Machine learning approaches for the discovery of gene-gene interactions in disease data
Machine learning approaches for the discovery of gene-gene interactions in disease data
Because of the complexity of gene-phenotype relationships machine learning approaches have considerable appeal as a strategy for modelling interactions. A number of such methods have been developed and applied in recent years with somemodest success. Progress is hampered by the challenges presented by the complexity of the disease genetic data, including phenotypic and genetic heterogeneity, polygenic forms of inheritance and variable penetrance, combined with the analytical and computational issues arising from the enormous number of potential interactions. We review here recent and current approaches focusing, wherever possible, on applications to real data (particularly in the context of genome-wide association studies) and looking ahead to the further challenges posed by next generation sequencing data.
Gene-gene interaction, Genome-wide association study, Machine learning, Multifactor-dimensionality reduction, Random forest, Support vector machines
251-260
Upstill-Goddard, Rosanna
db6c4d69-2a08-4185-9fc8-cad65f27dde6
Eccles, Diana
5b59bc73-11c9-4cf0-a9d5-7a8e523eee23
Fliege, Joerg
54978787-a271-4f70-8494-3c701c893d98
Collins, Andrew
7daa83eb-0b21-43b2-af1a-e38fb36e2a64
1 March 2013
Upstill-Goddard, Rosanna
db6c4d69-2a08-4185-9fc8-cad65f27dde6
Eccles, Diana
5b59bc73-11c9-4cf0-a9d5-7a8e523eee23
Fliege, Joerg
54978787-a271-4f70-8494-3c701c893d98
Collins, Andrew
7daa83eb-0b21-43b2-af1a-e38fb36e2a64
Upstill-Goddard, Rosanna, Eccles, Diana, Fliege, Joerg and Collins, Andrew
(2013)
Machine learning approaches for the discovery of gene-gene interactions in disease data.
Briefings in Bioinformatics, 14 (2), .
(doi:10.1093/bib/bbs024).
Abstract
Because of the complexity of gene-phenotype relationships machine learning approaches have considerable appeal as a strategy for modelling interactions. A number of such methods have been developed and applied in recent years with somemodest success. Progress is hampered by the challenges presented by the complexity of the disease genetic data, including phenotypic and genetic heterogeneity, polygenic forms of inheritance and variable penetrance, combined with the analytical and computational issues arising from the enormous number of potential interactions. We review here recent and current approaches focusing, wherever possible, on applications to real data (particularly in the context of genome-wide association studies) and looking ahead to the further challenges posed by next generation sequencing data.
This record has no associated files available for download.
More information
Accepted/In Press date: 2012
Published date: 1 March 2013
Keywords:
Gene-gene interaction, Genome-wide association study, Machine learning, Multifactor-dimensionality reduction, Random forest, Support vector machines
Organisations:
Faculty of Medicine, Operational Research
Identifiers
Local EPrints ID: 337228
URI: http://eprints.soton.ac.uk/id/eprint/337228
ISSN: 1467-5463
PURE UUID: e1954fac-6b52-4c5f-bfd0-2555d3722933
Catalogue record
Date deposited: 20 Apr 2012 10:38
Last modified: 15 Mar 2024 03:30
Export record
Altmetrics
Contributors
Author:
Rosanna Upstill-Goddard
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
