Assessment of bagging GBLUP for whole-genome prediction of broiler chicken traits

R. Abdollahi-Arpanahi, G. Morota, B. D. Valente, A. Kranis, G. J.M. Rosa, D. Gianola

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Bootstrap aggregation (bagging) is a resampling method known to produce more accurate predictions when predictors are unstable or when the number of markers is much larger than sample size, because of variance reduction capabilities. The purpose of this study was to compare genomic best linear unbiased prediction (GBLUP) with bootstrap aggregated sampling GBLUP (Bagged GBLUP, or BGBLUP) in terms of prediction accuracy. We used a 600 K Affymetrix platform with 1351 birds genotyped and phenotyped for three traits in broiler chickens; body weight, ultrasound measurement of breast muscle and hen house egg production. The predictive performance of GBLUP versus BGBLUP was evaluated in different scenarios consisting of including or excluding the TOP 20 markers from a standard genome-wide association study (GWAS) as fixed effects in the GBLUP model, and varying training sample sizes and allelic frequency bins. Predictive performance was assessed via five replications of a threefold cross-validation using the correlation between observed and predicted values, and prediction mean-squared error. GBLUP overfitted the training set data, and BGBLUP delivered a better predictive ability in testing sets. Treating the TOP 20 markers from the GWAS into the model as fixed effects improved prediction accuracy and added advantages to BGBLUP over GBLUP. The performance of GBLUP and BGBLUP at different allele frequency bins and training sample sizes was similar. In general, results of this study confirm that BGBLUP can be valuable for enhancing genome-enabled prediction of complex traits.

Original languageEnglish (US)
Pages (from-to)218-228
Number of pages11
JournalJournal of Animal Breeding and Genetics
Volume132
Issue number3
DOIs
StatePublished - Jun 1 2015

Fingerprint

Sample Size
Chickens
broiler chickens
Genome-Wide Association Study
Genome
genomics
genome
prediction
Gene Frequency
Birds
Ovum
Breast
Body Weight
Muscles
gene frequency
sampling
breast muscle
egg production
hens
Datasets

Keywords

  • Bagging
  • Genome-enabled prediction
  • Genomic BLUP
  • Predictive ability
  • Resampling methods

ASJC Scopus subject areas

  • Food Animals
  • Animal Science and Zoology

Cite this

Abdollahi-Arpanahi, R., Morota, G., Valente, B. D., Kranis, A., Rosa, G. J. M., & Gianola, D. (2015). Assessment of bagging GBLUP for whole-genome prediction of broiler chicken traits. Journal of Animal Breeding and Genetics, 132(3), 218-228. https://doi.org/10.1111/jbg.12131

Assessment of bagging GBLUP for whole-genome prediction of broiler chicken traits. / Abdollahi-Arpanahi, R.; Morota, G.; Valente, B. D.; Kranis, A.; Rosa, G. J.M.; Gianola, D.

In: Journal of Animal Breeding and Genetics, Vol. 132, No. 3, 01.06.2015, p. 218-228.

Research output: Contribution to journalArticle

Abdollahi-Arpanahi, R, Morota, G, Valente, BD, Kranis, A, Rosa, GJM & Gianola, D 2015, 'Assessment of bagging GBLUP for whole-genome prediction of broiler chicken traits', Journal of Animal Breeding and Genetics, vol. 132, no. 3, pp. 218-228. https://doi.org/10.1111/jbg.12131
Abdollahi-Arpanahi, R. ; Morota, G. ; Valente, B. D. ; Kranis, A. ; Rosa, G. J.M. ; Gianola, D. / Assessment of bagging GBLUP for whole-genome prediction of broiler chicken traits. In: Journal of Animal Breeding and Genetics. 2015 ; Vol. 132, No. 3. pp. 218-228.
@article{f071e1cb50564fe19e27847eccdb5722,
title = "Assessment of bagging GBLUP for whole-genome prediction of broiler chicken traits",
abstract = "Bootstrap aggregation (bagging) is a resampling method known to produce more accurate predictions when predictors are unstable or when the number of markers is much larger than sample size, because of variance reduction capabilities. The purpose of this study was to compare genomic best linear unbiased prediction (GBLUP) with bootstrap aggregated sampling GBLUP (Bagged GBLUP, or BGBLUP) in terms of prediction accuracy. We used a 600 K Affymetrix platform with 1351 birds genotyped and phenotyped for three traits in broiler chickens; body weight, ultrasound measurement of breast muscle and hen house egg production. The predictive performance of GBLUP versus BGBLUP was evaluated in different scenarios consisting of including or excluding the TOP 20 markers from a standard genome-wide association study (GWAS) as fixed effects in the GBLUP model, and varying training sample sizes and allelic frequency bins. Predictive performance was assessed via five replications of a threefold cross-validation using the correlation between observed and predicted values, and prediction mean-squared error. GBLUP overfitted the training set data, and BGBLUP delivered a better predictive ability in testing sets. Treating the TOP 20 markers from the GWAS into the model as fixed effects improved prediction accuracy and added advantages to BGBLUP over GBLUP. The performance of GBLUP and BGBLUP at different allele frequency bins and training sample sizes was similar. In general, results of this study confirm that BGBLUP can be valuable for enhancing genome-enabled prediction of complex traits.",
keywords = "Bagging, Genome-enabled prediction, Genomic BLUP, Predictive ability, Resampling methods",
author = "R. Abdollahi-Arpanahi and G. Morota and Valente, {B. D.} and A. Kranis and Rosa, {G. J.M.} and D. Gianola",
year = "2015",
month = "6",
day = "1",
doi = "10.1111/jbg.12131",
language = "English (US)",
volume = "132",
pages = "218--228",
journal = "Journal of Animal Breeding and Genetics",
issn = "0931-2668",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Assessment of bagging GBLUP for whole-genome prediction of broiler chicken traits

