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...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-01-01
|
| Series: | Computational and Structural Biotechnology Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2001037022004342 |
| _version_ | 1797978170788413440 |
|---|---|
| author | Weverton Gomes da Costa Maurício de Oliveira Celeri Ivan de Paiva Barbosa Gabi Nunes Silva Camila Ferreira Azevedo Aluizio Borem Moysés Nascimento Cosme Damião Cruz |
| author_facet | Weverton Gomes da Costa Maurício de Oliveira Celeri Ivan de Paiva Barbosa Gabi Nunes Silva Camila Ferreira Azevedo Aluizio Borem Moysés Nascimento Cosme Damião Cruz |
| author_sort | Weverton Gomes da Costa |
| collection | DOAJ |
| 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 (h2) 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 h2 of 0.3 with R2 values 16.51% and 16.30%, respectively, while MARS methods showed better results for oligogenic traits with R2 values ranging from 39,12 % to 43,20 % in h2 of 0.5 and from 59.92% to 78,56% in h2 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. |
| first_indexed | 2024-04-11T05:18:44Z |
| format | Article |
| id | doaj.art-b43284a44af440cdbded5705888b9609 |
| institution | Directory Open Access Journal |
| issn | 2001-0370 |
| language | English |
| last_indexed | 2024-04-11T05:18:44Z |
| publishDate | 2022-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computational and Structural Biotechnology Journal |
| spelling | doaj.art-b43284a44af440cdbded5705888b96092022-12-24T04:54:34ZengElsevierComputational and Structural Biotechnology Journal2001-03702022-01-012054905499Genomic prediction through machine learning and neural networks for traits with epistasisWeverton Gomes da Costa0Maurício de Oliveira Celeri1Ivan de Paiva Barbosa2Gabi Nunes Silva3Camila Ferreira Azevedo4Aluizio Borem5Moysés Nascimento6Cosme Damião Cruz7Department of General Biology, Bioinformatics Laboratory, Federal University of Viçosa, Viçosa, MG, Brazil; Corresponding author.Department of Statistics, Laboratory of Computational Intelligence and Statistical Learning, Federal University of Viçosa – UFV, Viçosa, MG, BrazilDepartment of Agronomy, Federal University of Viçosa, Viçosa, MG, BrazilDepartment of Mathematics and Statistics, Federal University of Rondônia, Ji-Paraná Campus, RO, BrazilDepartment of Agronomy, Federal University of Viçosa, Viçosa, MG, BrazilDepartment of Agronomy, Federal University of Viçosa, Viçosa, MG, BrazilDepartment of Statistics, Laboratory of Computational Intelligence and Statistical Learning, Federal University of Viçosa – UFV, Viçosa, MG, BrazilDepartment of General Biology, Bioinformatics Laboratory, Federal University of Viçosa, Viçosa, MG, BrazilGenomic 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 (h2) 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 h2 of 0.3 with R2 values 16.51% and 16.30%, respectively, while MARS methods showed better results for oligogenic traits with R2 values ranging from 39,12 % to 43,20 % in h2 of 0.5 and from 59.92% to 78,56% in h2 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.http://www.sciencedirect.com/science/article/pii/S2001037022004342Genome wide selectionQuantitative trait locusNon-additive effectsMultivariate adaptive regression splinesGenome-enabled prediction |
| spellingShingle | Weverton Gomes da Costa Maurício de Oliveira Celeri Ivan de Paiva Barbosa Gabi Nunes Silva Camila Ferreira Azevedo Aluizio Borem Moysés Nascimento Cosme Damião Cruz Genomic prediction through machine learning and neural networks for traits with epistasis Computational and Structural Biotechnology Journal Genome wide selection Quantitative trait locus Non-additive effects Multivariate adaptive regression splines Genome-enabled prediction |
| 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 | Genome wide selection Quantitative trait locus Non-additive effects Multivariate adaptive regression splines Genome-enabled prediction |
| url | http://www.sciencedirect.com/science/article/pii/S2001037022004342 |
| work_keys_str_mv | AT wevertongomesdacosta genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT mauriciodeoliveiraceleri genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT ivandepaivabarbosa genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT gabinunessilva genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT camilaferreiraazevedo genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT aluizioborem genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT moysesnascimento genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis AT cosmedamiaocruz genomicpredictionthroughmachinelearningandneuralnetworksfortraitswithepistasis |