Local pre-processing for node classification in networks: application in protein-protein interaction

Christopher Eric Foley, Sana Mohammad M Al Azwari, Mark Dufton, Isla Ross, John Wilson

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

Abstract

Network modelling provides an increasingly popular conceptualisation in a wide range of domains, including the analysis of protein structure. Typical approaches to analysis model parameter values at nodes within the network. The spherical locality around a node provides a microenvironment that can be used to characterise an area of a network rather than a particular point within it. Microenvironments that centre on the nodes in a protein chain can be used to quantify parameters that are related to protein functionality. They also permit particular patterns of such parameters in node-centred microenvironments to be used to locate sites of particular interest. This paper evaluates an approach to index generation that seeks to rapidly construct microenvironment data. The results show that index generation performs best when the radius of microenvironments matches the granularity of the index. Results are presented to show that such microenvironments improve the utility of protein chain parameters in classifying the structural characteristics of nodes using both support vector machines and neural networks.
LanguageEnglish
Title of host publicationInformation Technology in Bio- and Medical Informatics
Subtitle of host publication4th International Conference, ITBAM 2013, Prague, Czech Republic, August 28, 2013. Proceedings
EditorsM. Bursa, S. Khuri, M.E. Renda
Place of PublicationHeidelberg
Pages32-46
Number of pages15
DOIs
StatePublished - 14 Aug 2013

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume8060
ISSN (Print)0302-9743

Fingerprint

Proteins
Processing
Support vector machines
Neural networks

Keywords

  • network classification
  • protein structure
  • computational biology/bioinformatics
  • health informatics
  • information systems
  • communication service
  • computer applications

Cite this

Foley, C. E., Al Azwari, S. M. M., Dufton, M., Ross, I., & Wilson, J. (2013). Local pre-processing for node classification in networks: application in protein-protein interaction. In M. Bursa, S. Khuri, & M. E. Renda (Eds.), Information Technology in Bio- and Medical Informatics: 4th International Conference, ITBAM 2013, Prague, Czech Republic, August 28, 2013. Proceedings (pp. 32-46). (Lecture Notes in Computer Science; Vol. 8060). Heidelberg. DOI: 10.1007/978-3-642-40093-3_3
Foley, Christopher Eric ; Al Azwari, Sana Mohammad M ; Dufton, Mark ; Ross, Isla ; Wilson, John. / Local pre-processing for node classification in networks : application in protein-protein interaction. Information Technology in Bio- and Medical Informatics: 4th International Conference, ITBAM 2013, Prague, Czech Republic, August 28, 2013. Proceedings. editor / M. Bursa ; S. Khuri ; M.E. Renda. Heidelberg, 2013. pp. 32-46 (Lecture Notes in Computer Science).
@inproceedings{c5277eb7d25d420dbec5869c0fdb4ce4,
title = "Local pre-processing for node classification in networks: application in protein-protein interaction",
abstract = "Network modelling provides an increasingly popular conceptualisation in a wide range of domains, including the analysis of protein structure. Typical approaches to analysis model parameter values at nodes within the network. The spherical locality around a node provides a microenvironment that can be used to characterise an area of a network rather than a particular point within it. Microenvironments that centre on the nodes in a protein chain can be used to quantify parameters that are related to protein functionality. They also permit particular patterns of such parameters in node-centred microenvironments to be used to locate sites of particular interest. This paper evaluates an approach to index generation that seeks to rapidly construct microenvironment data. The results show that index generation performs best when the radius of microenvironments matches the granularity of the index. Results are presented to show that such microenvironments improve the utility of protein chain parameters in classifying the structural characteristics of nodes using both support vector machines and neural networks.",
keywords = "network classification, protein structure, computational biology/bioinformatics, health informatics, information systems, communication service, computer applications",
author = "Foley, {Christopher Eric} and {Al Azwari}, {Sana Mohammad M} and Mark Dufton and Isla Ross and John Wilson",
year = "2013",
month = "8",
day = "14",
doi = "10.1007/978-3-642-40093-3_3",
language = "English",
isbn = "9783642400926",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "32--46",
editor = "M. Bursa and S. Khuri and M.E. Renda",
booktitle = "Information Technology in Bio- and Medical Informatics",

