Estimation of Variance Components and Genomic Prediction for Individual Birth Weight Using Three Different Genome-Wide SNP Platforms in Yorkshire Pigs

Vetinformatics from functional genomics to drug discovery: Insights into decoding complex molecular mechanisms of livestock systems in veterinary science

Having played important roles in human growth and development, livestock animals are regarded as integral parts of society. However, industrialization has depleted natural resources and exacerbated climate change worldwide, spurring the emergence of various diseases that reduce livestock productivity. Meanwhile, a growing human population demands sufficient food to meet their needs, necessitating innovations in veterinary sciences that increase productivity both quantitatively and qualitatively. We have been able to address various challenges facing veterinary and farm systems with new scientific and technological advances, which might open new opportunities for research. Recent breakthroughs in multi-omics platforms have produced a wealth of genetic and genomic data for livestock that must be converted into knowledge for breeding, disease prevention and management, productivity, and sustainability. Vetinformatics is regarded as a new bioinformatics research concept or approach that is revolutionizing the field of veterinary science. It employs an interdisciplinary approach to understand the complex molecular mechanisms of animal systems in order to expedite veterinary research, ensuring food and nutritional security. This review article highlights the background, recent advances, challenges, opportunities, and application of vetinformatics for quality veterinary services.

A Comparative Study of Machine Learning Methods for Predicting Live Weight of Duroc, Landrace, and Yorkshire Pigs

Simple Summary

Live weight is an important indicator of livestock productivity and serves as an informative measure for the health, feeding, breeding, and selection of livestock. In this paper, the live weight of pig was estimated using six morphometric measurements, breed, weight at birth, weight at weaning, and age at weaning. In the present paper, we propose a comparative analysis of various machine learning methods using outlier detection, normalisation, hyperparameter optimisation, and stack generalisation to increase the accuracy of the predictions of the live weight of pigs. The StackingRegressor algorithm yielded a prediction quality of the live weight of Duroc, Landrace, and Yorkshire pigs that was higher than that of the state-of-the art algorithms.

Abstract

Live weight is an important indicator of livestock productivity and serves as an informative measure for the health, feeding, breeding, and selection of livestock. In this paper, the live weight of pig was estimated using six morphometric measurements, weight at birth, weight at weaning, and age at weaning. This study utilised a dataset including 340 pigs of the Duroc, Landrace, and Yorkshire breeds. In the present paper, we propose a comparative analysis of various machine learning methods using outlier detection, normalisation, hyperparameter optimisation, and stack generalisation to increase the accuracy of the predictions of the live weight of pigs. The performance of live weight prediction was assessed based on the evaluation criteria: the coefficient of determination, the root-mean-squared error, the mean absolute error, and the mean absolute percentage error. The performance measures in our experiments were also validated through 10-fold cross-validation to provide a robust model for predicting the pig live weight. The StackingRegressor model was found to provide the best results with an MAE of 4.331 and a MAPE of 4.296 on the test dataset.