Comparación de métodos de aprendizaje automático para predicción de valores de cría genómicos en características de crecimiento en bovinos Suizo Europeo
DOI:
https://doi.org/10.22319/rmcp.v16i1.6616Palabras clave:
Árboles de regresión, Bosques aleatorios, Redes neuronales, Capacidad predictivaResumen
Los algoritmos de Aprendizaje Automático (AA) han demostrado ventaja al abordar desafíos asociados con la cantidad y la complejidad de la información, permiten descubrir patrones, realizar análisis eficientes y servir como herramienta para la toma de decisiones. Este estudio, tuvo como objetivo comparar cuatro métodos de AA: redes neuronales artificiales (RN), árboles de regresión (AR), bosques aleatorios (BA) y máquina de soporte vectorial (SVM) para predecir el valor genómico en bovinos Suizo Europeo utilizando registros fenotípicos de pesos al nacimiento (PN), destete (PD) y al año (PA), así como información genómica. Los resultados indican que la capacidad predictiva de los modelos varía según la característica y la cantidad de información disponible. En general, RN, BA y SVM mostraron un desempeño similar, mientras que AR tuvo un desempeño inferior. La metodología SVM destacó como la herramienta con mayor potencial, obteniendo los valores más altos de correlación Pearson entre fenotipos corregidos y valores genéticos predichos para PD. A pesar de un mayor costo computacional, RN tuvo un desempeño razonable, especialmente para PN y PA. La selección del modelo final depende de las necesidades particulares de la aplicación, así como de factores prácticos como la disponibilidad de datos, recursos computacionales y la interpretabilidad; pero en general, RN y SVM surgieron como opciones sólidas en varias categorías.
Descargas
Citas
Pérez-Enciso M, Steibel JP. Phenomes: the current frontier in animal breeding. Genet Sel Evol 2021;53(1):22. doi: 10.1186/s12711-021-00618-1. PMID: 33673800; PMCID: PMC7934239. DOI: https://doi.org/10.1186/s12711-021-00618-1
Song H, Dong T, Yan X, Wang W, Tian Z, Hu H. Using Bayesian threshold model and machine learning method to improve the accuracy of genomic prediction for ordered categorical traits in fish. Agric Comm 2023;1(1):100005. https://doi.org/10.1016/j.agrcom.2023.100005. DOI: https://doi.org/10.1016/j.agrcom.2023.100005
Rodríguez-Alcántar E. Aplicación de algoritmos de aprendizaje automático para la clasificación de ganado lechero utilizando SNP de genoma completo [tesis Doctorado]. Baja California, México: Universidad Autónoma de Baja California; 2019.
Campos TL, Korhonen PK, Hofmann A, Gasser RB, Young ND. Harnessing model organism genomics to underpin the machine learning-based prediction of essential genes in eukaryotes – Biotechnological implications. Biotechnol Adv 2022;54:107822. https://doi.org/10.1016/J.BIOTECHADV.2021.107822. DOI: https://doi.org/10.1016/j.biotechadv.2021.107822
Zhao T, Wu H, Wang X, Zhao Y, Wang L, Pan J, et al. Integration of eQTL and machine learning to dissect causal genes with pleiotropic effects in genetic regulation networks of seed cotton yield. Cell Rep 2023;42(9). https://doi.org/10.1016/j.celrep.2023.113111. DOI: https://doi.org/10.1016/j.celrep.2023.113111
Guo T, Li X. Machine learning for predicting phenotype from genotype and environment. Curr Opin Biotechnol 2023;79:102853. https://doi.org/10.1016/J.COPBIO.2022.102853. DOI: https://doi.org/10.1016/j.copbio.2022.102853
Wang X, Shi S, Wang G, Luo W, Wei X, Qiu A, et al. Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs. J Anim Sci Biotechnol 2022;13(60). https://doi.org/10.1186/s40104-022-00708-0. DOI: https://doi.org/10.1186/s40104-022-00708-0
Long N, Gianola D, Rosa GJM, Weigel KA. Application of support vector regression to genome-assisted prediction of quantitative traits. Theor Appl Genet 2011;123(7):1065-1074. https://doi.org/10.1007/s00122-011-1648-y. DOI: https://doi.org/10.1007/s00122-011-1648-y
González‐Camacho JM, Ornella L, Pérez‐Rodríguez P, Gianola D, Dreisigacker S, Crossa J. Applications of machine learning methods to genomic selection in breeding wheat for rust resistance. Plant Genome 2018;11(2):170104. https://doi.org/10.3835/plantgenome2017.11.0104.
Müller AC, Guido S. Introduction to Machine Learning with Python: A guide for data scientists. O'Reilly Media, Inc. 2016.
