Feature selection and combination criteria for improving predictive accuracy in protein structure classification

Chun Yuan Lin; Ken Li Lin; Chuen Der Huang; Hsiu Ming Chang; Chiao Yun Yang; Chin Teng Lin; Chuan Yi Tang; D. Frank Hsu

doi:10.1109/BIBE.2005.26

Feature selection and combination criteria for improving predictive accuracy in protein structure classification

Chun Yuan Lin^*, Ken Li Lin, Chuen Der Huang, Hsiu Ming Chang, Chiao Yun Yang, Chin Teng Lin, Chuan Yi Tang, D. Frank Hsu

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Scopus citations

Abstract

The classification of protein structures is essential for their function determination in bioinformatics. The success of the protein structure classification depends on two factors: the computational methods used and the features selected. In this paper, we use a combinatorial fusion analysis technique to facilitate feature selection and combination for improving predictive accuracy in protein structure classification. When applying these criteria to our previous work, the resulting classification has an overall prediction accuracy rate of 87% for four classes and 69.6% for 27 folding categories. These rates are significantly higher than our previous work and demonstrate that combinatorial fusion is a valuable method for protein structure classification.

Original language	English
Title of host publication	Proceedings - BIBE 2005
Subtitle of host publication	5th IEEE Symposium on Bioinformatics and Bioengineering
Pages	311-315
Number of pages	5
DOIs	https://doi.org/10.1109/BIBE.2005.26
State	Published - 2005
Externally published	Yes
Event	BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering - Minneapolis, MN, United States Duration: 19 10 2005 → 21 10 2005

Publication series

Name	Proceedings - BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering
Volume	2005

Conference

Conference	BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering
Country/Territory	United States
City	Minneapolis, MN
Period	19/10/05 → 21/10/05

Access to Document

10.1109/BIBE.2005.26

Cite this

Lin, C. Y., Lin, K. L., Huang, C. D., Chang, H. M., Yang, C. Y., Lin, C. T., Tang, C. Y., & Hsu, D. F. (2005). Feature selection and combination criteria for improving predictive accuracy in protein structure classification. In Proceedings - BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering (pp. 311-315). Article 1544487 (Proceedings - BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering; Vol. 2005). https://doi.org/10.1109/BIBE.2005.26

@inproceedings{cccc51f9e11f4daeb6c97854ea084f99,

title = "Feature selection and combination criteria for improving predictive accuracy in protein structure classification",

abstract = "The classification of protein structures is essential for their function determination in bioinformatics. The success of the protein structure classification depends on two factors: the computational methods used and the features selected. In this paper, we use a combinatorial fusion analysis technique to facilitate feature selection and combination for improving predictive accuracy in protein structure classification. When applying these criteria to our previous work, the resulting classification has an overall prediction accuracy rate of 87\% for four classes and 69.6\% for 27 folding categories. These rates are significantly higher than our previous work and demonstrate that combinatorial fusion is a valuable method for protein structure classification.",

author = "Lin, \{Chun Yuan\} and Lin, \{Ken Li\} and Huang, \{Chuen Der\} and Chang, \{Hsiu Ming\} and Yang, \{Chiao Yun\} and Lin, \{Chin Teng\} and Tang, \{Chuan Yi\} and Hsu, \{D. Frank\}",

year = "2005",

doi = "10.1109/BIBE.2005.26",

language = "英语",

isbn = "0769524761",

series = "Proceedings - BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering",

pages = "311--315",

booktitle = "Proceedings - BIBE 2005",

note = "BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering ; Conference date: 19-10-2005 Through 21-10-2005",

}

Lin, CY, Lin, KL, Huang, CD, Chang, HM, Yang, CY, Lin, CT, Tang, CY & Hsu, DF 2005, Feature selection and combination criteria for improving predictive accuracy in protein structure classification. in Proceedings - BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering., 1544487, Proceedings - BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering, vol. 2005, pp. 311-315, BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering, Minneapolis, MN, United States, 19/10/05. https://doi.org/10.1109/BIBE.2005.26

Feature selection and combination criteria for improving predictive accuracy in protein structure classification. / Lin, Chun Yuan; Lin, Ken Li; Huang, Chuen Der et al.
Proceedings - BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering. 2005. p. 311-315 1544487 (Proceedings - BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering; Vol. 2005).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Feature selection and combination criteria for improving predictive accuracy in protein structure classification

AU - Lin, Chun Yuan

AU - Lin, Ken Li

AU - Huang, Chuen Der

AU - Chang, Hsiu Ming

AU - Yang, Chiao Yun

AU - Lin, Chin Teng

AU - Tang, Chuan Yi

AU - Hsu, D. Frank

PY - 2005

Y1 - 2005

N2 - The classification of protein structures is essential for their function determination in bioinformatics. The success of the protein structure classification depends on two factors: the computational methods used and the features selected. In this paper, we use a combinatorial fusion analysis technique to facilitate feature selection and combination for improving predictive accuracy in protein structure classification. When applying these criteria to our previous work, the resulting classification has an overall prediction accuracy rate of 87% for four classes and 69.6% for 27 folding categories. These rates are significantly higher than our previous work and demonstrate that combinatorial fusion is a valuable method for protein structure classification.

AB - The classification of protein structures is essential for their function determination in bioinformatics. The success of the protein structure classification depends on two factors: the computational methods used and the features selected. In this paper, we use a combinatorial fusion analysis technique to facilitate feature selection and combination for improving predictive accuracy in protein structure classification. When applying these criteria to our previous work, the resulting classification has an overall prediction accuracy rate of 87% for four classes and 69.6% for 27 folding categories. These rates are significantly higher than our previous work and demonstrate that combinatorial fusion is a valuable method for protein structure classification.

UR - https://www.scopus.com/pages/publications/33751173177

U2 - 10.1109/BIBE.2005.26

DO - 10.1109/BIBE.2005.26

M3 - 会议稿件

AN - SCOPUS:33751173177

SN - 0769524761

SN - 9780769524764

T3 - Proceedings - BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering

SP - 311

EP - 315

BT - Proceedings - BIBE 2005

T2 - BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering

Y2 - 19 October 2005 through 21 October 2005

ER -

Lin CY, Lin KL, Huang CD, Chang HM, Yang CY, Lin CT et al. Feature selection and combination criteria for improving predictive accuracy in protein structure classification. In Proceedings - BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering. 2005. p. 311-315. 1544487. (Proceedings - BIBE 2005: 5th IEEE Symposium on Bioinformatics and Bioengineering). doi: 10.1109/BIBE.2005.26

Feature selection and combination criteria for improving predictive accuracy in protein structure classification

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this