Accessing marker effects and heritability estimates from genome prediction by Bayesian regularized neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | LOCUS Repositório Institucional da UFV |
Texto Completo: | https://doi.org/10.1016/j.livsci.2016.07.015 http://www.locus.ufv.br/handle/123456789/23555 |
Resumo: | Recently, there is an increasing interest on semi- and non-parametric methods for genome-enabled prediction, among which the Bayesian regularized artificial neural networks (BRANN) stand. We aimed to evaluate the predictive performance of BRANN and to exploit SNP effects and heritability estimates using two different approaches (relative importance-RI, and relative contribution-RC). Additionally, we aimed also to compare BRANN with the traditional RR-BLUP and BLASSO by using simulated datasets. The simplest BRANN (net1), RR-BLUP and BLASSO methods outperformed other more parameterized BRANN (net2, net3, … net6) in terms of predictive ability. For both simulated traits (Y1 and Y2) the net1 provided the best h2 estimates (0.33 for both, being the true h2=0.35), whereas RR-BLUP (0.18 and 0.22 for Y1 and Y2, respectively) and BLASSO (0.20 and 0.26 for Y1 and Y2, respectively) underestimated h2. The marker effects estimated from net1 (using RI and RC approaches) and RR-BLUP were similar, but the shrinkage strength was remarkable for BLASSO on both traits. For Y1, the correlation between the true fifty QTL effects and the effects estimated for the SNPs located in the same QTL positions were 0.61, 0.60, 0.60 and 0.55, for RI, RC, RR-BLUP and BLASSO; and for Y2, these correlations were 0.81, 0.81, 0.81 and 0.71, respectively. In summary, we believe that estimates of SNP effects are promising quantitative tools to bring discussions on chromosome regions contributing most effectively to the phenotype expression when using ANN for genomic predictions. |
id |
UFV_97ff6ebed0dc54725748069ba257e506 |
---|---|
oai_identifier_str |
oai:locus.ufv.br:123456789/23555 |
network_acronym_str |
UFV |
network_name_str |
LOCUS Repositório Institucional da UFV |
repository_id_str |
2145 |
spelling |
Glória, Leonardo SiqueiraCruz, Cosme DamiãoVieira, Ricardo Augusto MendonçaResende, Marcos Deon Vilela deLopes, Paulo SávioSilva, Fabyano Fonseca eSiqueira, Otávio H. G. B. Dias de2019-02-18T12:00:25Z2019-02-18T12:00:25Z2016-091871-1413https://doi.org/10.1016/j.livsci.2016.07.015http://www.locus.ufv.br/handle/123456789/23555Recently, there is an increasing interest on semi- and non-parametric methods for genome-enabled prediction, among which the Bayesian regularized artificial neural networks (BRANN) stand. We aimed to evaluate the predictive performance of BRANN and to exploit SNP effects and heritability estimates using two different approaches (relative importance-RI, and relative contribution-RC). Additionally, we aimed also to compare BRANN with the traditional RR-BLUP and BLASSO by using simulated datasets. The simplest BRANN (net1), RR-BLUP and BLASSO methods outperformed other more parameterized BRANN (net2, net3, … net6) in terms of predictive ability. For both simulated traits (Y1 and Y2) the net1 provided the best h2 estimates (0.33 for both, being the true h2=0.35), whereas RR-BLUP (0.18 and 0.22 for Y1 and Y2, respectively) and BLASSO (0.20 and 0.26 for Y1 and Y2, respectively) underestimated h2. The marker effects estimated from net1 (using RI and RC approaches) and RR-BLUP were similar, but the shrinkage strength was remarkable for BLASSO on both traits. For Y1, the correlation between the true fifty QTL effects and the effects estimated for the SNPs located in the same QTL positions were 0.61, 0.60, 0.60 and 0.55, for RI, RC, RR-BLUP and BLASSO; and for Y2, these correlations were 0.81, 0.81, 0.81 and 0.71, respectively. In summary, we believe that estimates of SNP effects are promising quantitative tools to bring discussions on chromosome regions contributing most effectively to the phenotype expression when using ANN for genomic predictions.engLivestock ScienceVolume 191, Pages 91- 96, September 20162016 Elsevier B.V. All rights reserved.info:eu-repo/semantics/openAccessGenomic selectionArtificial neural networksQTLGenetic parametersAccessing marker effects and heritability estimates from genome prediction by Bayesian regularized neural networksinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfreponame:LOCUS Repositório Institucional da UFVinstname:Universidade Federal de Viçosa (UFV)instacron:UFVORIGINALartigo.pdfartigo.pdfTexto completoapplication/pdf1091260https://locus.ufv.br//bitstream/123456789/23555/1/artigo.pdf27c91ab675d63ebae930b117cf6991b4MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-81748https://locus.ufv.br//bitstream/123456789/23555/2/license.txt8a4605be74aa9ea9d79846c1fba20a33MD52123456789/235552019-02-18 09:34:00.858oai:locus.ufv.br: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Repositório InstitucionalPUBhttps://www.locus.ufv.br/oai/requestfabiojreis@ufv.bropendoar:21452019-02-18T12:34LOCUS Repositório Institucional da UFV - Universidade Federal de Viçosa (UFV)false |
dc.title.en.fl_str_mv |
Accessing marker effects and heritability estimates from genome prediction by Bayesian regularized neural networks |
