Using predicted shape string to enhance the accuracy of γ-turn prediction
Zhu, Yaojuan ; Li, Tonghua ; Li, Dapeng ; Zhang, Yun LU ; Xiong, Wenwei ; Sun, Jiangming LU
; Tang, Zehui
and Chen, Guanyan
(2012)
In Amino Acids
42(5).
p.1749-1755
- Abstract
Numerous methods for predicting c-turns in proteins have been developed. However, the results they generally provided are not very good, with a Matthews correlation coefficient (MCC) ≤0.18. Here, an attempt has been made to develop a method to improve the accuracy of γ-turn prediction. First, we employ the geometric mean metric as optimal criterion to evaluate the performance of support vector machine for the highly imbalanced γ-turn dataset. This metric tries to maximize both the sensitivity and the specificity while keeping them balanced. Second, a predictor to generate protein shape string by structure alignment against the protein structure database has been designed and the predicted shape string is introduced as new variable for... (More)
Numerous methods for predicting c-turns in proteins have been developed. However, the results they generally provided are not very good, with a Matthews correlation coefficient (MCC) ≤0.18. Here, an attempt has been made to develop a method to improve the accuracy of γ-turn prediction. First, we employ the geometric mean metric as optimal criterion to evaluate the performance of support vector machine for the highly imbalanced γ-turn dataset. This metric tries to maximize both the sensitivity and the specificity while keeping them balanced. Second, a predictor to generate protein shape string by structure alignment against the protein structure database has been designed and the predicted shape string is introduced as new variable for γ-turn prediction. Based on this perception, we have developed a new method for γ-turn prediction. After training and testing the benchmark dataset of 320 nonhomologous protein chains using a fivefold cross-validation technique, the present method achieves excellent performance. The overall prediction accuracy Q total can achieve 92.2% and the MCC is 0.38, which outperform the existing γ-turn prediction methods. Our results indicate that the protein shape string is useful for predicting protein tight turns and it is reasonable to use the dihedral angle information as a variable for machine learning to predict protein folding. The dataset used in this work and the software to generate predicted shape string from structure database can be obtained from anonymous ftp site ftp://cheminfo.tongji. edu.cn/ GammaTurnPrediction/ freely.
(Less)
- author
- Zhu, Yaojuan
; Li, Tonghua
; Li, Dapeng
; Zhang, Yun
LU
; Xiong, Wenwei
; Sun, Jiangming
LU
; Tang, Zehui
and Chen, Guanyan
- publishing date
- 2012-05
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- γ-Turn prediction, Imbalanced data, Shape string, Support vector machine (SVM)
- in
- Amino Acids
- volume
- 42
- issue
- 5
- pages
- 1749 - 1755
- publisher
- Springer
- external identifiers
-
- pmid:21424809
- scopus:84862772398
- ISSN
- 0939-4451
- DOI
- 10.1007/s00726-011-0889-z
- language
- English
- LU publication?
- no
- id
- b9102a91-048a-4465-921e-00981f82bfaf
- date added to LUP
- 2023-04-24 16:40:22
- date last changed
- 2024-02-03 12:33:51
@article{b9102a91-048a-4465-921e-00981f82bfaf,
abstract = {{<p>Numerous methods for predicting c-turns in proteins have been developed. However, the results they generally provided are not very good, with a Matthews correlation coefficient (MCC) ≤0.18. Here, an attempt has been made to develop a method to improve the accuracy of γ-turn prediction. First, we employ the geometric mean metric as optimal criterion to evaluate the performance of support vector machine for the highly imbalanced γ-turn dataset. This metric tries to maximize both the sensitivity and the specificity while keeping them balanced. Second, a predictor to generate protein shape string by structure alignment against the protein structure database has been designed and the predicted shape string is introduced as new variable for γ-turn prediction. Based on this perception, we have developed a new method for γ-turn prediction. After training and testing the benchmark dataset of 320 nonhomologous protein chains using a fivefold cross-validation technique, the present method achieves excellent performance. The overall prediction accuracy Q <sub>total</sub> can achieve 92.2% and the MCC is 0.38, which outperform the existing γ-turn prediction methods. Our results indicate that the protein shape string is useful for predicting protein tight turns and it is reasonable to use the dihedral angle information as a variable for machine learning to predict protein folding. The dataset used in this work and the software to generate predicted shape string from structure database can be obtained from anonymous ftp site ftp://cheminfo.tongji. edu.cn/ GammaTurnPrediction/ freely.</p>}},
author = {{Zhu, Yaojuan and Li, Tonghua and Li, Dapeng and Zhang, Yun and Xiong, Wenwei and Sun, Jiangming and Tang, Zehui and Chen, Guanyan}},
issn = {{0939-4451}},
keywords = {{γ-Turn prediction; Imbalanced data; Shape string; Support vector machine (SVM)}},
language = {{eng}},
number = {{5}},
pages = {{1749--1755}},
publisher = {{Springer}},
series = {{Amino Acids}},
title = {{Using predicted shape string to enhance the accuracy of γ-turn prediction}},
url = {{http://dx.doi.org/10.1007/s00726-011-0889-z}},
doi = {{10.1007/s00726-011-0889-z}},
volume = {{42}},
year = {{2012}},
}