A comparison of genomic profiles of complex diseases under different models

BMC Medical Genomics
Víctor PotencianoFuencisla Matesanz

Abstract

Various approaches are being used to predict individual risk to polygenic diseases from data provided by genome-wide association studies. As there are substantial differences between the diseases investigated, the data sets used and the way they are tested, it is difficult to assess which models are more suitable for this task. We compared different approaches for seven complex diseases provided by the Wellcome Trust Case Control Consortium (WTCCC) under a within-study validation approach. Risk models were inferred using a variety of learning machines and assumptions about the underlying genetic model, including a haplotype-based approach with different haplotype lengths and different thresholds in association levels to choose loci as part of the predictive model. In accordance with previous work, our results generally showed low accuracy considering disease heritability and population prevalence. However, the boosting algorithm returned a predictive area under the ROC curve (AUC) of 0.8805 for Type 1 diabetes (T1D) and 0.8087 for rheumatoid arthritis, both clearly over the AUC obtained by other approaches and over 0.75, which is the minimum required for a disease to be successfully tested on a sample at risk, which means that ...Continue Reading

References

Mar 1, 2003·American Journal of Human Genetics·Jung-Ying TzengKathryn Roeder
Jun 20, 2006·Bioinformatics·María M Abad-GrauPaola Sebastiani
Jun 8, 2007·Nature·UNKNOWN Wellcome Trust Case Control Consortium
Aug 21, 2007·Genetics in Medicine : Official Journal of the American College of Medical Genetics·A Cecile J W JanssensMuin J Khoury
Feb 7, 2008·IEEE Transactions on Neural Networks·V N Vapnik
Oct 15, 2008·Human Molecular Genetics·A Cecile J W Janssens, Cornelia M van Duijn
Feb 10, 2009·Nature Genetics·UNKNOWN Myocardial Infarction Genetics ConsortiumDavid Altshuler
May 12, 2009·Nature Genetics·Jeffrey C BarrettUNKNOWN Type 1 Diabetes Genetics Consortium
Mar 3, 2010·PLoS Genetics·Naomi R WrayPeter M Visscher
Mar 18, 2010·Annals of the Rheumatic Diseases·Elizabeth W KarlsonRobert M Plenge
Mar 24, 2010·Journal of Biopharmaceutical Statistics·Jia KangHongyu Zhao
Apr 7, 2010·American Journal of Human Genetics·UNKNOWN International Multiple Sclerosis Genetics Consortium (IMSGC)Jonathan L Haines
Jun 23, 2010·Molecular Psychiatry·A DemirkanC M Middeldorp
Sep 16, 2010·Genetic Epidemiology·Charles KooperbergValerie Obenchain
Mar 24, 2011·Human Molecular Genetics·Jia KangUNKNOWN NIDDK IBD Genetics Consortium
Aug 30, 2011·Human Molecular Genetics·Luke Jostins, Jeffrey C Barrett
Jan 27, 2012·PloS One·Paola SebastianiThomas T Perls
Mar 1, 2012·Journal of Forensic Sciences·Ewelina PośpiechWojciech Branicki
Jun 6, 2012·PloS One·Felix GrassmannBernhard H F Weber
Dec 28, 2012·Nature Methods·Olivier DelaneauJonathan Marchini
Apr 29, 2015·Human Molecular Genetics·Athina SpiliopoulouChris S Haley

❮ Previous
Next ❯

Citations

May 18, 2016·European Journal of Human Genetics : EJHG·Fuencisla MatesanzAntonio Alcina
Feb 9, 2017·Human Heredity·Susan E Hodge, David A Greenberg

❮ Previous
Next ❯

Methods Mentioned

BETA
genotyping
chip

Software Mentioned

mTDT
add
20RF
BmapBuilder
PLINK
sSVM
Shapeit
mAssocTest
AdaBoostM1
Weka

Related Concepts

Related Feeds

Autoimmune Diabetes & Tolerance

Patients with type I diabetes lack insulin-producing beta cells due to the loss of immunological tolerance and autoimmune disease. Discover the latest research on targeting tolerance to prevent diabetes.