Predicting β-turns and their types using predicted backbone dihedral angles and secondary structures

Background: β-turns are secondary structure elements usually classified as coil. Their prediction is important, because of their role in protein folding and their frequent occurrence in protein chains. Results: We have developed a novel method that predicts β-turns and their types using informati...

Full description

Bibliographic Details
Main Authors: Kountouris, Peter, Hirst, J.D.
Format: Article
Published: BioMed Central Ltd 2010
Online Access:https://eprints.nottingham.ac.uk/1426/
_version_ 1848790603945476096
author Kountouris, Peter
Hirst, J.D.
author_facet Kountouris, Peter
Hirst, J.D.
author_sort Kountouris, Peter
building Nottingham Research Data Repository
collection Online Access
description Background: β-turns are secondary structure elements usually classified as coil. Their prediction is important, because of their role in protein folding and their frequent occurrence in protein chains. Results: We have developed a novel method that predicts β-turns and their types using information from multiple sequence alignments, predicted secondary structures and, for the first time, predicted dihedral angles. Our method uses support vector machines, a supervised classification technique, and is trained and tested on three established datasets of 426, 547 and 823 protein chains. We achieve a Matthews correlation coefficient of up to 0.49, when predicting the location of β-turns, the highest reported value to date. Moreover, the additional dihedral information improves the prediction of β-turn types I, II, IV, VIII and “non-specific”, achieving correlation coefficients up to 0.39, 0.33, 0.27, 0.14 and 0.38, respectively. Our results are more accurate than other methods. Conclusions: We have created an accurate predictor of b-turns and their types. Our method, called DEBT, is available online at http://comp.chem.nottingham.ac.uk/debt/.
first_indexed 2025-11-14T18:15:15Z
format Article
id nottingham-1426
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T18:15:15Z
publishDate 2010
publisher BioMed Central Ltd
recordtype eprints
repository_type Digital Repository
spelling nottingham-14262020-05-04T20:25:34Z https://eprints.nottingham.ac.uk/1426/ Predicting β-turns and their types using predicted backbone dihedral angles and secondary structures Kountouris, Peter Hirst, J.D. Background: β-turns are secondary structure elements usually classified as coil. Their prediction is important, because of their role in protein folding and their frequent occurrence in protein chains. Results: We have developed a novel method that predicts β-turns and their types using information from multiple sequence alignments, predicted secondary structures and, for the first time, predicted dihedral angles. Our method uses support vector machines, a supervised classification technique, and is trained and tested on three established datasets of 426, 547 and 823 protein chains. We achieve a Matthews correlation coefficient of up to 0.49, when predicting the location of β-turns, the highest reported value to date. Moreover, the additional dihedral information improves the prediction of β-turn types I, II, IV, VIII and “non-specific”, achieving correlation coefficients up to 0.39, 0.33, 0.27, 0.14 and 0.38, respectively. Our results are more accurate than other methods. Conclusions: We have created an accurate predictor of b-turns and their types. Our method, called DEBT, is available online at http://comp.chem.nottingham.ac.uk/debt/. BioMed Central Ltd 2010 Article PeerReviewed Kountouris, Peter and Hirst, J.D. (2010) Predicting β-turns and their types using predicted backbone dihedral angles and secondary structures. BMC Bioinformatics, 11 . p. 407. ISSN 1471-2105 http://dx.doi.org/10.1186/1471-2105-11-407
spellingShingle Kountouris, Peter
Hirst, J.D.
Predicting β-turns and their types using predicted backbone dihedral angles and secondary structures
title Predicting β-turns and their types using predicted backbone dihedral angles and secondary structures
title_full Predicting β-turns and their types using predicted backbone dihedral angles and secondary structures
title_fullStr Predicting β-turns and their types using predicted backbone dihedral angles and secondary structures
title_full_unstemmed Predicting β-turns and their types using predicted backbone dihedral angles and secondary structures
title_short Predicting β-turns and their types using predicted backbone dihedral angles and secondary structures
title_sort predicting β-turns and their types using predicted backbone dihedral angles and secondary structures
url https://eprints.nottingham.ac.uk/1426/
https://eprints.nottingham.ac.uk/1426/