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

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

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.
Original 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

    Research areas

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

View graph of relations