A Hidden Markov Model method, capable of predicting and discriminating β-barrel outer membrane proteins
<p>Abstract</p> <p>Background</p> <p>Integral membrane proteins constitute about 20–30% of all proteins in the fully sequenced genomes. They come in two structural classes, the α-helical and the β-barrel membrane proteins, demonstrating different physicochemical charact...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2004-03-01
|
Series: | BMC Bioinformatics |
Online Access: | http://www.biomedcentral.com/1471-2105/5/29 |
id |
doaj-398ec1ce8b2544a2a9dec8fccdd421a9 |
---|---|
record_format |
Article |
spelling |
doaj-398ec1ce8b2544a2a9dec8fccdd421a92020-11-24T21:10:35ZengBMCBMC Bioinformatics1471-21052004-03-01512910.1186/1471-2105-5-29A Hidden Markov Model method, capable of predicting and discriminating β-barrel outer membrane proteinsHamodrakas Stavros JSpyropoulos Ioannis CLiakopoulos Theodore DBagos Pantelis G<p>Abstract</p> <p>Background</p> <p>Integral membrane proteins constitute about 20–30% of all proteins in the fully sequenced genomes. They come in two structural classes, the α-helical and the β-barrel membrane proteins, demonstrating different physicochemical characteristics, structure and localization. While transmembrane segment prediction for the α-helical integral membrane proteins appears to be an easy task nowadays, the same is much more difficult for the β-barrel membrane proteins. We developed a method, based on a Hidden Markov Model, capable of predicting the transmembrane β-strands of the outer membrane proteins of gram-negative bacteria, and discriminating those from water-soluble proteins in large datasets. The model is trained in a discriminative manner, aiming at maximizing the probability of correct predictions rather than the likelihood of the sequences.</p> <p>Results</p> <p>The training has been performed on a non-redundant database of 14 outer membrane proteins with structures known at atomic resolution; it has been tested with a jacknife procedure, yielding a per residue accuracy of 84.2% and a correlation coefficient of 0.72, whereas for the self-consistency test the per residue accuracy was 88.1% and the correlation coefficient 0.824. The total number of correctly predicted topologies is 10 out of 14 in the self-consistency test, and 9 out of 14 in the jacknife. Furthermore, the model is capable of discriminating outer membrane from water-soluble proteins in large-scale applications, with a success rate of 88.8% and 89.2% for the correct classification of outer membrane and water-soluble proteins respectively, the highest rates obtained in the literature. That test has been performed independently on a set of known outer membrane proteins with low sequence identity with each other and also with the proteins of the training set.</p> <p>Conclusion</p> <p>Based on the above, we developed a strategy, that enabled us to screen the entire proteome of <it>E. coli </it>for outer membrane proteins. The results were satisfactory, thus the method presented here appears to be suitable for screening entire proteomes for the discovery of novel outer membrane proteins. A web interface available for non-commercial users is located at: <url>http://bioinformatics.biol.uoa.gr/PRED-TMBB</url>, and it is the only freely available HMM-based predictor for β-barrel outer membrane protein topology.</p> http://www.biomedcentral.com/1471-2105/5/29 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hamodrakas Stavros J Spyropoulos Ioannis C Liakopoulos Theodore D Bagos Pantelis G |
spellingShingle |
Hamodrakas Stavros J Spyropoulos Ioannis C Liakopoulos Theodore D Bagos Pantelis G A Hidden Markov Model method, capable of predicting and discriminating β-barrel outer membrane proteins BMC Bioinformatics |
author_facet |
Hamodrakas Stavros J Spyropoulos Ioannis C Liakopoulos Theodore D Bagos Pantelis G |
author_sort |
Hamodrakas Stavros J |
title |
A Hidden Markov Model method, capable of predicting and discriminating β-barrel outer membrane proteins |
title_short |
