A Multivariate Poisson Deep Learning Model for Genomic Prediction of Count Data

Montesinos‐López, Osval A.; Montesinos-López, J. Cricelio; Singh, Pawan Kumar; Lozano-Ramírez, Nérida; Barrón-López, Alberto; Montesinos‐López, Abelardo; Crossa, J.

doi:10.1534/g3.120.401631

Cited by 28 publications

(33 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Montesinos-López et al [ 81 ] report that the best performance in terms of Average Spearman Correlation (ASC) occurred under the deep learning models [normal deep neural network (NDNN) and Poisson deep neural network (PDNN)], while the worst was under the Bayesian (BRR) and classic generalized Poisson model (GP) (Table 4 B). However, Table 4 B also shows that without genotype × environment interaction (WI), the NDNN models were better than the PDNN models, but when taking WI into account, no differences were observed between these deep learning models.…”

Section: Main Bodymentioning

confidence: 99%

A review of deep learning applications for genomic selection

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background Several conventional genomic Bayesian (or no Bayesian) prediction methods have been proposed including the standard additive genetic effect model for which the variance components are estimated with mixed model equations. In recent years, deep learning (DL) methods have been considered in the context of genomic prediction. The DL methods are nonparametric models providing flexibility to adapt to complicated associations between data and output with the ability to adapt to very complex patterns. Main body We review the applications of deep learning (DL) methods in genomic selection (GS) to obtain a meta-picture of GS performance and highlight how these tools can help solve challenging plant breeding problems. We also provide general guidance for the effective use of DL methods including the fundamentals of DL and the requirements for its appropriate use. We discuss the pros and cons of this technique compared to traditional genomic prediction approaches as well as the current trends in DL applications. Conclusions The main requirement for using DL is the quality and sufficiently large training data. Although, based on current literature GS in plant and animal breeding we did not find clear superiority of DL in terms of prediction power compared to conventional genome based prediction models. Nevertheless, there are clear evidences that DL algorithms capture nonlinear patterns more efficiently than conventional genome based. Deep learning algorithms are able to integrate data from different sources as is usually needed in GS assisted breeding and it shows the ability for improving prediction accuracy for large plant breeding data. It is important to apply DL to large training-testing data sets.

show abstract

Section: Main Bodymentioning

confidence: 99%

A review of deep learning applications for genomic selection

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The loss function was optimized with the R package glmnet and the

hyper-parameter was performed with 10-fold cross-validations for all regression models. More details of these models can be found in Montesinos-López et al (2020) .…”

Section: Univariate Generalized Poisson Regression Modelmentioning

confidence: 99%

Prediction of count phenotypes using high-resolution images and genomic data

Kismiantini

Montesinos‐López

Crossa

et al. 2021

G3 Genes|Genomes|Genetics

Self Cite

View full text Add to dashboard Cite

Genomic selection (GS) is revolutionizing plant breeding since the selection process is done with the help of statistical machine learning methods. A model is trained with a reference population and then it is used for predicting the candidate individuals available in the testing set. However, given that breeding phenotypic values are very noisy, new models must be able to integrate not only genotypic and environmental data but also high-resolution images that have been collected by breeders with advanced image technology. For this reason, this paper explores the use of generalized Poisson regression (GPR) for genome-enabled prediction of count phenotypes using genomic and hyperspectral images. The GPR model allows integrating input information of many sources like environments, genomic data, high resolution data, and interaction terms between these three sources. We found that the best prediction performance was obtained when the three sources of information were taken into account in the predictor, and those measures of high-resolution images close to the harvest day provided the best prediction performance.

show abstract

“…(Chollet & Allaire, 2017), and better prediction performance can be achieved. These applications have been used for predicting continuous, binary, count (Montesinos-López et al, 2020), and ordinal traits under univariate and multivariate frameworks.…”

Section: Core Ideasmentioning

confidence: 99%

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

et al. 2021

View full text Add to dashboard Cite

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

show abstract

A Multivariate Poisson Deep Learning Model for Genomic Prediction of Count Data

Cited by 28 publications

References 39 publications

A review of deep learning applications for genomic selection

A review of deep learning applications for genomic selection

Prediction of count phenotypes using high-resolution images and genomic data

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

Contact Info

Product

Resources

About