Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Feb 12;15(4):525.
doi: 10.3390/ani15040525.

Enhancing Genomic Prediction Accuracy of Reproduction Traits in Rongchang Pigs Through Machine Learning

Junge Wang  1 , Jie Chai  2   3 , Li Chen  2   3 , Tinghuan Zhang  2   3 , Xi Long  2   3 , Shuqi Diao  2   3 , Dong Chen  1 , Zongyi Guo  2   3 , Guoqing Tang  1 , Pingxian Wu  2   3
Affiliations

Enhancing Genomic Prediction Accuracy of Reproduction Traits in Rongchang Pigs Through Machine Learning

Junge Wang et al. Animals (Basel). .

Abstract

The increasing volume of genome sequencing data presents challenges for traditional genome-wide prediction methods in handling large datasets. Machine learning (ML) techniques, which can process high-dimensional data, offer promising solutions. This study aimed to find a genome-wide prediction method for local pig breeds, using 10 datasets with varying SNP densities derived from imputed sequencing data of 515 Rongchang pigs and the Pig QTL database. Three reproduction traits-litter weight, total number of piglets born, and number of piglets born alive-were predicted using six traditional methods and five ML methods, including kernel ridge regression, random forest, Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine, and Adaboost. The methods' efficacy was evaluated using fivefold cross-validation and independent tests. The predictive performance of both traditional and ML methods initially increased with SNP density, peaking at 800-900 k SNPs. ML methods outperformed traditional ones, showing improvements of 0.4-4.1%. The integration of GWAS and the Pig QTL database enhanced ML robustness. ML models exhibited superior generalizability, with high correlation coefficients (0.935-0.998) between cross-validation and independent test results. GBDT and random forest showed high computational efficiency, making them promising methods for genomic prediction in livestock breeding.

Keywords: Rongchang pigs; genomic prediction; machine learning; prediction accuracy.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

Figure 1
Figure 1
Imputation accuracy for each chromosome in Rongchang pigs. The imputation accuracy at various thresholds—0.3, 0.6, 0.9, and before filtering.
Figure 2
Figure 2
GWAS result for litter weight (LW), total number of piglets born (TNB), and number of piglets born alive (NBA) in Rongchang pigs. LW, TNB, and NBA are shown from inside to outside. Red sites indicate sites used for the weighting of each trait (p < 1 × 10−5). The numbers on the outer ring indicate chromosomes and the numbers on the central axis indicate −log10(P).
Figure 3
Figure 3
The genomic prediction accuracy of different methods for litter weight (LW), total number of piglets born (TNB), and number of piglets born alive (NBA) in Rongchang pigs. (A) The genomic prediction accuracy of LW. (B) The genomic prediction accuracy of TNB. (C) The genomic prediction accuracy of NBA. The redder the cell, the more accurate the prediction; white text: the highest predictive accuracy of each quantity; blue cell: the highest predictive accuracy of each method. The box plots show the median and distribution of accuracy for each method (right) and the violin plots show the same for each quantity (top).
Figure 4
Figure 4
Results comparing weighted and unweighted predictions for litter weight (LW) in Rongchang pigs. (A) The predictive results of KRR. (B) The predictive results of RF. (C) The predictive results of LightGBM. (D) The predictive results of Adaboost. (E) The predictive results of GBDT.
Figure 5
Figure 5
Results comparing weighted and unweighted predictions for total number of piglets born (TNB) in Rongchang pigs. (A) The predictive results of KRR. (B) The predictive results of RF. (C) The predictive results of LightGBM. (D) The predictive results of Adaboost. (E) The predictive results of GBDT.
Figure 6
Figure 6
Results comparing weighted and unweighted predictions for number of piglets born alive (NBA) in Rongchang pigs. (A) The predictive results of KRR. (B) The predictive results of RF. (C) The predictive results of LightGBM. (D) The predictive results of Adaboost. (E) The predictive results of GBDT.
Figure 7
Figure 7
The predictive accuracy of different methods during the independent test for litter weight (LW), total number of piglets born (TNB), and number of piglets born alive (NBA) with the best results in Rongchang pigs. (A) The predictive accuracy of LW with different methods. (B) The predictive accuracy of TNB with different methods. (C) The predictive accuracy of NBA with different methods.
Figure 8
Figure 8
The computational efficiency of different methods for litter weight (LW), total number of piglets born (TNB), and number of piglets born alive (NBA) with the best results in Rongchang pigs. (A) The computational efficiency of LW with different methods. (B) The computational efficiency of TNB with different methods. (C) The computational efficiency of NBA with different methods.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Xu T., Zheng X., Li B., Jin P., Qin Z., Wu H. A comprehensive review of computational prediction of genome-wide features. Brief. Bioinform. 2020;21:120–134. doi: 10.1093/bib/bby110. - DOI - PMC - PubMed
    1. Chafai N., Hayah I., Houaga I., Badaoui B. A review of machine learning models applied to genomic prediction in animal breeding. Front. Genet. 2023;14:1150596. doi: 10.3389/fgene.2023.1150596. - DOI - PMC - PubMed
    1. Jeon D., Kang Y., Lee S., Choi S., Sung Y., Lee T.H., Kim C. Digitalizing breeding in plants: A new trend of next-generation breeding based on genomic prediction. Front. Plant. Sci. 2023;14:1092584. doi: 10.3389/fpls.2023.1092584. - DOI - PMC - PubMed
    1. Danilevicz M.F., Gill M., Anderson R., Batley J., Bennamoun M., Bayer P.E., Edwards D. Plant Genotype to Phenotype Prediction Using Machine Learning. Front. Genet. 2022;13:822173. doi: 10.3389/fgene.2022.822173. - DOI - PMC - PubMed
    1. Nishio M., Arakawa A., Inoue K., Ichinoseki K., Kobayashi E., Okamura T., Fukuzawa Y., Ogawa S., Taniguchi M., Oe M., et al. Evaluating the performance of genomic prediction accounting for effects of single nucleotide polymorphism markers in reproductive traits of Japanese Black cattle. Anim. Sci. J. 2023;94:e13850. doi: 10.1111/asj.13850. - DOI - PubMed

LinkOut - more resources