Bayesian neural networks with variable selection for prediction of genotypic values
| Autor: | Pascal Duenk, Cornelis A. Albers, Giel H. H. van Bergen, Yvonne C. J. Wientjes, Piter Bijma, Mario P. L. Calus, Hilbert J. Kappen |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Multifactorial Inheritance
[SDV]Life Sciences [q-bio] Bayes' theorem Gene Frequency Statistics lcsh:SF1-1100 0303 health sciences Artificial neural network Percentage point Genomics 04 agricultural and veterinary sciences General Medicine Phenotype Molecular Developmental Biology Algorithms Research Article Genotype lcsh:QH426-470 Quantitative Trait Loci Biophysics Feature selection Quantitative trait locus Biology Best linear unbiased prediction Animal Breeding and Genomics Polymorphism Single Nucleotide 03 medical and health sciences Genetic model Genetics Life Science Animals Humans Fokkerij en Genomica Selection Genetic Alleles Ecology Evolution Behavior and Systematics 030304 developmental biology Neurodevelopmental disorders Donders Center for Medical Neuroscience [Radboudumc 7] Models Genetic 0402 animal and dairy science Bayes Theorem 040201 dairy & animal science lcsh:Genetics Genetics Population WIAS Epistasis Animal Science and Zoology Neural Networks Computer lcsh:Animal culture Forecasting |
| Zdroj: | Genetics, selection, evolution : GSE, 52(1) Genetics, Selection, Evolution, 52, 1, pp. 1-14 Genetics Selection Evolution Genetics Selection Evolution, BioMed Central, 2020, 52 (1), pp.26. ⟨10.1186/s12711-020-00544-8⟩ Genetics Selection Evolution, Vol 52, Iss 1, Pp 1-14 (2020) Genetics, Selection, Evolution : GSE Genetics, Selection, Evolution, 52, 1-14 Genetics, selection, evolution : GSE 52 (2020) 1 |
| ISSN: | 0999-193X 1297-9686 |
| Popis: | Background Estimating the genetic component of a complex phenotype is a complicated problem, mainly because there are many allele effects to estimate from a limited number of phenotypes. In spite of this difficulty, linear methods with variable selection have been able to give good predictions of additive effects of individuals. However, prediction of non-additive genetic effects is challenging with the usual prediction methods. In machine learning, non-additive relations between inputs can be modeled with neural networks. We developed a novel method (NetSparse) that uses Bayesian neural networks with variable selection for the prediction of genotypic values of individuals, including non-additive genetic effects. Results We simulated several populations with different phenotypic models and compared NetSparse to genomic best linear unbiased prediction (GBLUP), BayesB, their dominance variants, and an additive by additive method. We found that when the number of QTL was relatively small (10 or 100), NetSparse had 2 to 28 percentage points higher accuracy than the reference methods. For scenarios that included dominance or epistatic effects, NetSparse had 0.0 to 3.9 percentage points higher accuracy for predicting phenotypes than the reference methods, except in scenarios with extreme overdominance, for which reference methods that explicitly model dominance had 6 percentage points higher accuracy than NetSparse. Conclusions Bayesian neural networks with variable selection are promising for prediction of the genetic component of complex traits in animal breeding, and their performance is robust across different genetic models. However, their large computational costs can hinder their use in practice. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink