Learning condition-dependent dynamical PPI networks from conflict-sensitive phosphorylation dynamics

Qiong Cheng, Mitsunori Ogihara, Vineet Gupta

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

Abstract

An important issue in protein-protein interaction network studies is the identification of interaction dynamics. Two factors contribute to the dynamics. One, not all proteins may be expressed in a given cell, and two, competition may exist among multiple proteins for a particular protein domain. Taking into account these two factors, we propose a novel approach to predict protein-protein interaction network dynamics by learning from conflict-sensitive phosphorylation dynamics. We built a training model from conflict-sensitive phosphorylation dynamics. In this model, each node is not an individual protein but a protein-protein pair and is labeled with terms representing conditions in which the interaction should be observed. We mapped the protein pairs in a vector space, built hyper-edges over the interaction nodes, and developed rank-like SVM with Laplacian regularizers for PPI network dynamics prediction. We also employed the standard F1 measure for evaluating the effectiveness of classification results.

Original languageEnglish (US)
Title of host publicationProceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
Pages309-312
Number of pages4
DOIs
StatePublished - 2011
Event2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011 - Atlanta, GA, United States
Duration: Nov 12 2011Nov 15 2011

Other

Other2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
CountryUnited States
CityAtlanta, GA
Period11/12/1111/15/11

Fingerprint

Phosphorylation
Learning
Proteins
Protein Interaction Maps
Conflict (Psychology)
Vector spaces

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Cheng, Q., Ogihara, M., & Gupta, V. (2011). Learning condition-dependent dynamical PPI networks from conflict-sensitive phosphorylation dynamics. In Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011 (pp. 309-312). [6120458] https://doi.org/10.1109/BIBM.2011.127

Learning condition-dependent dynamical PPI networks from conflict-sensitive phosphorylation dynamics. / Cheng, Qiong; Ogihara, Mitsunori; Gupta, Vineet.

Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. p. 309-312 6120458.

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

Cheng, Q, Ogihara, M & Gupta, V 2011, Learning condition-dependent dynamical PPI networks from conflict-sensitive phosphorylation dynamics. in Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011., 6120458, pp. 309-312, 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011, Atlanta, GA, United States, 11/12/11. https://doi.org/10.1109/BIBM.2011.127
Cheng Q, Ogihara M, Gupta V. Learning condition-dependent dynamical PPI networks from conflict-sensitive phosphorylation dynamics. In Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. p. 309-312. 6120458 https://doi.org/10.1109/BIBM.2011.127
Cheng, Qiong ; Ogihara, Mitsunori ; Gupta, Vineet. / Learning condition-dependent dynamical PPI networks from conflict-sensitive phosphorylation dynamics. Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. pp. 309-312
@inproceedings{3bee2cf697ef4ee29a5674b515672009,
title = "Learning condition-dependent dynamical PPI networks from conflict-sensitive phosphorylation dynamics",
abstract = "An important issue in protein-protein interaction network studies is the identification of interaction dynamics. Two factors contribute to the dynamics. One, not all proteins may be expressed in a given cell, and two, competition may exist among multiple proteins for a particular protein domain. Taking into account these two factors, we propose a novel approach to predict protein-protein interaction network dynamics by learning from conflict-sensitive phosphorylation dynamics. We built a training model from conflict-sensitive phosphorylation dynamics. In this model, each node is not an individual protein but a protein-protein pair and is labeled with terms representing conditions in which the interaction should be observed. We mapped the protein pairs in a vector space, built hyper-edges over the interaction nodes, and developed rank-like SVM with Laplacian regularizers for PPI network dynamics prediction. We also employed the standard F1 measure for evaluating the effectiveness of classification results.",
author = "Qiong Cheng and Mitsunori Ogihara and Vineet Gupta",
year = "2011",
doi = "10.1109/BIBM.2011.127",
language = "English (US)",
isbn = "9780769545745",
pages = "309--312",
booktitle = "Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011",

}

TY - GEN

T1 - Learning condition-dependent dynamical PPI networks from conflict-sensitive phosphorylation dynamics

AU - Cheng, Qiong

AU - Ogihara, Mitsunori

AU - Gupta, Vineet

PY - 2011

Y1 - 2011

N2 - An important issue in protein-protein interaction network studies is the identification of interaction dynamics. Two factors contribute to the dynamics. One, not all proteins may be expressed in a given cell, and two, competition may exist among multiple proteins for a particular protein domain. Taking into account these two factors, we propose a novel approach to predict protein-protein interaction network dynamics by learning from conflict-sensitive phosphorylation dynamics. We built a training model from conflict-sensitive phosphorylation dynamics. In this model, each node is not an individual protein but a protein-protein pair and is labeled with terms representing conditions in which the interaction should be observed. We mapped the protein pairs in a vector space, built hyper-edges over the interaction nodes, and developed rank-like SVM with Laplacian regularizers for PPI network dynamics prediction. We also employed the standard F1 measure for evaluating the effectiveness of classification results.

AB - An important issue in protein-protein interaction network studies is the identification of interaction dynamics. Two factors contribute to the dynamics. One, not all proteins may be expressed in a given cell, and two, competition may exist among multiple proteins for a particular protein domain. Taking into account these two factors, we propose a novel approach to predict protein-protein interaction network dynamics by learning from conflict-sensitive phosphorylation dynamics. We built a training model from conflict-sensitive phosphorylation dynamics. In this model, each node is not an individual protein but a protein-protein pair and is labeled with terms representing conditions in which the interaction should be observed. We mapped the protein pairs in a vector space, built hyper-edges over the interaction nodes, and developed rank-like SVM with Laplacian regularizers for PPI network dynamics prediction. We also employed the standard F1 measure for evaluating the effectiveness of classification results.

UR - http://www.scopus.com/inward/record.url?scp=84856032939&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856032939&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2011.127

DO - 10.1109/BIBM.2011.127

M3 - Conference contribution

SN - 9780769545745

SP - 309

EP - 312

BT - Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011

ER -