Improving the accuracy of genomic prediction in dairy cattle using the biologically annotated neural networks framework.

IF 6.3 Q1 AGRICULTURE, DAIRY & ANIMAL SCIENCE Journal of Animal Science and Biotechnology Pub Date : 2024-07-01 DOI:10.1186/s40104-024-01044-1
Xue Wang, Shaolei Shi, Md Yousuf Ali Khan, Zhe Zhang, Yi Zhang
{"title":"Improving the accuracy of genomic prediction in dairy cattle using the biologically annotated neural networks framework.","authors":"Xue Wang, Shaolei Shi, Md Yousuf Ali Khan, Zhe Zhang, Yi Zhang","doi":"10.1186/s40104-024-01044-1","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Biologically annotated neural networks (BANNs) are feedforward Bayesian neural network models that utilize partially connected architectures based on SNP-set annotations. As an interpretable neural network, BANNs model SNP and SNP-set effects in their input and hidden layers, respectively. Furthermore, the weights and connections of the network are regarded as random variables with prior distributions reflecting the manifestation of genetic effects at various genomic scales. However, its application in genomic prediction has yet to be explored.</p><p><strong>Results: </strong>This study extended the BANNs framework to the area of genomic selection and explored the optimal SNP-set partitioning strategies by using dairy cattle datasets. The SNP-sets were partitioned based on two strategies-gene annotations and 100 kb windows, denoted as BANN_gene and BANN_100kb, respectively. The BANNs model was compared with GBLUP, random forest (RF), BayesB and BayesCπ through five replicates of five-fold cross-validation using genotypic and phenotypic data on milk production traits, type traits, and one health trait of 6,558, 6,210 and 5,962 Chinese Holsteins, respectively. Results showed that the BANNs framework achieves higher genomic prediction accuracy compared to GBLUP, RF and Bayesian methods. Specifically, the BANN_100kb demonstrated superior accuracy and the BANN_gene exhibited generally suboptimal accuracy compared to GBLUP, RF, BayesB and BayesCπ across all traits. The average accuracy improvements of BANN_100kb over GBLUP, RF, BayesB and BayesCπ were 4.86%, 3.95%, 3.84% and 1.92%, and the accuracy of BANN_gene was improved by 3.75%, 2.86%, 2.73% and 0.85% compared to GBLUP, RF, BayesB and BayesCπ, respectively across all seven traits. Meanwhile, both BANN_100kb and BANN_gene yielded lower overall mean square error values than GBLUP, RF and Bayesian methods.</p><p><strong>Conclusion: </strong>Our findings demonstrated that the BANNs framework performed better than traditional genomic prediction methods in our tested scenarios, and might serve as a promising alternative approach for genomic prediction in dairy cattle.</p>","PeriodicalId":64067,"journal":{"name":"Journal of Animal Science and Biotechnology","volume":null,"pages":null},"PeriodicalIF":6.3000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11215832/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Animal Science and Biotechnology","FirstCategoryId":"1089","ListUrlMain":"https://doi.org/10.1186/s40104-024-01044-1","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURE, DAIRY & ANIMAL SCIENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Biologically annotated neural networks (BANNs) are feedforward Bayesian neural network models that utilize partially connected architectures based on SNP-set annotations. As an interpretable neural network, BANNs model SNP and SNP-set effects in their input and hidden layers, respectively. Furthermore, the weights and connections of the network are regarded as random variables with prior distributions reflecting the manifestation of genetic effects at various genomic scales. However, its application in genomic prediction has yet to be explored.

Results: This study extended the BANNs framework to the area of genomic selection and explored the optimal SNP-set partitioning strategies by using dairy cattle datasets. The SNP-sets were partitioned based on two strategies-gene annotations and 100 kb windows, denoted as BANN_gene and BANN_100kb, respectively. The BANNs model was compared with GBLUP, random forest (RF), BayesB and BayesCπ through five replicates of five-fold cross-validation using genotypic and phenotypic data on milk production traits, type traits, and one health trait of 6,558, 6,210 and 5,962 Chinese Holsteins, respectively. Results showed that the BANNs framework achieves higher genomic prediction accuracy compared to GBLUP, RF and Bayesian methods. Specifically, the BANN_100kb demonstrated superior accuracy and the BANN_gene exhibited generally suboptimal accuracy compared to GBLUP, RF, BayesB and BayesCπ across all traits. The average accuracy improvements of BANN_100kb over GBLUP, RF, BayesB and BayesCπ were 4.86%, 3.95%, 3.84% and 1.92%, and the accuracy of BANN_gene was improved by 3.75%, 2.86%, 2.73% and 0.85% compared to GBLUP, RF, BayesB and BayesCπ, respectively across all seven traits. Meanwhile, both BANN_100kb and BANN_gene yielded lower overall mean square error values than GBLUP, RF and Bayesian methods.

Conclusion: Our findings demonstrated that the BANNs framework performed better than traditional genomic prediction methods in our tested scenarios, and might serve as a promising alternative approach for genomic prediction in dairy cattle.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用生物注释神经网络框架提高奶牛基因组预测的准确性。
背景:生物注释神经网络(BANNs)是一种前馈贝叶斯神经网络模型,它利用基于SNP集注释的部分连接架构。作为一种可解释的神经网络,BANNs 在其输入层和隐藏层分别模拟 SNP 和 SNP 集效应。此外,网络的权重和连接被视为随机变量,其先验分布反映了遗传效应在不同基因组尺度上的表现。然而,其在基因组预测中的应用还有待探索:本研究将 BANNs 框架扩展到基因组选择领域,并利用奶牛数据集探索最佳 SNP 集划分策略。SNP集的划分基于两种策略--基因注释和100 kb窗口,分别称为BANN_gene和BANN_100kb。利用 6558 头、6210 头和 5962 头中国荷斯坦牛的产奶性状、类型性状和一个健康性状的基因型和表型数据,通过五次重复的五倍交叉验证,将 BANNs 模型与 GBLUP、随机森林(RF)、BayesB 和 BayesCπ 进行了比较。结果表明,与 GBLUP、RF 和贝叶斯方法相比,BANNs 框架实现了更高的基因组预测精度。具体来说,在所有性状上,与 GBLUP、RF、BayesB 和 BayesCπ 相比,BANN_100kb 表现出更高的准确性,而 BANN_gene 一般表现出次优的准确性。与 GBLUP、RF、BayesB 和 BayesCπ 相比,BANN_100kb 在所有七个性状上的平均准确率分别提高了 4.86%、3.95%、3.84% 和 1.92%,BANN_gene 在所有七个性状上的准确率分别提高了 3.75%、2.86%、2.73% 和 0.85%。同时,与 GBLUP、RF 和贝叶斯方法相比,BANN_100kb 和 BANN_gene 的总体均方误差值更低:我们的研究结果表明,在我们测试的情况下,BANNs 框架比传统的基因组预测方法表现更好,可以作为奶牛基因组预测的一种有前途的替代方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
10.30
自引率
0.00%
发文量
822
期刊最新文献
Impact of probiotics-derived extracellular vesicles on livestock gut barrier function. Dietary supplementation with N-acetyl-L-cysteine ameliorates hyperactivated ERK signaling in the endometrium that is linked to poor pregnancy outcomes following ovarian stimulation in pigs. The assembly and activation of the PANoptosome promote porcine granulosa cell programmed cell death during follicular atresia. Natural plant polyphenols contribute to the ecological and healthy swine production. Embryotrophic effect of exogenous protein contained adipose-derived stem cell extracellular vesicles.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1