Network based subcellular localization prediction for multi-label proteins

Ananda Mohan Mondal, Jhih Rong Lin, Jianjun Hu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Many proteins are sorted to multiple subcellular localizations within the cell. However, computational prediction of multi-location proteins remains a challenging task. Here we applied a logistic regression and diffusion kernel based algorithm NetLoc for predicting multiplex proteins and explored its capability and limitations. Experiment shows that the overall and true success rates for physical protein-protein interaction network are 65% and 41% respectively, and for mixed PPI network these values are 88% and 75% respectively. Our study also showed that the performance of NetLoc in predicting protein localization is limited by the network characteristics such as ratio of the number of co-localized protein-protein interactions (coPPI) to the number of non-co-localized PPI (ncPPI) and the density of annotated coPPI in the network. For a given network with a specific number of proteins, NetLoc performance increases with higher coPPI/ncPPI ratio and higher density of annotated coPPI.

Original languageEnglish (US)
Title of host publication2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011
Pages473-480
Number of pages8
DOIs
StatePublished - Dec 1 2011
Externally publishedYes
Event2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011 - Atlanta, GA, United States
Duration: Nov 12 2011Nov 15 2011

Publication series

Name2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011

Conference

Conference2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011
CountryUnited States
CityAtlanta, GA
Period11/12/1111/15/11

Fingerprint

Labels
Proteins
Protein Interaction Maps
Logistic Models
Logistics

Keywords

  • bioinformatics
  • data mining
  • diffusion kernel
  • multi-label proteins
  • multiplex protein localization
  • multiplex proteins
  • NetLoc
  • network based protein localization
  • protein localization
  • protein subcellular localization

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Mondal, A. M., Lin, J. R., & Hu, J. (2011). Network based subcellular localization prediction for multi-label proteins. In 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011 (pp. 473-480). [6112416] (2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011). https://doi.org/10.1109/BIBMW.2011.6112416

Network based subcellular localization prediction for multi-label proteins. / Mondal, Ananda Mohan; Lin, Jhih Rong; Hu, Jianjun.

2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011. 2011. p. 473-480 6112416 (2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mondal, AM, Lin, JR & Hu, J 2011, Network based subcellular localization prediction for multi-label proteins. in 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011., 6112416, 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011, pp. 473-480, 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011, Atlanta, GA, United States, 11/12/11. https://doi.org/10.1109/BIBMW.2011.6112416
Mondal AM, Lin JR, Hu J. Network based subcellular localization prediction for multi-label proteins. In 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011. 2011. p. 473-480. 6112416. (2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011). https://doi.org/10.1109/BIBMW.2011.6112416
Mondal, Ananda Mohan ; Lin, Jhih Rong ; Hu, Jianjun. / Network based subcellular localization prediction for multi-label proteins. 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011. 2011. pp. 473-480 (2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011).
@inproceedings{7e0f7af4b8074f45a2473bd59b7b99c6,
title = "Network based subcellular localization prediction for multi-label proteins",
abstract = "Many proteins are sorted to multiple subcellular localizations within the cell. However, computational prediction of multi-location proteins remains a challenging task. Here we applied a logistic regression and diffusion kernel based algorithm NetLoc for predicting multiplex proteins and explored its capability and limitations. Experiment shows that the overall and true success rates for physical protein-protein interaction network are 65{\%} and 41{\%} respectively, and for mixed PPI network these values are 88{\%} and 75{\%} respectively. Our study also showed that the performance of NetLoc in predicting protein localization is limited by the network characteristics such as ratio of the number of co-localized protein-protein interactions (coPPI) to the number of non-co-localized PPI (ncPPI) and the density of annotated coPPI in the network. For a given network with a specific number of proteins, NetLoc performance increases with higher coPPI/ncPPI ratio and higher density of annotated coPPI.",
keywords = "bioinformatics, data mining, diffusion kernel, multi-label proteins, multiplex protein localization, multiplex proteins, NetLoc, network based protein localization, protein localization, protein subcellular localization",
author = "Mondal, {Ananda Mohan} and Lin, {Jhih Rong} and Jianjun Hu",
year = "2011",
month = "12",
day = "1",
doi = "10.1109/BIBMW.2011.6112416",
language = "English (US)",
isbn = "9781457716133",
series = "2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011",
pages = "473--480",
booktitle = "2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011",

}

TY - GEN

T1 - Network based subcellular localization prediction for multi-label proteins

AU - Mondal, Ananda Mohan

AU - Lin, Jhih Rong

AU - Hu, Jianjun

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Many proteins are sorted to multiple subcellular localizations within the cell. However, computational prediction of multi-location proteins remains a challenging task. Here we applied a logistic regression and diffusion kernel based algorithm NetLoc for predicting multiplex proteins and explored its capability and limitations. Experiment shows that the overall and true success rates for physical protein-protein interaction network are 65% and 41% respectively, and for mixed PPI network these values are 88% and 75% respectively. Our study also showed that the performance of NetLoc in predicting protein localization is limited by the network characteristics such as ratio of the number of co-localized protein-protein interactions (coPPI) to the number of non-co-localized PPI (ncPPI) and the density of annotated coPPI in the network. For a given network with a specific number of proteins, NetLoc performance increases with higher coPPI/ncPPI ratio and higher density of annotated coPPI.

AB - Many proteins are sorted to multiple subcellular localizations within the cell. However, computational prediction of multi-location proteins remains a challenging task. Here we applied a logistic regression and diffusion kernel based algorithm NetLoc for predicting multiplex proteins and explored its capability and limitations. Experiment shows that the overall and true success rates for physical protein-protein interaction network are 65% and 41% respectively, and for mixed PPI network these values are 88% and 75% respectively. Our study also showed that the performance of NetLoc in predicting protein localization is limited by the network characteristics such as ratio of the number of co-localized protein-protein interactions (coPPI) to the number of non-co-localized PPI (ncPPI) and the density of annotated coPPI in the network. For a given network with a specific number of proteins, NetLoc performance increases with higher coPPI/ncPPI ratio and higher density of annotated coPPI.

KW - bioinformatics

KW - data mining

KW - diffusion kernel

KW - multi-label proteins

KW - multiplex protein localization

KW - multiplex proteins

KW - NetLoc

KW - network based protein localization

KW - protein localization

KW - protein subcellular localization

UR - http://www.scopus.com/inward/record.url?scp=84862929318&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862929318&partnerID=8YFLogxK

U2 - 10.1109/BIBMW.2011.6112416

DO - 10.1109/BIBMW.2011.6112416

M3 - Conference contribution

AN - SCOPUS:84862929318

SN - 9781457716133

T3 - 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011

SP - 473

EP - 480

BT - 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2011

ER -