Cargando…

A zero altered Poisson random forest model for genomic-enabled prediction

In genomic selection choosing the statistical machine learning model is of paramount importance. In this paper, we present an application of a zero altered random forest model with two versions (ZAP_RF and ZAPC_RF) to deal with excess zeros in count response variables. The proposed model was compare...

Descripción completa

Detalles Bibliográficos
Autores principales: Montesinos-López, Osval Antonio, Montesinos-López, Abelardo, Mosqueda-Gonzalez, Brandon A, Montesinos-López, José Cricelio, Crossa, José, Ramirez, Nerida Lozano, Singh, Pawan, Valladares-Anguiano, Felícitas Alejandra
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8022945/
https://www.ncbi.nlm.nih.gov/pubmed/33693599
http://dx.doi.org/10.1093/g3journal/jkaa057
_version_ 1783675032222826496
author Montesinos-López, Osval Antonio
Montesinos-López, Abelardo
Mosqueda-Gonzalez, Brandon A
Montesinos-López, José Cricelio
Crossa, José
Ramirez, Nerida Lozano
Singh, Pawan
Valladares-Anguiano, Felícitas Alejandra
author_facet Montesinos-López, Osval Antonio
Montesinos-López, Abelardo
Mosqueda-Gonzalez, Brandon A
Montesinos-López, José Cricelio
Crossa, José
Ramirez, Nerida Lozano
Singh, Pawan
Valladares-Anguiano, Felícitas Alejandra
author_sort Montesinos-López, Osval Antonio
collection PubMed
description In genomic selection choosing the statistical machine learning model is of paramount importance. In this paper, we present an application of a zero altered random forest model with two versions (ZAP_RF and ZAPC_RF) to deal with excess zeros in count response variables. The proposed model was compared with the conventional random forest (RF) model and with the conventional Generalized Poisson Ridge regression (GPR) using two real datasets, and we found that, in terms of prediction performance, the proposed zero inflated random forest model outperformed the conventional RF and GPR models.
format Online
Article
Text
id pubmed-8022945
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-80229452021-04-09 A zero altered Poisson random forest model for genomic-enabled prediction Montesinos-López, Osval Antonio Montesinos-López, Abelardo Mosqueda-Gonzalez, Brandon A Montesinos-López, José Cricelio Crossa, José Ramirez, Nerida Lozano Singh, Pawan Valladares-Anguiano, Felícitas Alejandra G3 (Bethesda) Investigation In genomic selection choosing the statistical machine learning model is of paramount importance. In this paper, we present an application of a zero altered random forest model with two versions (ZAP_RF and ZAPC_RF) to deal with excess zeros in count response variables. The proposed model was compared with the conventional random forest (RF) model and with the conventional Generalized Poisson Ridge regression (GPR) using two real datasets, and we found that, in terms of prediction performance, the proposed zero inflated random forest model outperformed the conventional RF and GPR models. Oxford University Press 2020-12-21 /pmc/articles/PMC8022945/ /pubmed/33693599 http://dx.doi.org/10.1093/g3journal/jkaa057 Text en © The Author(s) 2020. Published by Oxford University Press on behalf of Genetics Society of America. https://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/ (https://creativecommons.org/licenses/by/4.0/) ), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Investigation
Montesinos-López, Osval Antonio
Montesinos-López, Abelardo
Mosqueda-Gonzalez, Brandon A
Montesinos-López, José Cricelio
Crossa, José
Ramirez, Nerida Lozano
Singh, Pawan
Valladares-Anguiano, Felícitas Alejandra
A zero altered Poisson random forest model for genomic-enabled prediction
title A zero altered Poisson random forest model for genomic-enabled prediction
title_full A zero altered Poisson random forest model for genomic-enabled prediction
title_fullStr A zero altered Poisson random forest model for genomic-enabled prediction
title_full_unstemmed A zero altered Poisson random forest model for genomic-enabled prediction
title_short A zero altered Poisson random forest model for genomic-enabled prediction
title_sort zero altered poisson random forest model for genomic-enabled prediction
topic Investigation
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8022945/
https://www.ncbi.nlm.nih.gov/pubmed/33693599
http://dx.doi.org/10.1093/g3journal/jkaa057
work_keys_str_mv AT montesinoslopezosvalantonio azeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT montesinoslopezabelardo azeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT mosquedagonzalezbrandona azeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT montesinoslopezjosecricelio azeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT crossajose azeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT ramirezneridalozano azeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT singhpawan azeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT valladaresanguianofelicitasalejandra azeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT montesinoslopezosvalantonio zeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT montesinoslopezabelardo zeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT mosquedagonzalezbrandona zeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT montesinoslopezjosecricelio zeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT crossajose zeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT ramirezneridalozano zeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT singhpawan zeroalteredpoissonrandomforestmodelforgenomicenabledprediction
AT valladaresanguianofelicitasalejandra zeroalteredpoissonrandomforestmodelforgenomicenabledprediction