dc.creator | Tamposis I.A., Sarantopoulou D., Theodoropoulou M.C., Stasi E.A., Kontou P.I., Tsirigos K.D., Bagos P.G. | en |
dc.date.accessioned | 2023-01-31T10:06:08Z | |
dc.date.available | 2023-01-31T10:06:08Z | |
dc.date.issued | 2021 | |
dc.identifier | 10.1016/j.csbj.2021.11.006 | |
dc.identifier.issn | 20010370 | |
dc.identifier.uri | http://hdl.handle.net/11615/79595 | |
dc.description.abstract | 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. © 2021 The Author(s) | en |
dc.language.iso | en | en |
dc.source | Computational and Structural Biotechnology Journal | en |
dc.source.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85119357197&doi=10.1016%2fj.csbj.2021.11.006&partnerID=40&md5=33b7b3392f561f1c950138f0520e8f09 | |
dc.subject | Forecasting | en |
dc.subject | Proteins | en |
dc.subject | Topology | en |
dc.subject | Trellis codes | en |
dc.subject | Biological sequence analysis | en |
dc.subject | Hidden neural network | en |
dc.subject | Hidden-Markov models | en |
dc.subject | Membrane proteins | en |
dc.subject | Neural-networks | en |
dc.subject | Protein structure prediction | en |
dc.subject | Sequence analysis | en |
dc.subject | Topology predictions | en |
dc.subject | Trans-membrane proteins | en |
dc.subject | Hidden Markov models | en |
dc.subject | amino acid | en |
dc.subject | membrane protein | en |
dc.subject | outer membrane protein | en |
dc.subject | amino acid sequence | en |
dc.subject | Article | en |
dc.subject | artificial neural network | en |
dc.subject | comparative study | en |
dc.subject | conceptual framework | en |
dc.subject | hidden Markov model | en |
dc.subject | hidden neural network | en |
dc.subject | molecular biology | en |
dc.subject | predictive value | en |
dc.subject | probability | en |
dc.subject | protein structure | en |
dc.subject | sequence analysis | en |
dc.subject | Elsevier B.V. | en |
dc.title | Hidden neural networks for transmembrane protein topology prediction | en |
dc.type | journalArticle | en |