Show simple item record

A benchmarking between deep learning, support vector machine and bayesian threshold best linear unbiased prediction for predicting ordinal traits in plant breeding

Author: Montesinos-Lopez, O.A.
Author: Martin-Vallejo, J.
Author: Crossa, J.
Author: Gianola, D.
Author: Hernández Suárez, C.M.
Author: Montesinos-Lopez, A.
Author: Juliana, P.
Author: Singh, R.P.
Year: 2019
ISSN: ESSN: 2160-1836
URI: https://hdl.handle.net/10883/20090
Abstract: Genomic selection is revolutionizing plant breeding. However, still lacking are better statistical models for ordinal phenotypes to improve the accuracy of the selection of candidate genotypes. For this reason, in this paper we explore the genomic based prediction performance of two popular machine learning methods: the Multi Layer Perceptron (MLP) and support vector machine (SVM) methods vs. the Bayesian threshold genomic best linear unbiased prediction (TGBLUP) model. We used the percentage of cases correctly classified (PCCC) as a metric to measure the prediction performance, and seven real data sets to evaluate the prediction accuracy, and found that the best predictions (in four out of the seven data sets) in terms of PCCC occurred under the TGLBUP model, while the worst occurred under the SVM method. Also, in general we found no statistical differences between using 1, 2 and 3 layers under the MLP models, which means that many times the conventional neuronal network model with only one layer is enough. However, although even that the TGBLUP model was better, we found that the predictions of MLP and SVM were very competitive with the advantage that the SVM was the most efficient in terms of the computational time required.
Format: PDF
Language: English
Publisher: Genetics Society of America
Type: Article
Place of Publication: Bethesda, MD
Pages: 601-618
Issue: 2
Volume: 9
DOI: 10.1534/g3.118.200998
Keywords: Threshold GBLUP
Keywords: Deep Learning
Keywords: Support Vector Machine
Keywords: Genomic Selection
Keywords: Genomic Prediction
Keywords: GenPred
Keywords: Shared Data Resources
Agrovoc: BAYESIAN THEORY
Agrovoc: STATISTICAL METHODS
Agrovoc: MACHINE LEARNING
Agrovoc: ARTIFICIAL SELECTION
Agrovoc: PLANT BREEDING
Agrovoc: CROP FORECASTING
Agrovoc: DATA ANALYSIS
Journal: G3: Genes, Genomes, Genetics


Files in this item

Thumbnail

This item appears in the following Collection(s)

  • Genetic Resources
    Genetic Resources including germplasm collections, wild relatives, genotyping, genomics, and IP
  • Wheat
    Wheat - breeding, phytopathology, physiology, quality, biotech

Show simple item record