Azodi CB, Bolger, E, McCarren, A, Roantree, M, de los Campos, G, Shiu, SH. Benchmarking parametric and machine learning models for genomic prediction of complex traits. G3: Genes, Genomes, Genetics 2019;9(11):3691-3702. https://doi.org/10.1534/g3.119.400498. DOI: https://doi.org/10.1534/g3.119.400498
Fa R, Cozzetto D, Wan C, Jones DT. Predicting human protein function with multitask deep neural networks. PLoS ONE 2018;13(6). https://doi.org/10.1371/journal.pone.0198216. DOI: https://doi.org/10.1371/journal.pone.0198216
VanRaden PM. Efficient methods to compute genomic predictions. J Dairy Sci 2008;91(11):4414-4423. https://doi.org/10.3168/jds.2007-0980. DOI: https://doi.org/10.3168/jds.2007-0980
Valerio-Hernández JE, Pérez-Rodríguez P, Ruíz-Flores A. Quantile regression for prediction of complex traits in Braunvieh cattle using SNP markers and pedigree. Rev Mex Cienc Pecu 2023;14(1):172–189. https://doi.org/10.22319/rmcp.v14i1.6182. DOI: https://doi.org/10.22319/rmcp.v14i1.6182
Valerio-Hernández JE, Ruíz-Flores A, Nilforooshan MA, Pérez-Rodríguez P. Single-step genomic evaluation for growth traits in a Mexican Braunvieh cattle population. Anim Biosci 2023;36(7):1003-1009. https://doi.org/10.5713/ab.22.0158. DOI: https://doi.org/10.5713/ab.22.0158
Jarquín D, Howard R, Graef G, Lorenz A. Response surface analysis of genomic prediction accuracy values using quality control covariates in soybean. Evol Bioinform Online 2019;15:1176934319831307. https://doi.org/10.1177/117693431 9831307. DOI: https://doi.org/10.1177/1176934319831307
Sargolzaei M, Chesnais JP, Schenkel FS. A new approach for efficient genotype imputation using information from relatives. BMC Genomics 2014;15:478. https://doi.org/10.1186/1471-2164-15-478. DOI: https://doi.org/10.1186/1471-2164-15-478
Pérez-Rodríguez P, Crossa J, Rutkoski J, Poland J, Singh R, Legarra A, et al. Single-step genomic and Pedigree Genotype × Environment interaction models for predicting wheat lines in international environments. Plant Genome 2017;10(2). https://doi.org/10.3835/plantgenome2016.09.0089. DOI: https://doi.org/10.3835/plantgenome2016.09.0089
Pérez P, de los Campos G. Genome-wide regression and prediction with the BGLR statistical package. Genetics 2014;198:483–95. https://doi.org/10.1534/genetics.114.164442. DOI: https://doi.org/10.1534/genetics.114.164442
Gianola D, Okut H, Weigel KA, Rosa GJM. Predicting complex quantitative traits with Bayesian neural networks: a case study with Jersey cows and wheat. BMC Genetics 2011;12:87. doi.org/10.1186/1471-2156-12-87. DOI: https://doi.org/10.1186/1471-2156-12-87
Pérez-Rodríguez P, Flores-Galarza S, Vaquera-Huerta H, del Valle-Paniagua DH, Montesinos-López OA, Crossa J. Genome-based prediction of Bayesian linear and non-linear regression models for ordinal data. Plant Genome 2020;13(2). https://doi.org/10.1002/tpg2.20021. DOI: https://doi.org/10.1002/tpg2.20021
Peng J, Yan G, Druzhinin Z. Applying an artificial neural network- Developed collective animal behavior algorithm for seismic reliability evaluation of structure. Measurement 2023;220:113355. DOI: https://doi.org/10.1016/j.measurement.2023.113355
Wang C, Xu S, Liu J, Yang J, Liu C. Building an improved artificial neural network model based on deeply optimizing the input variables to enhance rutting prediction. Constr Build Mater 2022;348:128658. DOI: https://doi.org/10.1016/j.conbuildmat.2022.128658
Bai S, Kolter JZ, Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. 2018. http://arxiv.org/abs/1803.01271.
Pérez-Rodríguez P, Gianola D, Weigel KA, Rosa GJM, Crossa J. An R package for fitting Bayesian regularized neural networks with applications in animal breeding. J Anim Sci 2013;91(8):3522–3531. https://doi.org/10.2527/jas.2012-6162. DOI: https://doi.org/10.2527/jas.2012-6162
Pérez-Rodriguez P, Gianola D. Title Bayesian regularization for Feed-Forward Neural Networks. 2022. https://cran.r-project.org/package=brnn.
R Core Team. R: A language and environment for statistical computing. R Foundation for statistical computing. 2021. Vienna, Austria. https://www.R-project.org/.
Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and Regression Trees. Wadsworth. 1984. https://doi.org/10.1201/9781315139470. DOI: https://doi.org/10.1201/9781315139470
Therneau T, Atkinson B, Ripley B. Package “rpart”. 2022. https://cran.r-project.org/package=rpart.
Liaw A, Wiener M. Classification and Regression by random Forest. R News 2002;2(3): 18-22. https://CRAN.R-project.org/doc/Rnews/.
