A Multivariate Poisson Deep Learning Model for Genomic Prediction of Count Data
Open Access
- 1 November 2020
- journal article
- research article
- Published by Oxford University Press (OUP) in G3: Genes, Genomes, Genetics
- Vol. 10 (11) , 4177-4190
Abstract
The paradigm called genomic selection (GS) is a revolutionary way of developing new plants and animals. This is a predictive methodology, since it uses learning methods to perform its task. Unfortunately, there is no universal model that can be used for all types of predictions; for this reason, specific methodologies are required for each type of output (response variables). Since there is a lack of efficient methodologies for multivariate count data outcomes, in this paper, a multivariate Poisson deep neural network (MPDN) model is proposed for the genomic prediction of various count outcomes simultaneously. The MPDN model uses the minus log-likelihood of a Poisson distribution as a loss function, in hidden layers for capturing nonlinear patterns using the rectified linear unit (RELU) activation function and, in the output layer, the exponential activation function was used for producing outputs on the same scale of counts. The proposed MPDN model was compared to conventional generalized Poisson regression models and univariate Poisson deep learning models in two experimental data sets of count data. We found that the proposed MPDL outperformed univariate Poisson deep neural network models, but did not outperform, in terms of prediction, the univariate generalized Poisson regression models. All deep learning models were implemented in Tensorflow as back-end and Keras as front-end, which allows implementing these models on moderate and large data sets, which is a significant advantage over previous GS models for multivariate count data.Keywords
This publication has 33 references indexed in Scilit:
- Genomic Bayesian Prediction Model for Count Data with Genotype × Environment InteractionG3: Genes, Genomes, Genetics, 2016
- Genomic Prediction Models for Count DataJournal of Agricultural, Biological and Environmental Statistics, 2015
- Genome-wide comparative diversity uncovers multiple targets of selection for improvement in hexaploid wheat landraces and cultivarsProceedings of the National Academy of Sciences, 2013
- Genomic prediction in CIMMYT maize and wheat breeding programsHeredity, 2013
- Accelerating Improvement of Livestock with Genomic SelectionAnnual Review of Animal Biosciences, 2013
- The use of count data models in biomedical informatics evaluation researchJournal of the American Medical Informatics Association, 2012
- Genomic-Assisted Prediction of Genetic Value With Semiparametric ProceduresGenetics, 2006
- No free lunch theorems for optimizationIEEE Transactions on Evolutionary Computation, 1997
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989