{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Mittag F"],"funding":["Intramural NIH HHS","NCRR NIH HHS","Medical Research Council","NINDS NIH HHS","Wellcome Trust"],"pagination":["1708-18"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC5968822"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["33(12)"],"pubmed_abstract":["The success of genome-wide association studies (GWAS) in deciphering the genetic architecture of complex diseases has fueled the expectations whether the individual risk can also be quantified based on the genetic architecture. So far, disease risk prediction based on top-validated single-nucleotide polymorphisms (SNPs) showed little predictive value. Here, we applied a support vector machine (SVM) to Parkinson disease (PD) and type 1 diabetes (T1D), to show that apart from magnitude of effect size of risk variants, heritability of the disease also plays an important role in disease risk prediction. Furthermore, we performed a simulation study to show the role of uncommon (frequency 1-5%) as well as rare variants (frequency <1%) in disease etiology of complex diseases. Using a cross-valida"],"journal":["Human mutation"],"pubmed_title":["Use of support vector machines for disease risk prediction in genome-wide association studies: concerns and opportunities."],"pmcid":["PMC5968822"],"funding_grant_id":["U01 NS082151","MC_PC_09003","Z01 AG000949","P30 NS057105","076113","MC_G0901330","090532","G1100479","085475","G0801418B","UL1 RR024992","Z01 ES101986","Z99 AG999999"],"pubmed_authors":["Cooper J","Dexter DT","Trabzuni D","Williams N","Uitterlinden AG","van Hilten JJ","Lees A","Gasser T","Guerreiro R","Revesz T","Wood NW","Talbot K","Clarke CE","Vidailhet M","Damier P","Dillman A","Cookson MR","Huber H","Wickremaratchi M","Jonsson PV","Dartigues JF","Durif F","Chinnery PF","Walker R","Petursson H","Burn DJ","Keller M","van Dijk KD","Moorby C","Stockton JD","Bonin M","Corvol JC","Hu M","Buchel F","Zell A","Durr A","Morris HR","Nalls MA","Chong S","Gibbs J","Berendse HW","Potter S","Evans JR","Sidransky E","Hershey MS","Deloukas P","Lopez G","Hofman A","Munchen HZ","Shaw K","Gibbs JR","Gardner M","Simon-Sanchez J","Rivadeneira F","International Parkinson’s Disease Genomics Consortium","Lambert JC","Pearson J","Deuschl G","Traynor BJ","Bhatia K","Scheffer H","Williams-Gray CH","Gray E","Hunt SE","Huang X","Winder-Rhodes S","Hudson G","Bloem B","Sveinbjornsdottir S","Velseboer D","Tison F","Stefansson K","Hernandez DG","Gao J","Stefansson H","Arepalli S","Barker R","Berg D","Bochdanovits Z","Foltynie T","Plagnol V","Gustafsson O","Sheerin UM","Spencer CC","Mittag F","Brice A","Pollak P","Heutink P","Edkins S","Schapira A","Chen H","Hollenbeck A","Sawcer S","Charlesworth G","Sharma M","Brooks J","Jahn A","Holton J","Martinez M","Perlmutter JS","McNeill A","Hardy J","van de Warrenburg B","Ryten M","Tashakkori-Ghanbaria A","Lesage S","O'Sullivan SS","Riess O","Limousin P","Illig T","Langford C","de Bie RM","Morrison KE","Biffi A","Brockmann K","Saad M","Counsell C","Steinberg S","Singleton AB","Ravina B","Smith C","Bras JM","Lichtner P","Rizzu P","Ben-Shlomo Y","Moore M","Harris C","Schulte C","Goate A","Huttenlocher J","Tanner CM","Lorenz D","Strange A"],"additional_accession":[]},"is_claimable":false,"name":"Use of support vector machines for disease risk prediction in genome-wide association studies: concerns and opportunities.","description":"The success of genome-wide association studies (GWAS) in deciphering the genetic architecture of complex diseases has fueled the expectations whether the individual risk can also be quantified based on the genetic architecture. So far, disease risk prediction based on top-validated single-nucleotide polymorphisms (SNPs) showed little predictive value. Here, we applied a support vector machine (SVM) to Parkinson disease (PD) and type 1 diabetes (T1D), to show that apart from magnitude of effect size of risk variants, heritability of the disease also plays an important role in disease risk prediction. Furthermore, we performed a simulation study to show the role of uncommon (frequency 1-5%) as well as rare variants (frequency <1%) in disease etiology of complex diseases. Using a cross-valida","dates":{"release":"2012-01-01T00:00:00Z","publication":"2012 Dec","modification":"2026-04-13T21:37:19.703Z","creation":"2026-04-07T13:36:44.267Z"},"accession":"S-EPMC5968822","cross_references":{"pubmed":["22777693"],"doi":["10.1002/humu.22161"]}}