Cargando…

Genomic prediction of complex human traits: relatedness, trait architecture and predictive meta-models

We explore the prediction of individuals' phenotypes for complex traits using genomic data. We compare several widely used prediction models, including Ridge Regression, LASSO and Elastic Nets estimated from cohort data, and polygenic risk scores constructed using published summary statistics f...

Descripción completa

Detalles Bibliográficos
Autores principales: Spiliopoulou, Athina, Nagy, Reka, Bermingham, Mairead L., Huffman, Jennifer E., Hayward, Caroline, Vitart, Veronique, Rudan, Igor, Campbell, Harry, Wright, Alan F., Wilson, James F., Pong-Wong, Ricardo, Agakov, Felix, Navarro, Pau, Haley, Chris S.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4476450/
https://www.ncbi.nlm.nih.gov/pubmed/25918167
http://dx.doi.org/10.1093/hmg/ddv145
_version_ 1782377602533556224
author Spiliopoulou, Athina
Nagy, Reka
Bermingham, Mairead L.
Huffman, Jennifer E.
Hayward, Caroline
Vitart, Veronique
Rudan, Igor
Campbell, Harry
Wright, Alan F.
Wilson, James F.
Pong-Wong, Ricardo
Agakov, Felix
Navarro, Pau
Haley, Chris S.
author_facet Spiliopoulou, Athina
Nagy, Reka
Bermingham, Mairead L.
Huffman, Jennifer E.
Hayward, Caroline
Vitart, Veronique
Rudan, Igor
Campbell, Harry
Wright, Alan F.
Wilson, James F.
Pong-Wong, Ricardo
Agakov, Felix
Navarro, Pau
Haley, Chris S.
author_sort Spiliopoulou, Athina
collection PubMed
description We explore the prediction of individuals' phenotypes for complex traits using genomic data. We compare several widely used prediction models, including Ridge Regression, LASSO and Elastic Nets estimated from cohort data, and polygenic risk scores constructed using published summary statistics from genome-wide association meta-analyses (GWAMA). We evaluate the interplay between relatedness, trait architecture and optimal marker density, by predicting height, body mass index (BMI) and high-density lipoprotein level (HDL) in two data cohorts, originating from Croatia and Scotland. We empirically demonstrate that dense models are better when all genetic effects are small (height and BMI) and target individuals are related to the training samples, while sparse models predict better in unrelated individuals and when some effects have moderate size (HDL). For HDL sparse models achieved good across-cohort prediction, performing similarly to the GWAMA risk score and to models trained within the same cohort, which indicates that, for predicting traits with moderately sized effects, large sample sizes and familial structure become less important, though still potentially useful. Finally, we propose a novel ensemble of whole-genome predictors with GWAMA risk scores and demonstrate that the resulting meta-model achieves higher prediction accuracy than either model on its own. We conclude that although current genomic predictors are not accurate enough for diagnostic purposes, performance can be improved without requiring access to large-scale individual-level data. Our methodologically simple meta-model is a means of performing predictive meta-analysis for optimizing genomic predictions and can be easily extended to incorporate multiple population-level summary statistics or other domain knowledge.
format Online
Article
Text
id pubmed-4476450
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-44764502015-06-24 Genomic prediction of complex human traits: relatedness, trait architecture and predictive meta-models Spiliopoulou, Athina Nagy, Reka Bermingham, Mairead L. Huffman, Jennifer E. Hayward, Caroline Vitart, Veronique Rudan, Igor Campbell, Harry Wright, Alan F. Wilson, James F. Pong-Wong, Ricardo Agakov, Felix Navarro, Pau Haley, Chris S. Hum Mol Genet Association Studies Articles We explore the prediction of individuals' phenotypes for complex traits using genomic data. We compare several widely used prediction models, including Ridge Regression, LASSO and Elastic Nets estimated from cohort data, and polygenic risk scores constructed using published summary statistics from genome-wide association meta-analyses (GWAMA). We evaluate the interplay between relatedness, trait architecture and optimal marker density, by predicting height, body mass index (BMI) and high-density lipoprotein level (HDL) in two data cohorts, originating from Croatia and Scotland. We empirically demonstrate that dense models are better when all genetic effects are small (height and BMI) and target individuals are related to the training samples, while sparse models predict better in unrelated individuals and when some effects have moderate size (HDL). For HDL sparse models achieved good across-cohort prediction, performing similarly to the GWAMA risk score and to models trained within the same cohort, which indicates that, for predicting traits with moderately sized effects, large sample sizes and familial structure become less important, though still potentially useful. Finally, we propose a novel ensemble of whole-genome predictors with GWAMA risk scores and demonstrate that the resulting meta-model achieves higher prediction accuracy than either model on its own. We conclude that although current genomic predictors are not accurate enough for diagnostic purposes, performance can be improved without requiring access to large-scale individual-level data. Our methodologically simple meta-model is a means of performing predictive meta-analysis for optimizing genomic predictions and can be easily extended to incorporate multiple population-level summary statistics or other domain knowledge. Oxford University Press 2015-07-15 2015-04-26 /pmc/articles/PMC4476450/ /pubmed/25918167 http://dx.doi.org/10.1093/hmg/ddv145 Text en © The Author 2015. Published by Oxford University Press http://creativecommons.org/licenses/by/4.0/ This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Association Studies Articles
Spiliopoulou, Athina
Nagy, Reka
Bermingham, Mairead L.
Huffman, Jennifer E.
Hayward, Caroline
Vitart, Veronique
Rudan, Igor
Campbell, Harry
Wright, Alan F.
Wilson, James F.
Pong-Wong, Ricardo
Agakov, Felix
Navarro, Pau
Haley, Chris S.
Genomic prediction of complex human traits: relatedness, trait architecture and predictive meta-models
title Genomic prediction of complex human traits: relatedness, trait architecture and predictive meta-models
title_full Genomic prediction of complex human traits: relatedness, trait architecture and predictive meta-models
title_fullStr Genomic prediction of complex human traits: relatedness, trait architecture and predictive meta-models
title_full_unstemmed Genomic prediction of complex human traits: relatedness, trait architecture and predictive meta-models
title_short Genomic prediction of complex human traits: relatedness, trait architecture and predictive meta-models
title_sort genomic prediction of complex human traits: relatedness, trait architecture and predictive meta-models
topic Association Studies Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4476450/
https://www.ncbi.nlm.nih.gov/pubmed/25918167
http://dx.doi.org/10.1093/hmg/ddv145
work_keys_str_mv AT spiliopoulouathina genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT nagyreka genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT berminghammaireadl genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT huffmanjennifere genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT haywardcaroline genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT vitartveronique genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT rudanigor genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT campbellharry genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT wrightalanf genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT wilsonjamesf genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT pongwongricardo genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT agakovfelix genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT navarropau genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels
AT haleychriss genomicpredictionofcomplexhumantraitsrelatednesstraitarchitectureandpredictivemetamodels