}

Foley, CE, Al Azwari, SMM, Dufton, M, Ross, I & Wilson, J 2013, Local pre-processing for node classification in networks: application in protein-protein interaction. in M Bursa, S Khuri & ME Renda (eds), Information Technology in Bio- and Medical Informatics: 4th International Conference, ITBAM 2013, Prague, Czech Republic, August 28, 2013. Proceedings. Lecture Notes in Computer Science, vol. 8060, Heidelberg, pp. 32-46. DOI: 10.1007/978-3-642-40093-3_3

Local pre-processing for node classification in networks : application in protein-protein interaction. / Foley, Christopher Eric; Al Azwari, Sana Mohammad M; Dufton, Mark; Ross, Isla; Wilson, John.

Information Technology in Bio- and Medical Informatics: 4th International Conference, ITBAM 2013, Prague, Czech Republic, August 28, 2013. Proceedings. ed. / M. Bursa; S. Khuri; M.E. Renda. Heidelberg, 2013. p. 32-46 (Lecture Notes in Computer Science; Vol. 8060).

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

TY - GEN

T1 - Local pre-processing for node classification in networks

T2 - application in protein-protein interaction

AU - Foley,Christopher Eric

AU - Al Azwari,Sana Mohammad M

AU - Dufton,Mark

AU - Ross,Isla

AU - Wilson,John

PY - 2013/8/14

Y1 - 2013/8/14

N2 - Network modelling provides an increasingly popular conceptualisation in a wide range of domains, including the analysis of protein structure. Typical approaches to analysis model parameter values at nodes within the network. The spherical locality around a node provides a microenvironment that can be used to characterise an area of a network rather than a particular point within it. Microenvironments that centre on the nodes in a protein chain can be used to quantify parameters that are related to protein functionality. They also permit particular patterns of such parameters in node-centred microenvironments to be used to locate sites of particular interest. This paper evaluates an approach to index generation that seeks to rapidly construct microenvironment data. The results show that index generation performs best when the radius of microenvironments matches the granularity of the index. Results are presented to show that such microenvironments improve the utility of protein chain parameters in classifying the structural characteristics of nodes using both support vector machines and neural networks.

AB - Network modelling provides an increasingly popular conceptualisation in a wide range of domains, including the analysis of protein structure. Typical approaches to analysis model parameter values at nodes within the network. The spherical locality around a node provides a microenvironment that can be used to characterise an area of a network rather than a particular point within it. Microenvironments that centre on the nodes in a protein chain can be used to quantify parameters that are related to protein functionality. They also permit particular patterns of such parameters in node-centred microenvironments to be used to locate sites of particular interest. This paper evaluates an approach to index generation that seeks to rapidly construct microenvironment data. The results show that index generation performs best when the radius of microenvironments matches the granularity of the index. Results are presented to show that such microenvironments improve the utility of protein chain parameters in classifying the structural characteristics of nodes using both support vector machines and neural networks.

KW - network classification

KW - protein structure

KW - computational biology/bioinformatics

KW - health informatics

KW - information systems

KW - communication service

KW - computer applications

UR - http://www.scopus.com/inward/record.url?scp=84885202052&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-40093-3_3

DO - 10.1007/978-3-642-40093-3_3

M3 - Conference contribution

SN - 9783642400926

T3 - Lecture Notes in Computer Science

SP - 32

EP - 46

BT - Information Technology in Bio- and Medical Informatics

CY - Heidelberg

ER -

Foley CE, Al Azwari SMM, Dufton M, Ross I, Wilson J. Local pre-processing for node classification in networks: application in protein-protein interaction. In Bursa M, Khuri S, Renda ME, editors, Information Technology in Bio- and Medical Informatics: 4th International Conference, ITBAM 2013, Prague, Czech Republic, August 28, 2013. Proceedings. Heidelberg. 2013. p. 32-46. (Lecture Notes in Computer Science). Available from, DOI: 10.1007/978-3-642-40093-3_3