Hayrettin OKUT, Daniel GİANOLA, Kent WEİGEL, Guilherme J. M. ROSA

Evaluation of Predictive Ability of Bayesian Regularized Neural Network Using Cholesky Factorization of Genetic Relationship Matrices for Additive and Non-additive Genetic Effects

This study aimed to explore the effects of additive and non-additive genetic effects on the prediction of complex traits using Bayesian regularized artificial neural network (BRANN). The data sets were simulated for two hypothetical pedigrees with five different fractions of total genetic variance accounted by additive, additive x additive, and additive x additive x additive genetic effects. A feed forward artificial neural network (ANN) with Bayesian regularization (BR) was used to assess the performance of different nonlinear ANNs and compare their predictive ability with those from linear models under different genetic architectures of phenotypic traits. Effective number of parameters and sum of squares error (SSE) in test data sets were used to evaluate the performance of ANNs. Distribution of weights and correlation between observed and predicted values in the test data set were used to evaluate the predictive ability. There were clear and significant improvements in terms of the predictive ability of linear (equivalent Bayesian ridge regression) and nonlinear models when the proportion of additive genetic variance in total genetic variance ( ) increased. On the other hand, nonlinear models outperformed the linear models across different genetic architectures. The weights for the linear models were larger and more variable than for the nonlinear network, and presented leptokurtic distributions, indicating strong shrinkage towards 0. In conclusion, our results showed that: a) inclusion of non-additive effects did not improve the prediction ability compared to purely additive models, b) The predictive ability of BRANN architectures with nonlinear activation function were substantially larger than the linear models for the scenarios considered.

Keywords:

Artificial neural networks, Bayesian regularization, Additive and non-additive genetic effects,

PDF

___

Allison, M. K., Cullus, C. B., Gilmour, A. R., Eccleston, J. A. and Thompson, R. (2009) Estimation in a multiplicative mixed model involving a genetic relationship matrix. Genetics Selection Evolution 41:33.
Bagheri, H. C., Wagner, G. P. (2004) Evolution of dominance in metabolic pathways. Genetics, 168, 1713-35.
Battiti, R. (1992) First- and second order methods for learning: Between steepest descent and Newton’s method. Neural Computation, 4, 2, pp. 141-166.
Bradshaw, W. E., Haggerty, B. P., Holzapfel, C. M. (2005) Epistasis underlying a fitness trait within a natural population of the pitcher-plant mosquito, Genetics, 169, 485-8.
Calus, M. P. L. (2010) Genomic breeding value prediction: methods and procedures. Animal, 4,157-164.
Carlborg, O., Haley, C. S. (2004) Epistasis: too often neglected in complex trait studies? Nat Rev Genet 5, 618–625.
Cheverud, J., Routman, J. (1995) Epistasis and its contribution to genetic variance components. Genetics, 139,1455-61.
Demuth, H., Beale, M., Hagan, M. (2009) Neural Network Toolbox™ 6 User’s Guide. The MathWorks, Inc., Natick, MA, USA.
Foresee, F. D., Hagan, M. T. (1997) Gauss-Newton approximation to Bayesian learning, In Proc. IEEE Int. Conf. Neural Networks. Edited by Martin T. Hagan, 1930–1935.
Gencay, R., Qi, M (2001) Pricing and hedging derivative securities with neural networks: Bayesian regularization, early stopping, and bagging. IEEE Trans. Neural Networks, 12,726-734.
Gianola, D., de los Campos, G. (2008) Inferring genetic values for quantitative traits non-parametrically. Genetics Research, 90(6), 525-540.
Gianola, D., Okut, H., Weigel, K. A., Rosa, G. J. M. (2011). Predicting complex quantitative traits with Bayesian neural networks: a case study with Jersey cows and wheat. BMC genetics, 12-87 http://www.biomedcentral.com/1471-2156/12/87
Habier, D., Fernando, R. L., Dekkers, J. C. M. (2007) The impact of genetic relationship information on genome-assisted breeding values. Genetics, 177(4), 2389-2397.
Hallander, J., Waldmann, P. (2007) The effect of non-additive genetic interactions on selection in multi-locus genetic models. Heredity, 98, 349–359.
Hill W.G., Goddard M.E., Visscher P.M. (2008) Data and theory point to mainly additive genetic variance for complex traits. PloS Genet., 4, e1000008.
Hofmann, T., Scholkopf, B., Smola, J. A. (2008) Kernel Methods In Machine Learning. The Annals of Statistics, 36:3, 1171–1220.
Ingileif, B. H., Yuster, S. D. (2008) A complete classification of epistatic two-locus models. BMC Genetics, 9:17.
Jamrozik, J., Fatehi, J., Kistemaker, G. J., Schaeffer, L.R. (2005) Estimates of genetic parameters for Canadian Holstein female reproduction traits. J. Dairy Sci. 88, 2199–2208.
Alvarez-Castro, J. M., Orjan, C. A. (2007) Uniﬁed Model for Functional and Statistical Epistasis and Its Application in Quantitative Trait Loci Analysis. Genetics, 176, 1151–1167.
Kumar, P., Merchant, S. N., Desai, U. B. (2004) Improving performance in pulse radar detection using Bayesian regularization for neural network training. Digital Signal Processing, 14,438–448.
Lampinen, J., Vehtari, A. (2001) Bayesian approach for neural networks review and case studies, Neural Networks, 14, 257-274.
Le Rouzic, A., Alvarez-Castro, J. M., Carlborg, O. (2008) Dissection of the genetic architecture of body weight in chicken reveals the impact of epistasis on domestication traits. Genetics, 179, 1591-9.
MacKay, D. J. C. (1992) Bayesian interpolation. Neural Computation, 4, 415–447.
MacKay, J. C. D. (2008) Information theory, inference and learning algorithms. Cambridge University Press, Cambridge, UK.
Marwala, T. (2007) Bayesian training of neural networks using genetic programming. Pattern Recognition Letters, 28,1452–1458.
Nagy, I., Gorjanc, G., Curik, I., Farkas, J., Kiszlinger, H., Szendro, Z. (2013) The contribution of dominance and inbreeding depression in estimating variance components for litter size in Pannon White rabbits. J. Anim. Breed. Genet., 130, 303–311.
Okut, H., Gianola, D., Rosa, G. J. M., Weigel, K. A. (2011) Prediction of body mass index in mice using dense molecular markers and a regularized neural network. Genet Res. 93(3):189–201. Available from: http:// dx.doi.org/10.1017/S0016672310000662
Okut H. (2016) Artificial Neural Networks Model and Application. Joao Juis G. Rosa (Eds), Bayesian Regularized Neural Networks for Small n Big p Data (pp 27-48). London, UK. IntechOpen.
Okut H. (2021) Deep Learning and Application, Pier Luigi Mazzeo and Paolo Spagnolo, (Eds), Deep Learning for Subtyping and Prediction of Diseases: Long-Short Term Memory (pp 27-48). London, UK. IntechOpen. DOI: 10.5772/intechopen.96180.
Oakey, H., Verbyla, A. P., Pitchford, W., Cullis, B. R., Kuchel, H. (2006) Joint modeling of additive and non-additive genetic line effects in single field trials. Theor Appl Genet, 113, 809-819. Pirchner, F. (1983) Population genetics in animal breeding. Second Edition. Planum Press, New York, USA.
Ripley, B. D. (2007) Pattern recognition and neural networks. Cambridge University Press, Cambridge, UK.
Sorich, M. J., Miners, J. O., Ross, A. M., Winker, D. A., Burden, F. R., Smith, P. A. (2003) Comparison of Linear and Nonlinear Classification Algorithms for the Prediction of Drug and Chemical Metabolism by Human UDP-Glucuronosyltransferase Isoforms. J. Chem. Inf. Comput. Sci., 43, 2019-2024.
Titterington, D. M. (2004) Bayesian methods for neural networks and related models. Statistical Science, 19, 128–139.
Valentina, P., Lawrence, R. S., Filippo M, Vern, O. (2007) Non-additive genetic effects for fertility traits in Canadian Holstein cattle. Genet. Sel. Evol., 39, 181–193.
Wade, M. (2002) A gene's eye view of epistasis, selection and speciation. J Evol Biol, 15, 337-346.
Weinreich, D. M., Watson, R. A., Chao, L. (2005) Perspective: sign epistasis and genetic constraint on evolutionary trajectories. Evolution, 59, 1165-74.
Wittenburg, D., Melzer, N., Reinsch, N. (2011) Including non-additive genetic effects in Bayesian methods for the prediction of genetic values based on genome-wide markers. BMC Genetic, 12:74.
Xu, M., Zengi, G., Xu, X., Huang, G., Jiang, R., Sun, W. (2006) Application of Bayesian regularized BP neural network model for trend analysis, acidity and chemical composition of precipitation in North. Water, Air, and Soil Pollution, 172, 167–184.
Zhu, M., Yu, M., Zhao, S. (2009) Understanding Quantitative Genetics in the Systems Biology Era. Int. J. Biol. Sci., 5(2), 161-170.