Chih-Chung C, Chih-Jen L. LIBSVM: A library for support vector machines. ACM Trans Intell Syst Technol 2011;2(3):1-27. http://www.csie.ntu.edu.tw/~cjlin/libsvm. DOI: https://doi.org/10.1145/1961189.1961199
Hastie T, Tibshirani R, Friedman J. The elements of statistical learning: Data mining, inference, and prediction. Berlin: Springer Science & Business Media. 2008.
Meyer D, Dimitriadou E, Hornik K, Weingessel A, Leisch F, Chang C, Lin C. Package “e1071”. 2023. https://cran.r-project.org/package=e1071.
Berrar D. Cross-Validation. ABC of bioinformatics. Elsevier 2018; 542-545. https://doi.org/10.1016/B978-0-12-809633-8.20349-X. DOI: https://doi.org/10.1016/B978-0-12-809633-8.20349-X
Royston P. An extension of Shapiro and Wilk's W test for normality to large samples. Applied Statistics 1982;(31):115-124. https://doi.org/10.2307/2347973. DOI: https://doi.org/10.2307/2347973
González-Recio O, Forni S. Genome-wide prediction of discrete traits using bayesian regressions and machine learning. Genet Sel 2011;43(1): https://doi.org/10.1186/1297-9686-43-7. DOI: https://doi.org/10.1186/1297-9686-43-7
Gianola D, de los Campos G. Inferring genetic values for quantitative traits non-parametrically. Genet Res (Camb) [Internet]. 2009/01/06. 2008;90(6):525–540. DOI: https://doi.org/10.1017/S0016672308009890
Gianola D, Fernando RL, Stella A. Genomic-Assisted prediction of genetic value with semiparametric procedures. Genetics 2006;173(3):1761–1776. https://doi.org/10.1534/genetics.105.049510. DOI: https://doi.org/10.1534/genetics.105.049510
Monaco A, Pantaleo E, Amoroso N, Lacalamita A, Lo Giudice C, Fonzino A, et al. A primer on machine learning techniques for genomic applications. Comput Struct Biotechnol J 2021;19:4345-4359. https://doi.org/10.1016/j.csbj.2021.07.021. DOI: https://doi.org/10.1016/j.csbj.2021.07.021
Alves AAC, da Costa RM, Bresolin T, Fernandes Júnior GA, Espigolan R, Ribeiro AMF, et al. Genome-wide prediction for complex traits under the presence of dominance effects in simulated populations using GBLUP and machine learning methods. J Anim Sci 2020;98(6):1–11. https://doi.org/10.1093/jas/skaa179. DOI: https://doi.org/10.1093/jas/skaa179
Cuyabano BCD, Boichard D, Gondro C. Expected values for the accuracy of predicted breeding values accounting for genetic differences between reference and target populations. Genet Sel Evol 2024;56:15. https://doi.org/10.1186/s12711-024-00876-9. DOI: https://doi.org/10.1186/s12711-024-00876-9
Zhang H, Yin L, Wang M, Yuan X, Liu X. Factors affecting the accuracy of genomic selection for agricultural economic traits in maize, cattle, and pig populations. Front Genet 2019;14(10):189. https://doi.org/10.3389/fgene.2019.00189. DOI: https://doi.org/10.3389/fgene.2019.00189
Zhao W, Lai X, Liu D, Zhang Z, Ma P, Wang Q, et al. Applications of support vector machine in genomic prediction in pig and maize populations. Front Genet 2020;11:598318. https://doi.org/10.3389/fgene.2020.598318. DOI: https://doi.org/10.3389/fgene.2020.598318
González-Camacho JM, Ornella L, Pérez-Rodríguez P, Gianola D, Dreisigacker S, Crossa J. Applications of machine learning methods to genomic selection in breeding wheat for rust resistance. Plant Genome 2018;11(2). https://doi.org/10.3835/plantgenome2017.11.0104. DOI: https://doi.org/10.3835/plantgenome2017.11.0104
Libbrecht M, Noble W. Machine learning applications in genetics and genomics. Nat Rev Genet 2015;16:321-332. https://doi.org/10.1038/nrg3920. DOI: https://doi.org/10.1038/nrg3920
Descargas
Publicado
Cómo citar
-
Resumen975
-
PDF454
-
PDF 311
-
Texto completo42
-
Full text 48
Número
Sección
Licencia
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
Los autores/as que publiquen en la Revista Mexicana de Ciencias Pecuarias aceptan las siguientes condiciones:
De acuerdo con la legislación de derechos de autor, la Revista Mexicana de Ciencias Pecuarias reconoce y respeta el derecho moral de los autores/as, así como la titularidad del derecho patrimonial, el cual será cedido a la revista para su difusión en acceso abierto.
Esta obra está bajo una Licencia Creative Commons Atribución-NoComercial-CompartirIgual 4.0 Internacional.
