Improving the performance of β-turn prediction using predicted shape strings and a two-layer support vector machine model
Tang, Zehui ; Li, Tonghua ; Liu, Rida ; Xiong, Wenwei ; Sun, Jiangming LU
; Zhu, Yaojuan
and Chen, Guanyan
(2011)
In BMC Bioinformatics
12.
p.1-9
- Abstract
The β-turn is a secondary protein structure type that plays an important role in protein configuration and function. Development of accurate prediction methods to identify β-turns in protein sequences is valuable. Several methods for β-turn prediction have been developed; however, the prediction quality is still a challenge and there is infstantial room for improvement. Innovations of the proposed method focus on discovering effective features, and constructing a new architectural model. ResultsWe utilized predicted secondary structures, predicted shape strings and the position-specific scoring matrix (PSSM) as input features, and proposed a novel two-layer model to enhance the prediction. We achieved the highest values according to... (More)
The β-turn is a secondary protein structure type that plays an important role in protein configuration and function. Development of accurate prediction methods to identify β-turns in protein sequences is valuable. Several methods for β-turn prediction have been developed; however, the prediction quality is still a challenge and there is infstantial room for improvement. Innovations of the proposed method focus on discovering effective features, and constructing a new architectural model. ResultsWe utilized predicted secondary structures, predicted shape strings and the position-specific scoring matrix (PSSM) as input features, and proposed a novel two-layer model to enhance the prediction. We achieved the highest values according to four evaluation measures, i.e. Qtotal = 87.2%, MCC = 0.66, Qobserved = 75.9%, and Qpredicted = 73.8% on the BT426 dataset. The results show that our proposed two-layer model discriminates better between β-turns and non-β-turns than the single model due to obtaining higher Qpredicted. Moreover, the predicted shape strings based on the structural alignment approach greatly improve the performance, and the same improvements were observed on BT547 and BT823 datasets as well. Conclusion In this article, we present a comprehensive method for the prediction of β-turns. Experiments show that the proposed method constitutes a great improvement over the competing prediction methods.
(Less)
- author
- Tang, Zehui
; Li, Tonghua
; Liu, Rida
; Xiong, Wenwei
; Sun, Jiangming
LU
; Zhu, Yaojuan
and Chen, Guanyan
- publishing date
- 2011-07-13
- type
- Contribution to journal
- publication status
- published
- in
- BMC Bioinformatics
- volume
- 12
- article number
- 283
- pages
- 1 - 9
- publisher
- BioMed Central (BMC)
- external identifiers
-
- pmid:21749732
- scopus:79960128304
- ISSN
- 1471-2105
- DOI
- 10.1186/1471-2105-12-283
- language
- English
- LU publication?
- no
- id
- 2f729b8c-861d-4bf9-9630-eca6ac3ed04c
- date added to LUP
- 2023-04-24 16:41:01
- date last changed
- 2025-01-12 23:27:02
@article{2f729b8c-861d-4bf9-9630-eca6ac3ed04c,
abstract = {{<p>The β-turn is a secondary protein structure type that plays an important role in protein configuration and function. Development of accurate prediction methods to identify β-turns in protein sequences is valuable. Several methods for β-turn prediction have been developed; however, the prediction quality is still a challenge and there is infstantial room for improvement. Innovations of the proposed method focus on discovering effective features, and constructing a new architectural model. ResultsWe utilized predicted secondary structures, predicted shape strings and the position-specific scoring matrix (PSSM) as input features, and proposed a novel two-layer model to enhance the prediction. We achieved the highest values according to four evaluation measures, i.e. Q<sub>total </sub>= 87.2%, MCC = 0.66, Q<sub>observed </sub>= 75.9%, and Q<sub>predicted </sub>= 73.8% on the BT426 dataset. The results show that our proposed two-layer model discriminates better between β-turns and non-β-turns than the single model due to obtaining higher Q<sub>predicted</sub>. Moreover, the predicted shape strings based on the structural alignment approach greatly improve the performance, and the same improvements were observed on BT547 and BT823 datasets as well. Conclusion In this article, we present a comprehensive method for the prediction of β-turns. Experiments show that the proposed method constitutes a great improvement over the competing prediction methods.</p>}},
author = {{Tang, Zehui and Li, Tonghua and Liu, Rida and Xiong, Wenwei and Sun, Jiangming and Zhu, Yaojuan and Chen, Guanyan}},
issn = {{1471-2105}},
language = {{eng}},
month = {{07}},
pages = {{1--9}},
publisher = {{BioMed Central (BMC)}},
series = {{BMC Bioinformatics}},
title = {{Improving the performance of β-turn prediction using predicted shape strings and a two-layer support vector machine model}},
url = {{http://dx.doi.org/10.1186/1471-2105-12-283}},
doi = {{10.1186/1471-2105-12-283}},
volume = {{12}},
year = {{2011}},
}