File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Assessing optimal neural network architecture for identifying disease-associated multi-marker genotypes using a permutation test, and application to calpain 10 polymorphisms associated with diabetes

TitleAssessing optimal neural network architecture for identifying disease-associated multi-marker genotypes using a permutation test, and application to calpain 10 polymorphisms associated with diabetes
Authors
Issue Date2003
PublisherBlackwell Publishing Ltd. The Journal's web site is located at http://www.blackwellpublishing.com/journals/AHG
Citation
Annals Of Human Genetics, 2003, v. 67 n. 4, p. 348-356 How to Cite?
AbstractBiallelic markers, such as single nucleotide polymorphisms (SNPs), provide greater information for localising disease loci when treated as multilocus haplotypes, but often haplotypes are not immediately available from multilocus genotypes in case-control studies. An artificial neural network allows investigation of association between disease phenotype and tightly linked markers without requiring haplotype phase and without modelling any evolutionary history for the disease-related haplotypes. The network assesses whether marker haplotypes differ between cases and controls to the extent that classification of disease status based on multi-marker genotypes is achievable. The network is "trained" to "recognise" affection status based on supplied marker genotypes, and then for each multi-marker genotype it produces outputs which aim to approximate the associated affection status. Next, the genotypes are permuted relative to affection status to produce many random datasets and the process of training and recording of outputs is repeated. The extent to which the ability to predict affection for the real dataset exceeds that for the random datasets measures the statistical significance of the association between multi-marker genotype and affection. This permutation test performs well with simulated case-control datasets, particularly when major gene effects are present. We have explored the effects of systematically varying different network parameters in order to identify their optimal values. We have applied the permutation test to 4 SNPs of the calpain 10 (CAPN10) gene typed in a case-control sample of subjects with type 2 diabetes, impaired glucose tolerance, and controls. We show that the neural network produces more highly significant evidence for association than do single marker tests corrected for the number of markers genotyped. The use of a permutation test could potentially allow conditional analyses which could incorporate known risk factors alongside marker genotypes. Permuting only the marker genotypes relative to affection status and these risk factors would allow the contribution of the markers to disease risk to be independently assessed. © University College London 2003.
Persistent Identifierhttp://hdl.handle.net/10722/175911
ISSN
2015 Impact Factor: 1.889
2015 SCImago Journal Rankings: 1.191
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorNorth, BVen_US
dc.contributor.authorCurtis, Den_US
dc.contributor.authorCassell, PGen_US
dc.contributor.authorHitman, GAen_US
dc.contributor.authorSham, PCen_US
dc.date.accessioned2012-11-26T09:02:24Z-
dc.date.available2012-11-26T09:02:24Z-
dc.date.issued2003en_US
dc.identifier.citationAnnals Of Human Genetics, 2003, v. 67 n. 4, p. 348-356en_US
dc.identifier.issn0003-4800en_US
dc.identifier.urihttp://hdl.handle.net/10722/175911-
dc.description.abstractBiallelic markers, such as single nucleotide polymorphisms (SNPs), provide greater information for localising disease loci when treated as multilocus haplotypes, but often haplotypes are not immediately available from multilocus genotypes in case-control studies. An artificial neural network allows investigation of association between disease phenotype and tightly linked markers without requiring haplotype phase and without modelling any evolutionary history for the disease-related haplotypes. The network assesses whether marker haplotypes differ between cases and controls to the extent that classification of disease status based on multi-marker genotypes is achievable. The network is "trained" to "recognise" affection status based on supplied marker genotypes, and then for each multi-marker genotype it produces outputs which aim to approximate the associated affection status. Next, the genotypes are permuted relative to affection status to produce many random datasets and the process of training and recording of outputs is repeated. The extent to which the ability to predict affection for the real dataset exceeds that for the random datasets measures the statistical significance of the association between multi-marker genotype and affection. This permutation test performs well with simulated case-control datasets, particularly when major gene effects are present. We have explored the effects of systematically varying different network parameters in order to identify their optimal values. We have applied the permutation test to 4 SNPs of the calpain 10 (CAPN10) gene typed in a case-control sample of subjects with type 2 diabetes, impaired glucose tolerance, and controls. We show that the neural network produces more highly significant evidence for association than do single marker tests corrected for the number of markers genotyped. The use of a permutation test could potentially allow conditional analyses which could incorporate known risk factors alongside marker genotypes. Permuting only the marker genotypes relative to affection status and these risk factors would allow the contribution of the markers to disease risk to be independently assessed. © University College London 2003.en_US
dc.languageengen_US
dc.publisherBlackwell Publishing Ltd. The Journal's web site is located at http://www.blackwellpublishing.com/journals/AHGen_US
dc.relation.ispartofAnnals of Human Geneticsen_US
dc.subject.meshCalpain - Geneticsen_US
dc.subject.meshCase-Control Studiesen_US
dc.subject.meshComputer Simulationen_US
dc.subject.meshDiabetes Mellitus, Type 2 - Geneticsen_US
dc.subject.meshGenetic Testing - Methodsen_US
dc.subject.meshGenotypeen_US
dc.subject.meshHaplotypes - Geneticsen_US
dc.subject.meshHumansen_US
dc.subject.meshIndiaen_US
dc.subject.meshNeural Networks (Computer)en_US
dc.subject.meshPolymorphism, Genetic - Geneticsen_US
dc.titleAssessing optimal neural network architecture for identifying disease-associated multi-marker genotypes using a permutation test, and application to calpain 10 polymorphisms associated with diabetesen_US
dc.typeArticleen_US
dc.identifier.emailSham, PC: pcsham@hku.hken_US
dc.identifier.authoritySham, PC=rp00459en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1046/j.1469-1809.2003.00030.xen_US
dc.identifier.pmid12914569-
dc.identifier.scopuseid_2-s2.0-1542330229en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-1542330229&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume67en_US
dc.identifier.issue4en_US
dc.identifier.spage348en_US
dc.identifier.epage356en_US
dc.identifier.isiWOS:000184420300006-
dc.publisher.placeUnited Kingdomen_US
dc.identifier.scopusauthoridNorth, BV=7005058731en_US
dc.identifier.scopusauthoridCurtis, D=14633020700en_US
dc.identifier.scopusauthoridCassell, PG=7004546189en_US
dc.identifier.scopusauthoridHitman, GA=7006269069en_US
dc.identifier.scopusauthoridSham, PC=34573429300en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats