Hidden neural networks for transmembrane protein topology prediction

Hidden Markov Models (HMMs) are amongst the most successful methods for predicting protein features in biological sequence analysis. However, there are biological problems where the Markovian assumption is not sufficient since the sequence context can provide useful information for prediction purpos...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ioannis A. Tamposis, Dimitra Sarantopoulou, Margarita C. Theodoropoulou, Evangelia A. Stasi, Panagiota I. Kontou, Konstantinos D. Tsirigos, Pantelis G. Bagos
Formato: article
Lenguaje:EN
Publicado: Elsevier 2021
Materias:
Acceso en línea:https://doaj.org/article/1826dcfedd9741849193e7818f992144
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:1826dcfedd9741849193e7818f992144
record_format dspace
spelling oai:doaj.org-article:1826dcfedd9741849193e7818f9921442021-11-20T05:05:23ZHidden neural networks for transmembrane protein topology prediction2001-037010.1016/j.csbj.2021.11.006https://doaj.org/article/1826dcfedd9741849193e7818f9921442021-01-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2001037021004712https://doaj.org/toc/2001-0370Hidden Markov Models (HMMs) are amongst the most successful methods for predicting protein features in biological sequence analysis. However, there are biological problems where the Markovian assumption is not sufficient since the sequence context can provide useful information for prediction purposes. Several extensions of HMMs have appeared in the literature in order to overcome their limitations. We apply here a hybrid method that combines HMMs and Neural Networks (NNs), termed Hidden Neural Networks (HNNs), for biological sequence analysis in a straightforward manner. In this framework, the traditional HMM probability parameters are replaced by NN outputs. As a case study, we focus on the topology prediction of for alpha-helical and beta-barrel membrane proteins. The HNNs show performance gains compared to standard HMMs and the respective predictors outperform the top-scoring methods in the field. The implementation of HNNs can be found in the package JUCHMME, downloadable from http://www.compgen.org/tools/juchmme, https://github.com/pbagos/juchmme. The updated PRED-TMBB2 and HMM-TM prediction servers can be accessed at www.compgen.org.Ioannis A. TamposisDimitra SarantopoulouMargarita C. TheodoropoulouEvangelia A. StasiPanagiota I. KontouKonstantinos D. TsirigosPantelis G. BagosElsevierarticleHidden Markov ModelsHidden Neural NetworksMembrane proteinsSequence analysisNeural NetworksProtein structure predictionBiotechnologyTP248.13-248.65ENComputational and Structural Biotechnology Journal, Vol 19, Iss , Pp 6090-6097 (2021)
institution DOAJ
collection DOAJ
language EN
topic Hidden Markov Models
Hidden Neural Networks
Membrane proteins
Sequence analysis
Neural Networks
Protein structure prediction
Biotechnology
TP248.13-248.65
spellingShingle Hidden Markov Models
Hidden Neural Networks
Membrane proteins
Sequence analysis
Neural Networks
Protein structure prediction
Biotechnology
TP248.13-248.65
Ioannis A. Tamposis
Dimitra Sarantopoulou
Margarita C. Theodoropoulou
Evangelia A. Stasi
Panagiota I. Kontou
Konstantinos D. Tsirigos
Pantelis G. Bagos
Hidden neural networks for transmembrane protein topology prediction
description Hidden Markov Models (HMMs) are amongst the most successful methods for predicting protein features in biological sequence analysis. However, there are biological problems where the Markovian assumption is not sufficient since the sequence context can provide useful information for prediction purposes. Several extensions of HMMs have appeared in the literature in order to overcome their limitations. We apply here a hybrid method that combines HMMs and Neural Networks (NNs), termed Hidden Neural Networks (HNNs), for biological sequence analysis in a straightforward manner. In this framework, the traditional HMM probability parameters are replaced by NN outputs. As a case study, we focus on the topology prediction of for alpha-helical and beta-barrel membrane proteins. The HNNs show performance gains compared to standard HMMs and the respective predictors outperform the top-scoring methods in the field. The implementation of HNNs can be found in the package JUCHMME, downloadable from http://www.compgen.org/tools/juchmme, https://github.com/pbagos/juchmme. The updated PRED-TMBB2 and HMM-TM prediction servers can be accessed at www.compgen.org.
format article
author Ioannis A. Tamposis
Dimitra Sarantopoulou
Margarita C. Theodoropoulou
Evangelia A. Stasi
Panagiota I. Kontou
Konstantinos D. Tsirigos
Pantelis G. Bagos
author_facet Ioannis A. Tamposis
Dimitra Sarantopoulou
Margarita C. Theodoropoulou
Evangelia A. Stasi
Panagiota I. Kontou
Konstantinos D. Tsirigos
Pantelis G. Bagos
author_sort Ioannis A. Tamposis
title Hidden neural networks for transmembrane protein topology prediction
title_short Hidden neural networks for transmembrane protein topology prediction
title_full Hidden neural networks for transmembrane protein topology prediction
title_fullStr Hidden neural networks for transmembrane protein topology prediction
title_full_unstemmed Hidden neural networks for transmembrane protein topology prediction
title_sort hidden neural networks for transmembrane protein topology prediction
publisher Elsevier
publishDate 2021
url https://doaj.org/article/1826dcfedd9741849193e7818f992144
work_keys_str_mv AT ioannisatamposis hiddenneuralnetworksfortransmembraneproteintopologyprediction
AT dimitrasarantopoulou hiddenneuralnetworksfortransmembraneproteintopologyprediction
AT margaritactheodoropoulou hiddenneuralnetworksfortransmembraneproteintopologyprediction
AT evangeliaastasi hiddenneuralnetworksfortransmembraneproteintopologyprediction
AT panagiotaikontou hiddenneuralnetworksfortransmembraneproteintopologyprediction
AT konstantinosdtsirigos hiddenneuralnetworksfortransmembraneproteintopologyprediction
AT pantelisgbagos hiddenneuralnetworksfortransmembraneproteintopologyprediction
_version_ 1718419584305856512