DSRIG: Incorporating graphical structure in the regularized modeling of SNP data

Pork Production with Entire Males: Directions for Control of Boar Taint

Simple Summary

Castration of male piglets has traditionally been carried out to control boar taint, but animal welfare concerns about surgical castration has brought this practice under scrutiny. In addition, castration decreases growth performance and increases the environmental impact of pork production, so alternatives to castration are needed to control boar taint. In this review, we summarize the current knowledge on boar taint metabolism and outline some key areas that require further study. We also describe some opportunities for controlling the boar taint problem and propose that by defining the differences in metabolic processes and the genetic variations that can lead to boar taint in individual pigs, we can design effective custom solutions for boar taint.

Abstract

Boar taint is caused by the accumulation of androstenone and skatole and other indoles in the fat; this is regulated by the balance between synthesis and degradation of these compounds and can be affected by a number of factors, including environment and management practices, sexual maturity, nutrition, and genetics. Boar taint can be controlled by immunocastration, but this practice has not been accepted in some countries. Genetics offers a long-term solution to the boar taint problem via selective breeding or genome editing. A number of short-term strategies to control boar taint have been proposed, but these can have inconsistent effects and there is too much variability between breeds and individuals to implement a blanket solution for boar taint. Therefore, we propose a precision livestock management approach to developing solutions for controlling taint. This involves determining the differences in metabolic processes and the genetic variations that cause boar taint in specific groups of pigs and using this information to design custom treatments based on the cause of boar taint. Genetic, proteomic or metabolomic profiling can then be used to identify and implement effective solutions for boar taint for specific populations of animals.

Sparse Convolutional Neural Networks for Genome-Wide Prediction

Genome-wide prediction (GWP) has become the state-of-the art method in artificial selection. Data sets often comprise number of genomic markers and individuals in ranges from a few thousands to millions. Hence, computational efficiency is important and various machine learning methods have successfully been used in GWP. Neural networks (NN) and deep learning (DL) are very flexible methods that usually show outstanding prediction properties on complex structured data, but their use in GWP is nevertheless rare and debated. This study describes a powerful NN method for genomic marker data that can easily be extended. It is shown that a one-dimensional convolutional neural network (CNN) can be used to incorporate the ordinal information between markers and, together with pooling and ℓ₁-norm regularization, provides a sparse and computationally efficient approach for GWP. The method, denoted CNNGWP, is implemented in the deep learning software Keras, and hyper-parameters of the NN are tuned with Bayesian optimization. Model averaged ensemble predictions further reduce prediction error. Evaluations show that CNNGWP improves prediction error by more than 25% on simulated data and around 3% on real pig data compared with results obtained with GBLUP and the LASSO. In conclusion, the CNNGWP provides a promising approach for GWP, but the magnitude of improvement depends on the genetic architecture and the heritability.