A Hidden Markov Model method, capable of predicting and discriminating β-barrel outer membrane proteins |
title_full |
A Hidden Markov Model method, capable of predicting and discriminating β-barrel outer membrane proteins |
title_fullStr |
A Hidden Markov Model method, capable of predicting and discriminating β-barrel outer membrane proteins |
title_full_unstemmed |
A Hidden Markov Model method, capable of predicting and discriminating β-barrel outer membrane proteins |
title_sort |
hidden markov model method, capable of predicting and discriminating β-barrel outer membrane proteins |
publisher |
BMC |
series |
BMC Bioinformatics |
issn |
1471-2105 |
publishDate |
2004-03-01 |
description |
<p>Abstract</p> <p>Background</p> <p>Integral membrane proteins constitute about 20–30% of all proteins in the fully sequenced genomes. They come in two structural classes, the α-helical and the β-barrel membrane proteins, demonstrating different physicochemical characteristics, structure and localization. While transmembrane segment prediction for the α-helical integral membrane proteins appears to be an easy task nowadays, the same is much more difficult for the β-barrel membrane proteins. We developed a method, based on a Hidden Markov Model, capable of predicting the transmembrane β-strands of the outer membrane proteins of gram-negative bacteria, and discriminating those from water-soluble proteins in large datasets. The model is trained in a discriminative manner, aiming at maximizing the probability of correct predictions rather than the likelihood of the sequences.</p> <p>Results</p> <p>The training has been performed on a non-redundant database of 14 outer membrane proteins with structures known at atomic resolution; it has been tested with a jacknife procedure, yielding a per residue accuracy of 84.2% and a correlation coefficient of 0.72, whereas for the self-consistency test the per residue accuracy was 88.1% and the correlation coefficient 0.824. The total number of correctly predicted topologies is 10 out of 14 in the self-consistency test, and 9 out of 14 in the jacknife. Furthermore, the model is capable of discriminating outer membrane from water-soluble proteins in large-scale applications, with a success rate of 88.8% and 89.2% for the correct classification of outer membrane and water-soluble proteins respectively, the highest rates obtained in the literature. That test has been performed independently on a set of known outer membrane proteins with low sequence identity with each other and also with the proteins of the training set.</p> <p>Conclusion</p> <p>Based on the above, we developed a strategy, that enabled us to screen the entire proteome of <it>E. coli </it>for outer membrane proteins. The results were satisfactory, thus the method presented here appears to be suitable for screening entire proteomes for the discovery of novel outer membrane proteins. A web interface available for non-commercial users is located at: <url>http://bioinformatics.biol.uoa.gr/PRED-TMBB</url>, and it is the only freely available HMM-based predictor for β-barrel outer membrane protein topology.</p> |
url |
http://www.biomedcentral.com/1471-2105/5/29 |
work_keys_str_mv |
AT hamodrakasstavrosj ahiddenmarkovmodelmethodcapableofpredictinganddiscriminatingbbarreloutermembraneproteins AT spyropoulosioannisc ahiddenmarkovmodelmethodcapableofpredictinganddiscriminatingbbarreloutermembraneproteins AT liakopoulostheodored ahiddenmarkovmodelmethodcapableofpredictinganddiscriminatingbbarreloutermembraneproteins AT bagospantelisg ahiddenmarkovmodelmethodcapableofpredictinganddiscriminatingbbarreloutermembraneproteins AT hamodrakasstavrosj hiddenmarkovmodelmethodcapableofpredictinganddiscriminatingbbarreloutermembraneproteins AT spyropoulosioannisc hiddenmarkovmodelmethodcapableofpredictinganddiscriminatingbbarreloutermembraneproteins AT liakopoulostheodored hiddenmarkovmodelmethodcapableofpredictinganddiscriminatingbbarreloutermembraneproteins AT bagospantelisg hiddenmarkovmodelmethodcapableofpredictinganddiscriminatingbbarreloutermembraneproteins |
_version_ |
1716755961488605184 |