# Genomic prediction of feed efficiency in boars by deep learning

## TL;DR

This paper shows that deep learning models can better predict feed efficiency in pigs than traditional methods, though at higher computational cost.

## Contribution

The study introduces a novel method for estimating genetic variance using deep learning in genomic prediction.

## Key findings

- Deep learning models outperformed linear models in predicting feed efficiency in boar populations.
- Deep learning captured nonadditive genetic variance, but this did not significantly improve predictive ability.
- Multilayer perceptrons showed the highest predictive ability in both sire and dam line test populations.

## Abstract

Pork is the most widely consumed meat globally, and the industry has achieved substantial genetic advancements for several traits using genomic selection. However, traditional linear genomic prediction models may be inadequate for predicting complex traits, such as feed efficiency, as they primarily capture additive genetic effects and overlook nonadditive effects, including dominance and epistasis. Deep learning (DL) has the potential to address this limitation due to its ability to model nonlinear patterns inherent in genomic data. The objectives of this study were to compare the predictive ability of DL models to the linear models for predicting feed efficiency (FE) trait in 2 boar populations, estimate the nonadditive genetic variance captured by DL, and assess its effect on predictive ability. Our results showed that the DL models using the averaged-prediction method had the highest predictive ability in the sire line test population (0.381 for multilayer perceptron [MLP] and 0.377 for convolutional neural network [CNN]), compared to 0.366 for linear models. DL models also showed higher abilities in the dam line test population, with MLP achieving a predictive ability of 0.364. Additionally, we showed that DL models captured nonadditive variance; however, this did not significantly improve predictive ability. In conclusion, DL models, particularly MLP, demonstrated the highest predictive ability for FE, improving performance by approximately 4.1% for the sire line and 2.8% for the dam line compared to the traditional linear models. Therefore, DL models are recommended for predicting phenotypes and for estimating total genetic effects, including nonadditive components. However, this comes at a significant increase of computational cost.

The target audience for this research are researchers with interest in using deep learning (DL) for genomic prediction. The article presents a different way of estimating DL prediction accuracy, provides insight into using data augmentation technique in animal breeding, and presents a novel method of estimating genetic variance with DL. In this article, Onabanjo et al. used DL for genomic prediction of feed efficiency (FE). The authors hypothesized that DL models might capture the unknown patterns of gene interactions for complex traits and thus might have more accurate prediction compared to linear models. Their results confirmed that DL models capture non-additive genetic effects.