Multivariate Statistical Machine Learning Methods for Genomic Prediction

Preface.- Chapter 1.- General elements of genomic selection and statistical learning.- Chapter. 2.- Preprocessing tools for data preparation.- Chapter. 3.- Elements for building supervised statistical machine learning models.- Chapter. 4.- Overfitting, model tuning and evaluation of prediction performance.- Chapter. 5.- Linear Mixed Models.- Chapter. 6.- Bayesian Genomic Linear Regression.- Chapter. 7.- Bayesian and classical prediction models for categorical and count data.- Chapter. 8.- Reproducing Kernel Hilbert Spaces Regression and Classification Methods.- Chapter. 9.- Support vector machines and support vector regression.- Chapter. 10.- Fundamentals of artificial neural networks and deep learning.- Chapter. 11.- Artificial neural networks and deep learning for genomic prediction of continuous outcomes.- Chapter. 12.- Artificial neural networks and deep learning for genomic prediction of binary, ordinal and mixed outcomes.- Chapter. 13.- Convolutional neural networks.- Chapter. 14.- Functional regression.- Chapter. 15.- Random forest for genomic prediction.

Dr. Osval Antonio Montesinos López earned a PhD in Statistics and Biometry from the University of Nebraska-Lincoln, USA, in 2014.  He is currently a Professor of Statistics, Probability and Statistical Learning Methods at the Facultad de Telemática, University of Colima, México. His areas of interest include the development of novel genomic prediction models for plant breeding, high-dimensional data analysis, generalized linear mixed models and Bayesian analysis, multivariate analysis and experimental designs. He has contributed univariate and multivariate genomic prediction models for predicting breeding values in plants with normal, binary, count and ordinal phenotypes.
Dr. Abelardo Montesinos López holds a PhD in Probability and Statistics from the Centro de Investigación en Matemáticas (CIMAT), Guanajuato, México.  He is currently a Professor of Statistical Interference, Probability and Statistical Learning Methods at the Departamento de Matemáticas, CentroUniversitario de Ciencias Exactas e Ingenierías (CUCEI), Universidad de Guadalajara, Mexico. His areas of interest are: development of novel genomic prediction models for plant breeding, high dimensional data analysis, generalized linear mixed models, survival analysis, Bayesian analysis and multivariate analysis. He has contributed univariate and multivariate genomic prediction models for predicting breeding values in plants with normal, binary, count and ordinal phenotypes.
Dr. José Crossa is a distinguished Scientist at the Biometrics and Statistics Unit of the International Maize and Wheat Improvement Center (CIMMYT). He has contributed to the statistical analyses of plant breeding trials with an emphasis on modeling genotype x environment interactions, QTL x environment interactions and genomic x environment interactions. He has significantly advanced the integration of essential factors such as pedigree and trial data into genomic selection for crop breeding, by creating and describing