Predictive modeling of schizophrenia from genomic data: Comparison of polygenic risk score with kernel support vector machines approach.
polygenic risk score
schizophrenia
support vector machines
Journal
American journal of medical genetics. Part B, Neuropsychiatric genetics : the official publication of the International Society of Psychiatric Genetics
ISSN: 1552-485X
Titre abrégé: Am J Med Genet B Neuropsychiatr Genet
Pays: United States
ID NLM: 101235742
Informations de publication
Date de publication:
01 2019
01 2019
Historique:
received:
20
07
2018
revised:
03
09
2018
accepted:
09
11
2018
pubmed:
6
12
2018
medline:
10
3
2020
entrez:
6
12
2018
Statut:
ppublish
Résumé
A major controversy in psychiatric genetics is whether nonadditive genetic interaction effects contribute to the risk of highly polygenic disorders. We applied a support vector machines (SVMs) approach, which is capable of building linear and nonlinear models using kernel methods, to classify cases from controls in a large schizophrenia case-control sample of 11,853 subjects (5,554 cases and 6,299 controls) and compared its prediction accuracy with the polygenic risk score (PRS) approach. We also investigated whether SVMs are a suitable approach to detecting nonlinear genetic effects, that is, interactions. We found that PRS provided more accurate case/control classification than either linear or nonlinear SVMs, and give a tentative explanation why PRS outperforms both multivariate regression and linear kernel SVMs. In addition, we observe that nonlinear kernel SVMs showed higher classification accuracy than linear SVMs when a large number of SNPs are entered into the model. We conclude that SVMs are a potential tool for assessing the presence of interactions, prior to searching for them explicitly.
Identifiants
pubmed: 30516002
doi: 10.1002/ajmg.b.32705
pmc: PMC6492016
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
80-85Subventions
Organisme : Medical Research Council
ID : MR/L010305/1
Pays : United Kingdom
Organisme : Medical Research Council
ID : MR/L023784/2
Pays : United Kingdom
Organisme : Medical Research Council
ID : MR/P005748/1
Pays : United Kingdom
Organisme : Medical Research Council
ID : G0800509
Pays : United Kingdom
Informations de copyright
© 2018 The Authors. American Journal of Medical Genetics Part B: Neuropsychiatric Genetics published by Wiley Periodicals, Inc.
Références
Bioinformatics. 2011 Jun 1;27(11):1462-5
pubmed: 21471009
BMC Bioinformatics. 2004 Sep 01;5:120
pubmed: 15339344
Nat Rev Genet. 2009 Jun;10(6):392-404
pubmed: 19434077
Nature. 2014 Jul 24;511(7510):421-7
pubmed: 25056061
Genet Epidemiol. 2012 Feb;36(2):88-98
pubmed: 22851472
Trends Genet. 2018 Apr;34(4):301-312
pubmed: 29331490
Genet Epidemiol. 2018 Jun;42(4):366-377
pubmed: 29532500
Eur J Hum Genet. 2008 Feb;16(2):229-35
pubmed: 17971837
PLoS One. 2011 May 12;6(5):e14802
pubmed: 21589856
Nature. 2009 Aug 6;460(7256):748-52
pubmed: 19571811
Brain. 2015 Dec;138(Pt 12):3673-84
pubmed: 26490334
Am J Med Genet B Neuropsychiatr Genet. 2019 Jan;180(1):80-85
pubmed: 30516002
Mol Psychiatry. 2013 Jun;18(6):708-12
pubmed: 22614287
BMC Bioinformatics. 2009 Jan 30;10 Suppl 1:S65
pubmed: 19208169
BMC Bioinformatics. 2010 Feb 27;11:110
pubmed: 20187966
Semin Nucl Med. 1978 Oct;8(4):283-98
pubmed: 112681
BMC Genet. 2004 Dec 10;5:32
pubmed: 15588316
Nat Rev Genet. 2012 Jul 10;13(8):537-51
pubmed: 22777127
Nat Genet. 2012 Mar 18;44(4):369-75, S1-3
pubmed: 22426310
Nat Genet. 2015 Jul;47(7):702-9
pubmed: 25985137
Nature. 2014 Apr 10;508(7495):249-53
pubmed: 24572353
Nat Biotechnol. 2006 Dec;24(12):1565-7
pubmed: 17160063
J Clin Epidemiol. 2015 Jun;68(6):627-36
pubmed: 25704724
Biomed Res Int. 2013;2013:432375
pubmed: 24228248
Nat Genet. 2012 Feb 19;44(3):247-50
pubmed: 22344220
Genet Epidemiol. 2008 Feb;32(2):152-67
pubmed: 17968988
BMC Genet. 2010 Apr 23;11:26
pubmed: 20416077
Ann Neurol. 2015 Apr;77(4):582-91
pubmed: 25773351