title |
Accessing marker effects and heritability estimates from genome prediction by Bayesian regularized neural networks |
spellingShingle |
Accessing marker effects and heritability estimates from genome prediction by Bayesian regularized neural networks Glória, Leonardo Siqueira Genomic selection Artificial neural networks QTL Genetic parameters |
title_short |
Accessing marker effects and heritability estimates from genome prediction by Bayesian regularized neural networks |
title_full |
Accessing marker effects and heritability estimates from genome prediction by Bayesian regularized neural networks |
title_fullStr |
Accessing marker effects and heritability estimates from genome prediction by Bayesian regularized neural networks |
title_full_unstemmed |
Accessing marker effects and heritability estimates from genome prediction by Bayesian regularized neural networks |
title_sort |
Accessing marker effects and heritability estimates from genome prediction by Bayesian regularized neural networks |
author |
Glória, Leonardo Siqueira |
author_facet |
Glória, Leonardo Siqueira Cruz, Cosme Damião Vieira, Ricardo Augusto Mendonça Resende, Marcos Deon Vilela de Lopes, Paulo Sávio Silva, Fabyano Fonseca e Siqueira, Otávio H. G. B. Dias de |
author_role |
author |
author2 |
Cruz, Cosme Damião Vieira, Ricardo Augusto Mendonça Resende, Marcos Deon Vilela de Lopes, Paulo Sávio Silva, Fabyano Fonseca e Siqueira, Otávio H. G. B. Dias de |
author2_role |
author author author author author author |
dc.contributor.author.fl_str_mv |
Glória, Leonardo Siqueira Cruz, Cosme Damião Vieira, Ricardo Augusto Mendonça Resende, Marcos Deon Vilela de Lopes, Paulo Sávio Silva, Fabyano Fonseca e Siqueira, Otávio H. G. B. Dias de |
dc.subject.pt-BR.fl_str_mv |
Genomic selection Artificial neural networks QTL Genetic parameters |
topic |
Genomic selection Artificial neural networks QTL Genetic parameters |
description |
Recently, there is an increasing interest on semi- and non-parametric methods for genome-enabled prediction, among which the Bayesian regularized artificial neural networks (BRANN) stand. We aimed to evaluate the predictive performance of BRANN and to exploit SNP effects and heritability estimates using two different approaches (relative importance-RI, and relative contribution-RC). Additionally, we aimed also to compare BRANN with the traditional RR-BLUP and BLASSO by using simulated datasets. The simplest BRANN (net1), RR-BLUP and BLASSO methods outperformed other more parameterized BRANN (net2, net3, … net6) in terms of predictive ability. For both simulated traits (Y1 and Y2) the net1 provided the best h2 estimates (0.33 for both, being the true h2=0.35), whereas RR-BLUP (0.18 and 0.22 for Y1 and Y2, respectively) and BLASSO (0.20 and 0.26 for Y1 and Y2, respectively) underestimated h2. The marker effects estimated from net1 (using RI and RC approaches) and RR-BLUP were similar, but the shrinkage strength was remarkable for BLASSO on both traits. For Y1, the correlation between the true fifty QTL effects and the effects estimated for the SNPs located in the same QTL positions were 0.61, 0.60, 0.60 and 0.55, for RI, RC, RR-BLUP and BLASSO; and for Y2, these correlations were 0.81, 0.81, 0.81 and 0.71, respectively. In summary, we believe that estimates of SNP effects are promising quantitative tools to bring discussions on chromosome regions contributing most effectively to the phenotype expression when using ANN for genomic predictions. |
publishDate |
2016 |
dc.date.issued.fl_str_mv |
2016-09 |
dc.date.accessioned.fl_str_mv |
2019-02-18T12:00:25Z |
dc.date.available.fl_str_mv |
2019-02-18T12:00:25Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://doi.org/10.1016/j.livsci.2016.07.015 http://www.locus.ufv.br/handle/123456789/23555 |
dc.identifier.issn.none.fl_str_mv |
1871-1413 |
identifier_str_mv |
1871-1413 |
url |
https://doi.org/10.1016/j.livsci.2016.07.015 http://www.locus.ufv.br/handle/123456789/23555 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartofseries.pt-BR.fl_str_mv |
Volume 191, Pages 91- 96, September 2016 |
dc.rights.driver.fl_str_mv |
2016 Elsevier B.V. All rights reserved. info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
2016 Elsevier B.V. All rights reserved. |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Livestock Science |
publisher.none.fl_str_mv |
Livestock Science |
dc.source.none.fl_str_mv |
reponame:LOCUS Repositório Institucional da UFV instname:Universidade Federal de Viçosa (UFV) instacron:UFV |
instname_str |
Universidade Federal de Viçosa (UFV) |
instacron_str |
UFV |
institution |
UFV |
reponame_str |
LOCUS Repositório Institucional da UFV |
collection |
LOCUS Repositório Institucional da UFV |
bitstream.url.fl_str_mv |
https://locus.ufv.br//bitstream/123456789/23555/1/artigo.pdf https://locus.ufv.br//bitstream/123456789/23555/2/license.txt |
bitstream.checksum.fl_str_mv |
27c91ab675d63ebae930b117cf6991b4 8a4605be74aa9ea9d79846c1fba20a33 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
LOCUS Repositório Institucional da UFV - Universidade Federal de Viçosa (UFV) |
repository.mail.fl_str_mv |
fabiojreis@ufv.br |
_version_ |
1801213108930215936 |