Show simple item record

dc.contributor.authorNg, Shu-Kay
dc.contributor.authorMcLachlan, Geoffrey J
dc.contributor.editorLi, GZ
dc.contributor.editorKim, S
dc.contributor.editorHughes, M
dc.contributor.editorMcLachlan, G
dc.contributor.editorSun, H
dc.contributor.editorHu, X
dc.contributor.editorRessom, H
dc.contributor.editorLiu, B
dc.contributor.editorLiebman, M
dc.date.accessioned2017-05-03T13:14:16Z
dc.date.available2017-05-03T13:14:16Z
dc.date.issued2013
dc.date.modified2014-05-30T03:20:20Z
dc.identifier.isbn978-1-4799-1310-7
dc.identifier.issn2156-1125
dc.identifier.refurihttp://bibm2013.tongji.edu.cn/
dc.identifier.doi10.1109/BIBM.2013.6732501
dc.identifier.urihttp://hdl.handle.net/10072/59674
dc.description.abstractThe identification of genes that have different expression levels in a known number of distinct disease phenotypes contributes significantly to the construction of a discriminant rule (classifier) for predicting the class of origin of an unclassified tissue sample. Existing methods for detecting differentially-expressed genes are mainly based on multiple hypothesis tests. Clustering-based approaches either work on gene-specific summary statistics or reduced forms of gene-expression profiles. Advancement in clustering-based approaches that work on full profiling data has been minor, due to the methodological barriers for assessing differential expression between tissue classes from identified clusters of genes. In this paper, we adopt a clustering-based approach, which works on full gene-expression profiles and draws inference on differential expression using weighted contrasts of mixed effects. With a real published gene-expression data set, we show that the proposed clustering-based approach can provide a list of marker genes that improves the prediction of disease outcomes. Comparisons with existing methods are also provided using simulated data.
dc.description.peerreviewedYes
dc.description.publicationstatusYes
dc.languageEnglish
dc.publisherIEEE
dc.publisher.placeUnited States
dc.relation.ispartofstudentpublicationN
dc.relation.ispartofconferencenameIEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM)
dc.relation.ispartofconferencetitle2013 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM)
dc.relation.ispartofdatefrom2013-12-18
dc.relation.ispartofdateto2013-12-21
dc.relation.ispartoflocationShanghai, PEOPLES R CHINA
dc.rights.retentionY
dc.subject.fieldofresearchcode270203
dc.titleUsing cluster analysis to improve gene selection in the formation of discriminant rules for the prediction of disease outcomes
dc.typeConference output
dc.type.descriptionE1 - Conferences
dc.type.codeE - Conference Publications
gro.facultyGriffith Health, School of Medicine
gro.hasfulltextNo Full Text
gro.griffith.authorNg, Shu Kay Angus


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record