Predicting Gram-positive bacterial protein subcellular localization based on localization motifs

Yinxia Hu; Tonghua Li; Jiangming Sun; Shengnan Tang; Wenwei Xiong; Dapeng Li; Guanyan Chen; Peisheng Cong

doi:10.1016/j.jtbi.2012.05.031

Predicting Gram-positive bacterial protein subcellular localization based on localization motifs

Yinxia Hu, Tonghua Li, Jiangming Sun, Shengnan Tang, Wenwei Xiong, Dapeng Li, Guanyan Chen, Peisheng Cong

Tongji University

Research output: Contribution to journal › Article › peer-review

Abstract

The subcellular localization of proteins is closely related to their functions. In this work, we propose a novel approach based on localization motifs to improve the accuracy of predicting subcellular localization of Gram-positive bacterial proteins. Our approach performed well on a five-fold cross validation with an overall success rate of 89.5%. Besides, the overall success rate of an independent testing dataset was 97.7%. Moreover, our approach was tested using a new experimentally-determined set of Gram-positive bacteria proteins and achieved an overall success rate of 96.3%.

Original language	English
Pages (from-to)	135-140
Journal	Journal of Theoretical Biology
Volume	308
DOIs	https://doi.org/10.1016/j.jtbi.2012.05.031
Publication status	Published - 2012 Sept 7
Externally published	Yes

Bibliographical note

Funding Information:
The authors would like to thank financial support by the National Natural Science Foundation of China ( 20675057 , 20705024 ).

Free keywords

Motif finding
Position-specific frequencies encoding
Subcellular location prediction
Support vector machine (SVM)

Access to Document

10.1016/j.jtbi.2012.05.031

Cite this

@article{8238ff44b063431c9a8d685a0034ebf8,

title = "Predicting Gram-positive bacterial protein subcellular localization based on localization motifs",

abstract = "The subcellular localization of proteins is closely related to their functions. In this work, we propose a novel approach based on localization motifs to improve the accuracy of predicting subcellular localization of Gram-positive bacterial proteins. Our approach performed well on a five-fold cross validation with an overall success rate of 89.5\%. Besides, the overall success rate of an independent testing dataset was 97.7\%. Moreover, our approach was tested using a new experimentally-determined set of Gram-positive bacteria proteins and achieved an overall success rate of 96.3\%.",

keywords = "Motif finding, Position-specific frequencies encoding, Subcellular location prediction, Support vector machine (SVM)",

author = "Yinxia Hu and Tonghua Li and Jiangming Sun and Shengnan Tang and Wenwei Xiong and Dapeng Li and Guanyan Chen and Peisheng Cong",

note = "Funding Information: The authors would like to thank financial support by the National Natural Science Foundation of China ( 20675057 , 20705024 ). ",

year = "2012",

month = sep,

day = "7",

doi = "10.1016/j.jtbi.2012.05.031",

language = "English",

volume = "308",

pages = "135--140",

journal = "Journal of Theoretical Biology",

issn = "0022-5193",

publisher = "Academic Press",

}

TY - JOUR

T1 - Predicting Gram-positive bacterial protein subcellular localization based on localization motifs

AU - Hu, Yinxia

AU - Li, Tonghua

AU - Sun, Jiangming

AU - Tang, Shengnan

AU - Xiong, Wenwei

AU - Li, Dapeng

AU - Chen, Guanyan

AU - Cong, Peisheng

N1 - Funding Information: The authors would like to thank financial support by the National Natural Science Foundation of China ( 20675057 , 20705024 ).

PY - 2012/9/7

Y1 - 2012/9/7

N2 - The subcellular localization of proteins is closely related to their functions. In this work, we propose a novel approach based on localization motifs to improve the accuracy of predicting subcellular localization of Gram-positive bacterial proteins. Our approach performed well on a five-fold cross validation with an overall success rate of 89.5%. Besides, the overall success rate of an independent testing dataset was 97.7%. Moreover, our approach was tested using a new experimentally-determined set of Gram-positive bacteria proteins and achieved an overall success rate of 96.3%.

AB - The subcellular localization of proteins is closely related to their functions. In this work, we propose a novel approach based on localization motifs to improve the accuracy of predicting subcellular localization of Gram-positive bacterial proteins. Our approach performed well on a five-fold cross validation with an overall success rate of 89.5%. Besides, the overall success rate of an independent testing dataset was 97.7%. Moreover, our approach was tested using a new experimentally-determined set of Gram-positive bacteria proteins and achieved an overall success rate of 96.3%.

KW - Motif finding

KW - Position-specific frequencies encoding

KW - Subcellular location prediction

KW - Support vector machine (SVM)

UR - https://www.scopus.com/pages/publications/84862677130

U2 - 10.1016/j.jtbi.2012.05.031

DO - 10.1016/j.jtbi.2012.05.031

M3 - Article

C2 - 22683368

AN - SCOPUS:84862677130

SN - 0022-5193

VL - 308

SP - 135

EP - 140

JO - Journal of Theoretical Biology

JF - Journal of Theoretical Biology

ER -

Predicting Gram-positive bacterial protein subcellular localization based on localization motifs

Abstract

Bibliographical note

Free keywords

Access to Document

Other files and links

Fingerprint

Cite this