A double-SVM classification system for single and multiple-subcellular localizations of yeast proteins using sequence motifs

Su Zhang; Wei Yang; Ning Wu; Yazhu Chen; Hongtao Lu; Zhizhou Zhang

doi:10.1109/ICIA.2007.4295720

A double-SVM classification system for single and multiple-subcellular localizations of yeast proteins using sequence motifs

Su Zhang^*
, Wei Yang
, Ning Wu
, Yazhu Chen
, Hongtao Lu
, Zhizhou Zhang

^*Corresponding author for this work

Shanghai Jiao Tong University
Tianjin University of Science & Technology

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

2 Scopus citations

Abstract

The cellular localization site and the potential functionality of a protein are closely related. In this paper, we develop a novel Double-SVM Classification System for predicting the subcellular localization sites of the proteins. First, a set of features are made from the occurrence frequency of sequence motifs. Then discriminant features are selected by I-RELIEF and used as the inputs of the support vector machine (SVM) for classification. The two classes are single and multiple-subcellular localizations. Due to the large size difference among the protein sequences, we set two SVMs, one for the shorter sequences and the other for the longer ones. This system is applied to predict the subcellular localization sites of Yeast proteins. The experimental result shows that the testing accuracy of the system is 66%, which is higher than that of the traditional single-SVM model.

Original language	English
Title of host publication	2007 International Conference on Information Acquisition, ICIA
Pages	173-176
Number of pages	4
DOIs	https://doi.org/10.1109/ICIA.2007.4295720
State	Published - 2007
Externally published	Yes
Event	International Conference on Information Acquisition, ICIA 2007 - Jeju City, Korea, Republic of Duration: 9 Jul 2007 → 11 Jul 2007

Publication series

Name	Proceedings of the 2007 International Conference on Information Acquisition, ICIA

Conference

Conference	International Conference on Information Acquisition, ICIA 2007
Country/Territory	Korea, Republic of
City	Jeju City
Period	9/07/07 → 11/07/07

Keywords

Protein subcellular localization
Sequence motif
Support vector machine

Access to Document

10.1109/ICIA.2007.4295720

Cite this

Zhang, S., Yang, W., Wu, N., Chen, Y., Lu, H., & Zhang, Z. (2007). A double-SVM classification system for single and multiple-subcellular localizations of yeast proteins using sequence motifs. In 2007 International Conference on Information Acquisition, ICIA (pp. 173-176). Article 4295720 (Proceedings of the 2007 International Conference on Information Acquisition, ICIA). https://doi.org/10.1109/ICIA.2007.4295720

@inproceedings{be447908d2964977a1fa5ff8e8032fc6,

title = "A double-SVM classification system for single and multiple-subcellular localizations of yeast proteins using sequence motifs",

abstract = "The cellular localization site and the potential functionality of a protein are closely related. In this paper, we develop a novel Double-SVM Classification System for predicting the subcellular localization sites of the proteins. First, a set of features are made from the occurrence frequency of sequence motifs. Then discriminant features are selected by I-RELIEF and used as the inputs of the support vector machine (SVM) for classification. The two classes are single and multiple-subcellular localizations. Due to the large size difference among the protein sequences, we set two SVMs, one for the shorter sequences and the other for the longer ones. This system is applied to predict the subcellular localization sites of Yeast proteins. The experimental result shows that the testing accuracy of the system is 66\%, which is higher than that of the traditional single-SVM model.",

keywords = "Protein subcellular localization, Sequence motif, Support vector machine",

author = "Su Zhang and Wei Yang and Ning Wu and Yazhu Chen and Hongtao Lu and Zhizhou Zhang",

year = "2007",

doi = "10.1109/ICIA.2007.4295720",

language = "英语",

isbn = "1424412196",

series = "Proceedings of the 2007 International Conference on Information Acquisition, ICIA",

pages = "173--176",

booktitle = "2007 International Conference on Information Acquisition, ICIA",

note = "International Conference on Information Acquisition, ICIA 2007 ; Conference date: 09-07-2007 Through 11-07-2007",

}

Zhang, S, Yang, W, Wu, N, Chen, Y, Lu, H & Zhang, Z 2007, A double-SVM classification system for single and multiple-subcellular localizations of yeast proteins using sequence motifs. in 2007 International Conference on Information Acquisition, ICIA., 4295720, Proceedings of the 2007 International Conference on Information Acquisition, ICIA, pp. 173-176, International Conference on Information Acquisition, ICIA 2007, Jeju City, Korea, Republic of, 9/07/07. https://doi.org/10.1109/ICIA.2007.4295720

A double-SVM classification system for single and multiple-subcellular localizations of yeast proteins using sequence motifs. / Zhang, Su; Yang, Wei; Wu, Ning et al.
2007 International Conference on Information Acquisition, ICIA. 2007. p. 173-176 4295720 (Proceedings of the 2007 International Conference on Information Acquisition, ICIA).

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

TY - GEN

T1 - A double-SVM classification system for single and multiple-subcellular localizations of yeast proteins using sequence motifs

AU - Zhang, Su

AU - Yang, Wei

AU - Wu, Ning

AU - Chen, Yazhu

AU - Lu, Hongtao

AU - Zhang, Zhizhou

PY - 2007

Y1 - 2007

N2 - The cellular localization site and the potential functionality of a protein are closely related. In this paper, we develop a novel Double-SVM Classification System for predicting the subcellular localization sites of the proteins. First, a set of features are made from the occurrence frequency of sequence motifs. Then discriminant features are selected by I-RELIEF and used as the inputs of the support vector machine (SVM) for classification. The two classes are single and multiple-subcellular localizations. Due to the large size difference among the protein sequences, we set two SVMs, one for the shorter sequences and the other for the longer ones. This system is applied to predict the subcellular localization sites of Yeast proteins. The experimental result shows that the testing accuracy of the system is 66%, which is higher than that of the traditional single-SVM model.

AB - The cellular localization site and the potential functionality of a protein are closely related. In this paper, we develop a novel Double-SVM Classification System for predicting the subcellular localization sites of the proteins. First, a set of features are made from the occurrence frequency of sequence motifs. Then discriminant features are selected by I-RELIEF and used as the inputs of the support vector machine (SVM) for classification. The two classes are single and multiple-subcellular localizations. Due to the large size difference among the protein sequences, we set two SVMs, one for the shorter sequences and the other for the longer ones. This system is applied to predict the subcellular localization sites of Yeast proteins. The experimental result shows that the testing accuracy of the system is 66%, which is higher than that of the traditional single-SVM model.

KW - Protein subcellular localization

KW - Sequence motif

KW - Support vector machine

UR - https://www.scopus.com/pages/publications/47349099636

U2 - 10.1109/ICIA.2007.4295720

DO - 10.1109/ICIA.2007.4295720

M3 - 会议稿件

AN - SCOPUS:47349099636

SN - 1424412196

SN - 9781424412198

T3 - Proceedings of the 2007 International Conference on Information Acquisition, ICIA

SP - 173

EP - 176

BT - 2007 International Conference on Information Acquisition, ICIA

T2 - International Conference on Information Acquisition, ICIA 2007

Y2 - 9 July 2007 through 11 July 2007

ER -

Zhang S, Yang W, Wu N, Chen Y, Lu H, Zhang Z. A double-SVM classification system for single and multiple-subcellular localizations of yeast proteins using sequence motifs. In 2007 International Conference on Information Acquisition, ICIA. 2007. p. 173-176. 4295720. (Proceedings of the 2007 International Conference on Information Acquisition, ICIA). doi: 10.1109/ICIA.2007.4295720

A double-SVM classification system for single and multiple-subcellular localizations of yeast proteins using sequence motifs

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this