AU - Abdollahi-Arpanahi, R.

AU - Morota, G.

AU - Valente, B. D.

AU - Kranis, A.

AU - Rosa, G. J.M.

AU - Gianola, D.

PY - 2015/6/1

Y1 - 2015/6/1

N2 - Bootstrap aggregation (bagging) is a resampling method known to produce more accurate predictions when predictors are unstable or when the number of markers is much larger than sample size, because of variance reduction capabilities. The purpose of this study was to compare genomic best linear unbiased prediction (GBLUP) with bootstrap aggregated sampling GBLUP (Bagged GBLUP, or BGBLUP) in terms of prediction accuracy. We used a 600 K Affymetrix platform with 1351 birds genotyped and phenotyped for three traits in broiler chickens; body weight, ultrasound measurement of breast muscle and hen house egg production. The predictive performance of GBLUP versus BGBLUP was evaluated in different scenarios consisting of including or excluding the TOP 20 markers from a standard genome-wide association study (GWAS) as fixed effects in the GBLUP model, and varying training sample sizes and allelic frequency bins. Predictive performance was assessed via five replications of a threefold cross-validation using the correlation between observed and predicted values, and prediction mean-squared error. GBLUP overfitted the training set data, and BGBLUP delivered a better predictive ability in testing sets. Treating the TOP 20 markers from the GWAS into the model as fixed effects improved prediction accuracy and added advantages to BGBLUP over GBLUP. The performance of GBLUP and BGBLUP at different allele frequency bins and training sample sizes was similar. In general, results of this study confirm that BGBLUP can be valuable for enhancing genome-enabled prediction of complex traits.

AB - Bootstrap aggregation (bagging) is a resampling method known to produce more accurate predictions when predictors are unstable or when the number of markers is much larger than sample size, because of variance reduction capabilities. The purpose of this study was to compare genomic best linear unbiased prediction (GBLUP) with bootstrap aggregated sampling GBLUP (Bagged GBLUP, or BGBLUP) in terms of prediction accuracy. We used a 600 K Affymetrix platform with 1351 birds genotyped and phenotyped for three traits in broiler chickens; body weight, ultrasound measurement of breast muscle and hen house egg production. The predictive performance of GBLUP versus BGBLUP was evaluated in different scenarios consisting of including or excluding the TOP 20 markers from a standard genome-wide association study (GWAS) as fixed effects in the GBLUP model, and varying training sample sizes and allelic frequency bins. Predictive performance was assessed via five replications of a threefold cross-validation using the correlation between observed and predicted values, and prediction mean-squared error. GBLUP overfitted the training set data, and BGBLUP delivered a better predictive ability in testing sets. Treating the TOP 20 markers from the GWAS into the model as fixed effects improved prediction accuracy and added advantages to BGBLUP over GBLUP. The performance of GBLUP and BGBLUP at different allele frequency bins and training sample sizes was similar. In general, results of this study confirm that BGBLUP can be valuable for enhancing genome-enabled prediction of complex traits.

KW - Bagging

KW - Genome-enabled prediction

KW - Genomic BLUP

KW - Predictive ability

KW - Resampling methods

UR - http://www.scopus.com/inward/record.url?scp=84928754584&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928754584&partnerID=8YFLogxK

U2 - 10.1111/jbg.12131

DO - 10.1111/jbg.12131

M3 - Article

C2 - 25727456

AN - SCOPUS:84928754584

VL - 132

SP - 218

EP - 228

JO - Journal of Animal Breeding and Genetics

JF - Journal of Animal Breeding and Genetics

SN - 0931-2668

IS - 3

ER -