Cargando…
Genomic prediction through machine learning and neural networks for traits with epistasis
Genomic wide selection (GWS) is one contributions of molecular genetics to breeding. Machine learning (ML) and artificial neural networks (ANN) methods are non-parameterized and can develop more accurate and parsimonious models for GWS analysis. Multivariate Adaptive Regression Splines (MARS) is con...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Research Network of Computational and Structural Biotechnology
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9547190/ https://www.ncbi.nlm.nih.gov/pubmed/36249559 http://dx.doi.org/10.1016/j.csbj.2022.09.029 |
_version_ | 1784805208984911872 |
---|---|
author | Costa, Weverton Gomes da Celeri, Maurício de Oliveira Barbosa, Ivan de Paiva Silva, Gabi Nunes Azevedo, Camila Ferreira Borem, Aluizio Nascimento, Moysés Cruz, Cosme Damião |
author_facet | Costa, Weverton Gomes da Celeri, Maurício de Oliveira Barbosa, Ivan de Paiva Silva, Gabi Nunes Azevedo, Camila Ferreira Borem, Aluizio Nascimento, Moysés Cruz, Cosme Damião |
author_sort | Costa, Weverton Gomes da |
collection | PubMed |
description | Genomic wide selection (GWS) is one contributions of molecular genetics to breeding. Machine learning (ML) and artificial neural networks (ANN) methods are non-parameterized and can develop more accurate and parsimonious models for GWS analysis. Multivariate Adaptive Regression Splines (MARS) is considered one of the most flexible ML methods, automatically modeling nonlinearities and interactions of the predictor variables. This study aimed to evaluate and compare methods based on ANN, ML, including MARS, and G-BLUP through GWS. An F2 population formed by 1000 individuals and genotyped for 4010 SNP markers and twelve traits from a model considering epistatic effect, with QTL numbers ranging from eight to 480 and heritability ([Formula: see text]) of 0.3, 0.5 or 0.8 were simulated. Variation in heritability and number of QTL impacts the performance of methods. About quantitative traits (40, 80, 120, 240, and 480 QTLs) was observed highest R2 to Radial Base Network (RBF) and G-BLUP, followed by Random Forest (RF), Bagging (BA), and Boosting (BO). RF and BA also showed better results for traits to [Formula: see text] of 0.3 with [Formula: see text] values 16.51% and 16.30%, respectively, while MARS methods showed better results for oligogenic traits with [Formula: see text] values ranging from 39,12 % to 43,20 % in [Formula: see text] of 0.5 and from 59.92% to 78,56% in [Formula: see text] of 0.8. Non-additive MARS methods also showed high R2 for traits with high heritability and 240 QTLs or more. ANN and ML methods are powerful tools to predict genetic values in traits with epistatic effect, for different degrees of heritability and QTL numbers. |
format | Online Article Text |
id | pubmed-9547190 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Research Network of Computational and Structural Biotechnology |
record_format | MEDLINE/PubMed |
spelling | pubmed-95471902022-10-14 Genomic prediction through machine learning and neural networks for traits with epistasis Costa, Weverton Gomes da Celeri, Maurício de Oliveira Barbosa, Ivan de Paiva Silva, Gabi Nunes Azevedo, Camila Ferreira Borem, Aluizio Nascimento, Moysés Cruz, Cosme Damião Comput Struct Biotechnol J Research Article Genomic wide selection (GWS) is one contributions of molecular genetics to breeding. Machine learning (ML) and artificial neural networks (ANN) methods are non-parameterized and can develop more accurate and parsimonious models for GWS analysis. Multivariate Adaptive Regression Splines (MARS) is considered one of the most flexible ML methods, automatically modeling nonlinearities and interactions of the predictor variables. This study aimed to evaluate and compare methods based on ANN, ML, including MARS, and G-BLUP through GWS. An F2 population formed by 1000 individuals and genotyped for 4010 SNP markers and twelve traits from a model considering epistatic effect, with QTL numbers ranging from eight to 480 and heritability ([Formula: see text]) of 0.3, 0.5 or 0.8 were simulated. Variation in heritability and number of QTL impacts the performance of methods. About quantitative traits (40, 80, 120, 240, and 480 QTLs) was observed highest R2 to Radial Base Network (RBF) and G-BLUP, followed by Random Forest (RF), Bagging (BA), and Boosting (BO). RF and BA also showed better results for traits to [Formula: see text] of 0.3 with [Formula: see text] values 16.51% and 16.30%, respectively, while MARS methods showed better results for oligogenic traits with [Formula: see text] values ranging from 39,12 % to 43,20 % in [Formula: see text] of 0.5 and from 59.92% to 78,56% in [Formula: see text] of 0.8. Non-additive MARS methods also showed high R2 for traits with high heritability and 240 QTLs or more. ANN and ML methods are powerful tools to predict genetic values in traits with epistatic effect, for different degrees of heritability and QTL numbers. Research Network of Computational and Structural Biotechnology 2022-09-24 /pmc/articles/PMC9547190/ /pubmed/36249559 http://dx.doi.org/10.1016/j.csbj.2022.09.029 Text en © 2022 Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Biotechnology. https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
spellingShingle | Research Article Costa, Weverton Gomes da Celeri, Maurício de Oliveira Barbosa, Ivan de Paiva Silva, Gabi Nunes Azevedo, Camila Ferreira Borem, Aluizio Nascimento, Moysés Cruz, Cosme Damião Genomic prediction through machine learning and neural networks for traits with epistasis |
title | Genomic prediction through machine learning and neural networks for traits with epistasis |
title_full | Genomic prediction through machine learning and neural networks for traits with epistasis |
title_fullStr | Genomic prediction through machine learning and neural networks for traits with epistasis |
title_full_unstemmed | Genomic prediction through machine learning and neural networks for traits with epistasis |
title_short | Genomic prediction through machine learning and neural networks for traits with epistasis |
title_sort | genomic prediction through machine learning and neural networks for traits with epistasis |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9547190/ https://www.ncbi.nlm.nih.gov/pubmed/36249559 http://dx.doi.org/10.1016/j.csbj.2022.09.029 |
work_keys_str_mv | AT costawevertongomesda genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT celerimauriciodeoliveira genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT barbosaivandepaiva genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT silvagabinunes genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT azevedocamilaferreira genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT boremaluizio genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT nascimentomoyses genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT cruzcosmedamiao genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis |