基于芯片数据的长白猪繁殖性状基因组选择研究

doi:10.11843/j.issn.0366-6964.2025.01.020

畜牧兽医学报 ›› 2025, Vol. 56 ›› Issue (1): 213-221.doi: 10.11843/j.issn.0366-6964.2025.01.020

基于芯片数据的长白猪繁殖性状基因组选择研究

阳文攀¹^,²(), 刘相杰¹^,², 罗冬香³, 陈梦会¹, 谢瑛¹, 方跃鑫¹, 林婷燕¹, 李爱民¹, 李文静¹, 邓政¹^,², 丁能水¹^,²^,⁴^,*()

1. 福建傲农生物科技集团股份有限公司农业农村部华南生猪育种重点实验室, 漳州 363000
2. 福建傲芯生物科技集团有限公司, 漳州 363000
3. 上高县现代农业技术服务中心, 宜春 336400
4. 江西农业大学猪遗传改良与养殖技术国家重点实验室, 南昌 330045

收稿日期:2024-05-31 出版日期:2025-01-23 发布日期:2025-01-18
通讯作者: 丁能水 E-mail:945226087@qq.com;13631698@qq.com
作者简介:阳文攀(1994-)，男，湖北孝感人，硕士，主要从事动物遗传育种与繁殖研究，E-mail：945226087@qq.com
基金资助:
福建省种业企业培优项目(2120814-农业生产发展支出)

Research on Genomic Selection of Reproductive Traits in Landrace Pigs Based on Chip Data

YANG Wenpan¹^,²(), LIU Xiangjie¹^,², LUO Dongxiang³, CHEN Menghui¹, XIE Ying¹, FANG Yuexin¹, LIN Tingyan¹, LI Aimin¹, LI Wenjing¹, DENG Zheng¹^,², DING Nengshui¹^,²^,⁴^,*()

1. Key Laboratory of Swine Breeding for the South China of Ministry of Agriculture and Rural Affairs, Aonong Group, Zhangzhou 363000, China
2. Fujian Aoxin Biotechnology Group Co., Ltd., Zhangzhou 363000, China
3. Shanggao County Modern Agricultural Technology Service Center, Yichun 336400, China
4. State Key Laboratory of Pig Genetic Improvement and Production Technology, Jiangxi Agricultural University, Nanchang 330045, China

Received:2024-05-31 Online:2025-01-23 Published:2025-01-18
Contact: DING Nengshui E-mail:945226087@qq.com;13631698@qq.com

摘要/Abstract

摘要：

旨在比较不同基因组预测模型预测准确性与运行效率，以探究支持向量机(SVM)回归与随机森林(RandomForest)回归在基因组预测中的应用价值与应用前景。本研究使用博瑞迪猪50K液相芯片，采用GBLUP、BayesB、BayesLASSO、SVM回归和RandomForest回归等基因组预测模型，对1 001头长白猪繁殖性状进行基因组预测评估。研究发现，在总产仔数、产活仔数、窝重等繁殖性状中，使用SVM回归径向基函数核的评估准确性均最高；产活仔数、窝重在参数C值为1时评估准确性达到最大值，总产仔数在参数C值为2时评估准确性达到最大值。在总产仔数、产活仔数、窝重等繁殖性状中，使用RandomForest回归评估ntree、mtry、nodesize等参数时发现，基因组预测准确性随着参数的变化展现一定的随机性。RandomForest回归模型在总产仔数、产活仔数、窝重中的评估准确性均最高，其次为SVM回归，GBLUP、BayesB、BayesLASSO等模型遗传评估准确性较差且保持一致。交叉验证相关性显示，不同模型遗传评估结果存在较强的相关性，为0.806~0.995。SVM回归与RandomForest回归等非参数机器学习模型在猪繁殖性状基因组选择中具有一定的优势，但运行时间在一定程度上限制了这些算法的使用。随着算法的研究优化，SVM回归与RandomForest回归等非参数机器学习模型将具有良好的应用前景。

