Application of a Poisson deep neural network model for the prediction of count data in genome‐based prediction

Abstract Genomic selection (GS) is revolutionizing conventional ways of developing new plants and animals. However, because it is a predictive methodology, GS strongly depends on statistical and machine learning to perform these predictions. For continuous outcomes, more models are available for GS....

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Osval A. Montesinos‐Lopez, Jose C. Montesinos‐Lopez, Eduardo Salazar, Jose Alberto Barron, Abelardo Montesinos‐Lopez, Raymundo Buenrostro‐Mariscal, Jose Crossa
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Plant culture SB1-1110 Genetics QH426-470
Acceso en línea:	https://doaj.org/article/b692d1010fdd4c00a5ac6ed88572f440
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b692d1010fdd4c00a5ac6ed88572f440
record_format	dspace
spelling	oai:doaj.org-article:b692d1010fdd4c00a5ac6ed88572f4402021-12-05T07:50:11ZApplication of a Poisson deep neural network model for the prediction of count data in genome‐based prediction1940-337210.1002/tpg2.20118https://doaj.org/article/b692d1010fdd4c00a5ac6ed88572f4402021-11-01T00:00:00Zhttps://doi.org/10.1002/tpg2.20118https://doaj.org/toc/1940-3372Abstract Genomic selection (GS) is revolutionizing conventional ways of developing new plants and animals. However, because it is a predictive methodology, GS strongly depends on statistical and machine learning to perform these predictions. For continuous outcomes, more models are available for GS. Unfortunately, for count data outcomes, there are few efficient statistical machine learning models for large datasets or for datasets with fewer observations than independent variables. For this reason, in this paper, we applied the univariate version of the Poisson deep neural network (PDNN) proposed earlier for genomic predictions of count data. The model was implemented with (a) the negative log‐likelihood of Poisson distribution as the loss function, (b) the rectified linear activation unit as the activation function in hidden layers, and (c) the exponential activation function in the output layer. The advantage of the PDNN model is that it captures complex patterns in the data by implementing many nonlinear transformations in the hidden layers. Moreover, since it was implemented in Tensorflow as the back‐end, and in Keras as the front‐end, the model can be applied to moderate and large datasets, which is a significant advantage over previous GS models for count data. The PDNN model was compared with deep learning models with continuous outcomes, conventional generalized Poisson regression models, and conventional Bayesian regression methods. We found that the PDNN model outperformed the Bayesian regression and generalized Poisson regression methods in terms of prediction accuracy, although it was not better than the conventional deep neural network with continuous outcomes.Osval A. Montesinos‐LopezJose C. Montesinos‐LopezEduardo SalazarJose Alberto BarronAbelardo Montesinos‐LopezRaymundo Buenrostro‐MariscalJose CrossaWileyarticlePlant cultureSB1-1110GeneticsQH426-470ENThe Plant Genome, Vol 14, Iss 3, Pp n/a-n/a (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Plant culture SB1-1110 Genetics QH426-470
spellingShingle	Plant culture SB1-1110 Genetics QH426-470 Osval A. Montesinos‐Lopez Jose C. Montesinos‐Lopez Eduardo Salazar Jose Alberto Barron Abelardo Montesinos‐Lopez Raymundo Buenrostro‐Mariscal Jose Crossa Application of a Poisson deep neural network model for the prediction of count data in genome‐based prediction
description	Abstract Genomic selection (GS) is revolutionizing conventional ways of developing new plants and animals. However, because it is a predictive methodology, GS strongly depends on statistical and machine learning to perform these predictions. For continuous outcomes, more models are available for GS. Unfortunately, for count data outcomes, there are few efficient statistical machine learning models for large datasets or for datasets with fewer observations than independent variables. For this reason, in this paper, we applied the univariate version of the Poisson deep neural network (PDNN) proposed earlier for genomic predictions of count data. The model was implemented with (a) the negative log‐likelihood of Poisson distribution as the loss function, (b) the rectified linear activation unit as the activation function in hidden layers, and (c) the exponential activation function in the output layer. The advantage of the PDNN model is that it captures complex patterns in the data by implementing many nonlinear transformations in the hidden layers. Moreover, since it was implemented in Tensorflow as the back‐end, and in Keras as the front‐end, the model can be applied to moderate and large datasets, which is a significant advantage over previous GS models for count data. The PDNN model was compared with deep learning models with continuous outcomes, conventional generalized Poisson regression models, and conventional Bayesian regression methods. We found that the PDNN model outperformed the Bayesian regression and generalized Poisson regression methods in terms of prediction accuracy, although it was not better than the conventional deep neural network with continuous outcomes.
format	article
author	Osval A. Montesinos‐Lopez Jose C. Montesinos‐Lopez Eduardo Salazar Jose Alberto Barron Abelardo Montesinos‐Lopez Raymundo Buenrostro‐Mariscal Jose Crossa
author_facet	Osval A. Montesinos‐Lopez Jose C. Montesinos‐Lopez Eduardo Salazar Jose Alberto Barron Abelardo Montesinos‐Lopez Raymundo Buenrostro‐Mariscal Jose Crossa
author_sort	Osval A. Montesinos‐Lopez
title	Application of a Poisson deep neural network model for the prediction of count data in genome‐based prediction
title_short	Application of a Poisson deep neural network model for the prediction of count data in genome‐based prediction
title_full	Application of a Poisson deep neural network model for the prediction of count data in genome‐based prediction
title_fullStr	Application of a Poisson deep neural network model for the prediction of count data in genome‐based prediction
title_full_unstemmed	Application of a Poisson deep neural network model for the prediction of count data in genome‐based prediction
title_sort	application of a poisson deep neural network model for the prediction of count data in genome‐based prediction
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/b692d1010fdd4c00a5ac6ed88572f440
work_keys_str_mv	AT osvalamontesinoslopez applicationofapoissondeepneuralnetworkmodelforthepredictionofcountdataingenomebasedprediction AT josecmontesinoslopez applicationofapoissondeepneuralnetworkmodelforthepredictionofcountdataingenomebasedprediction AT eduardosalazar applicationofapoissondeepneuralnetworkmodelforthepredictionofcountdataingenomebasedprediction AT josealbertobarron applicationofapoissondeepneuralnetworkmodelforthepredictionofcountdataingenomebasedprediction AT abelardomontesinoslopez applicationofapoissondeepneuralnetworkmodelforthepredictionofcountdataingenomebasedprediction AT raymundobuenrostromariscal applicationofapoissondeepneuralnetworkmodelforthepredictionofcountdataingenomebasedprediction AT josecrossa applicationofapoissondeepneuralnetworkmodelforthepredictionofcountdataingenomebasedprediction
_version_	1718372578791260160

Application of a Poisson deep neural network model for the prediction of count data in genome‐based prediction

Ejemplares similares