciences

JF - Computer Applications in the Biosciences

SN - 1471-2105

IS - 1

ER -

ID: 1077616