关键词: 长白猪, 繁殖性状, 基因芯片, 基因组选择, 机器学习

Abstract:

The study aimed to compare the prediction accuracy and computational efficiency of different genomic prediction models, explore the application value and prospects of support vector machine (SVM) regression and RandomForest regression in genomic prediction. In this study, the 50K liquid chip was used to predict the reproductive traits of 1 001 Landrace pigs by GBLUP, BayesB, BayesLASSO, support vector machine regression and RandomForest regression. It was found that support vector machine regression radial basis function kernel had the highest predictive accuracy of reproductive traits such as total litter size, live litter size and litter weight. The predictive accuracy of live litter size and litter weight reached the maximum value when the parameter C value was 1, and the predictive accuracy of total litter size reached the maximum value when the parameter C value was 2. When using RandomForest regression to evaluate parameters such as ntree, mtry and nodesize in reproductive traits such as total litter size, number of live litter and litter weight, it was found that the predictive accuracy showed a certain randomness with the change of parameters. The RandomForest regression model showed the highest accuracy in total litter size, live litter size and litter weight, followed by support vector machine regression. The predictive accuracy of GBLUP, BayesB, BayesLasso models was poor and consistent. In the correlation of cross-validation of different models, it can also be found that there is a strong correlation between the results of different models ranging from 0.806 to 0.995. Non-parametric machine learning models such as support vector machine regression and RandomForest regression have certain advantages in pig reproductive trait genome selection, but the running time limits the use of this machine learning algorithm to some extent. With the optimization of the algorithm, non-parametric machine learning models such as support vector machine regression and RandomForest regression will have a good application prospect.

Key words: Landrace pig, reproductive traits, gene chip, genomic selection, machine learning

中图分类号:

S828.3

阳文攀, 刘相杰, 罗冬香, 陈梦会, 谢瑛, 方跃鑫, 林婷燕, 李爱民, 李文静, 邓政, 丁能水. 基于芯片数据的长白猪繁殖性状基因组选择研究[J]. 畜牧兽医学报, 2025, 56(1): 213-221.

YANG Wenpan, LIU Xiangjie, LUO Dongxiang, CHEN Menghui, XIE Ying, FANG Yuexin, LIN Tingyan, LI Aimin, LI Wenjing, DENG Zheng, DING Nengshui. Research on Genomic Selection of Reproductive Traits in Landrace Pigs Based on Chip Data[J]. Acta Veterinaria et Zootechnica Sinica, 2025, 56(1): 213-221.

图/表 5

表 1

图 1

图 2

图 3

图 4

参考文献 40

1	PILESM,BERGSMAR,GIANOLAD,et al.Feature selection stability and accuracy of prediction models for genomic prediction of residual feed intake in pigs using machine learning[J].Front Genet,2021,12,611506. doi: 10.3389/fgene.2021.611506
2	MUÑOZM,BOZZIR,GARCÍA-CASCOJ,et al.Genomic diversity, linkage disequilibrium and selection signatures in European local pig breeds assessed with a high density SNP chip[J].Sci Rep,2019,9(1):13546. doi: 10.1038/s41598-019-49830-6
3	WELLMANNR,PREUSSS,THOLENE,et al.Genomic selection using low density marker panels with application to a sire line in pigs[J].Genet Sel Evol,2013,45(1):28. doi: 10.1186/1297-9686-45-28
4	MEUWISSENT H,HAYESB J,GODDARDM E.Prediction of total genetic value using genome-wide dense marker maps[J].Genetics,2001,157(4):1819-1829. doi: 10.1093/genetics/157.4.1819
5	VANRADENP M.Efficient methods to compute genomic predictions[J].J Dairy Sci,2008,91(11):4414-4423. doi: 10.3168/jds.2007-0980
6	LEGARRAA,AGUILARI,MISZTALI.A relationship matrix including full pedigree and genomic information[J].J Dairy Sci,2009,92(9):4656-4663. doi: 10.3168/jds.2009-2061
7	MONTESINOS-LÓPEZO A,MONTESINOS-LÓPEZA,PÉREZ-RODRÍGUEZP,et al.A review of deep learning applications for genomic selection[J].BMC Genomics,2021,22(1):19. doi: 10.1186/s12864-020-07319-x
8	WANGZ Z,MAH R,LIH W,et al.Multi-trait genomic predictions using GBLUP and Bayesian mixture prior model in beef cattle[J].Anim Res One Health,2023,1(1):17-29. doi: 10.1002/aro2.13
9	VARONAL,LEGARRAA,TOROM A,et al.Non-additive effects in genomic selection[J].Front Genet,2018,9,78. doi: 10.3389/fgene.2018.00078
10	GIANOLAD,OKUTH,WEIGELK A,et al.Predicting complex quantitative traits with Bayesian neural networks: a case study with Jersey cows and wheat[J].BMC Genet,2011,12(1):87. doi: 10.1186/1471-2156-12-87
11	YINL L,ZHANGH H,ZHOUX,et al.KAML: improving genomic prediction accuracy of complex traits using machine learning determined parameters[J].Genome Biol,2020,21(1):146. doi: 10.1186/s13059-020-02052-w
12	WANGX,SHIS L,WANGG J,et al.Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs[J].J Anim Sci Biotechnol,2022,13(1):60. doi: 10.1186/s40104-022-00708-0
13	ABDOLLAHI-ARPANAHIR,GIANOLAD,PEÑAGARICANOF.Deep learning versus parametric and ensemble methods for genomic prediction of complex phenotypes[J].Genet Sel Evol,2020,52(1):12. doi: 10.1186/s12711-020-00531-z
14	SANDHUK S,AOUNM,MORRISC F,et al.Genomic selection for end-use quality and processing traits in soft white winter wheat breeding program with machine and deep learning models[J].Biology (Basel),2021,10(7):689.
15	GONZÁLEZ-RECIOO,ROSAG J M,GIANOLAD.Machine learning methods and predictive ability metrics for genome-wide prediction of complex traits[J].Livest Sci,2014,166,217-231. doi: 10.1016/j.livsci.2014.05.036
16	KASNAVIS A,AMINAFSHARM,SHARIATIM M,et al.The effect of kernel selection on genome wide prediction of discrete traits by Support Vector Machine[J].Gene Rep,2018,11,279-282. doi: 10.1016/j.genrep.2018.04.006
17	GHAFOURI-KESBIF,RAHIMI-MIANJIG,HONARVARM,et al.Predictive ability of Random Forests, Boosting, Support Vector Machines and Genomic Best Linear Unbiased Prediction in different scenarios of genomic evaluation[J].Anim Prod Sci,2016,57(2):229-236.
18	SCHÖLKOPFB,SMOLAA J,WILLIAMSONR C,et al.New support vector algorithms[J].Neural Comput,2000,12(5):1207-1245. doi: 10.1162/089976600300015565
19	NOBLEW S.What is a support vector machine?[J].Nat Biotechnol,2006,24(12):1565-1567. doi: 10.1038/nbt1206-1565
20	GIANOLAD,WEIGELK A,KRÄMERN,et al.Enhancing genome-enabled prediction by bagging genomic BLUP[J].PLoS One,2014,9(4):e91693. doi: 10.1371/journal.pone.0091693
21	WALTERSR,LAURINC,LUBKEG H.An integrated approach to reduce the impact of minor allele frequency and linkage disequilibrium on variable importance measures for genome-wide data[J].Bioinformatics,2012,28(20):2615-2623. doi: 10.1093/bioinformatics/bts483
22	BROWNINGB L,ZHOUY,BROWNINGS R.A one-penny imputed genome from next-generation reference panels[J].Am J Hum Genet,2018,103(3):338-348. doi: 10.1016/j.ajhg.2018.07.015
23	ZHENGX W,LEVINED,SHENJ,et al.A high-performance computing toolset for relatedness and principal component analysis of SNP data[J].Bioinformatics,2012,28(24):3326-3328. doi: 10.1093/bioinformatics/bts606
24	PARKT,CASELLAG.The Bayesian lasso[J].J Am Stat Assoc,2008,103(482):681-686. doi: 10.1198/016214508000000337
25	PÉREZP,DE LOS CAMPOSG.Genome-wide regression and prediction with the BGLR statistical package[J].Genetics,2014,198(2):483-495. doi: 10.1534/genetics.114.164442
26	XIANGT,LIT,LIJ L,et al.Using machine learning to realize genetic site screening and genomic prediction of productive traits in pigs[J].FASEB J,2023,37(6):e22961. doi: 10.1096/fj.202300245R
27	BARRETOC A V,DAS GRAÇAS DIASK O,DE SOUSAI C,et al.Genomic prediction in multi-environment trials in maize using statistical and machine learning methods[J].Sci Rep,2024,14(1):1062. doi: 10.1038/s41598-024-51792-3
28	ZHANGZ,ZHANGH,PANR Y,et al.Genetic parameters and trends for production and reproduction traits of a Landrace herd in China[J].J Integr Agric,2016,15(5):1069-1075. doi: 10.1016/S2095-3119(15)61105-4
29	ZHANGS Y,ZHANGJ X,OLASEGEB S,et al.Estimation of genetic parameters for reproductive traits in connectedness groups of Duroc, Landrace and Yorkshire pigs in China[J].J Anim Breed Genet,2020,137(2):211-222. doi: 10.1111/jbg.12431
30	ZHAOW,LAIX S,LIUD Y,et al.Applications of support vector machine in genomic prediction in pig and maize populations[J].Front Genet,2020,11,598318. doi: 10.3389/fgene.2020.598318
31	KASNAVIS A,AFSHARM A,SHARIATIM M,et al.Performance evaluation of support vector machine (SVM)-based predictors in genomic selection[J].Indian J Anim Sci,2017,87(10):1226-1231.
32	CHERKASSKYV,MAY Q.Practical selection of SVM parameters and noise estimation for SVM regression[J].Neural Netw,2004,17(1):113-126. doi: 10.1016/S0893-6080(03)00169-2
33	ALVESA A C,ESPIGOLANR,BRESOLINT,et al.Genome-enabled prediction of reproductive traits in Nellore cattle using parametric models and machine learning methods[J].Anim Genet,2021,52(1):32-46. doi: 10.1111/age.13021
34	MANCINE,MOTAL F M,TULIOZIB,et al.Improvement of genomic predictions in small breeds by construction of genomic relationship matrix through variable selection[J].Front Genet,2022,13,814264. doi: 10.3389/fgene.2022.814264
35	SARKARR K,RAOA R,MEHERP K,et al.Evaluation of random forest regression for prediction of breeding value from genomewide SNPs[J].J Genet,2015,94(2):187-192. doi: 10.1007/s12041-015-0501-5
36	BANERJEER,MARATHIB,SINGHM.Efficient genomic selection using ensemble learning and ensemble feature reduction[J].J Crop Sci Biotechnol,2020,23(4):311-323. doi: 10.1007/s12892-020-00039-4
37	LIANGM,MIAOJ,WANGX Q,et al.Application of ensemble learning to genomic selection in Chinese simmental beef cattle[J].J Anim Breed Genet,2021,138(3):291-299. doi: 10.1111/jbg.12514
38	MERRICKL F,CARTERA H.Comparison of genomic selection models for exploring predictive ability of complex traits in breeding programs[J].Plant Genome,2021,14(3):e20158. doi: 10.1002/tpg2.20158
39	WANGJ B,ZONGW C,SHIL Y,et al.Using mixed kernel support vector machine to improve the predictive accuracy of genome selection[J].J Integr Agric,2024, doi: 10.1016/j.jia.2024.03.083
40	HEINRICHF,LANGET M,KIRCHERM,et al.Exploring the potential of incremental feature selection to improve genomic prediction accuracy[J].Genet Sel Evol,2023,55(1):78. doi: 10.1186/s12711-023-00853-8

性状 Trait	加性方差 σ_a²	永久环境效应方差 σ_ep²	残差效应方差 σ_e²	遗传力 h²	重复力 R_ep²
总产仔数TNB	1.181±0.231	0.791±0.189	9.568±0.203	0.102±0.019	0.171±0.015
产活仔数NBA	0.948±0.200	0.615±0.174	9.777±0.207	0.084±0.017	0.138±0.015
窝重LWT	1.633±0.390	1.765±0.369	19.751±0.419	0.071±0.016	0.147±0.014

[1]	贾宏霞, 刘在霞, 周乐, 鲍艳春, 霍晨曦, 左鹏鹏, 谷明娟, 娜日苏, 张文广. 基因组选择在肉牛中的研究进展[J]. 畜牧兽医学报, 2024, 55(9): 3757-3768.
[2]	师睿, 李珊珊, 张海亮, 路海博, 闫青霞, 张毅, 陈绍祜, 王雅春. 中国荷斯坦牛繁殖性状的基因型与环境互作[J]. 畜牧兽医学报, 2024, 55(9): 3968-3977.
[3]	王进部, 李佳, 任德明, 王立贤, 王立刚. 机器学习在畜禽基因组选择中的应用进展[J]. 畜牧兽医学报, 2024, 55(7): 2775-2785.
[4]	郭子骄, 郑伟杰, 孙伟, 吴宝江, 包向男, 张琪, 贺巾锋, 包斯琴, 赵高平, 王子馨, 韩博, 李喜和, 孙东晓. 荷斯坦奶牛胚胎基因组遗传评估研究[J]. 畜牧兽医学报, 2024, 55(7): 2940-2950.
[5]	李竟, 张元旭, 王泽昭, 陈燕, 徐凌洋, 张路培, 高雪, 高会江, 李俊雅, 朱波, 郭鹏. 机器学习全基因组选择研究进展[J]. 畜牧兽医学报, 2024, 55(6): 2281-2292.
[6]	吴华煊, 杜志强. 基因型特征提取方法影响基因组选择预测准确性的研究[J]. 畜牧兽医学报, 2024, 55(6): 2431-2440.
[7]	张元旭, 李竟, 王泽昭, 陈燕, 徐凌洋, 张路培, 高雪, 高会江, 李俊雅, 朱波, 郭鹏. 动物遗传评估软件研究进展[J]. 畜牧兽医学报, 2024, 55(5): 1827-1841.
[8]	康佳威, 黄宣凯, 王志鹏, 张爱珍, 孟芳荣, 盖鹏, 包军付, 孙可心, 宋少康, 孙攀, 陈一川, 张蕾, 高圣玥, 常铭航. 大白猪生长、繁殖和体尺性状遗传参数估计[J]. 畜牧兽医学报, 2024, 55(5): 1936-1944.
[9]	钟欣, 张晖, 张充, 刘小红. 母猪繁殖力基因遗传育种研究进展[J]. 畜牧兽医学报, 2024, 55(2): 438-450.
[10]	祁军英, 裴全帮, 张文魁, 徐腾, 左明星, 韩步鹰, 李雪, 刘德会, 王松, 周佰成, 赵凯, 田得红. 全基因组选择信号鉴定高原型藏羊毛用性状候选基因及关联分析[J]. 畜牧兽医学报, 2024, 55(12): 5511-5526.
[11]	杨桐桐, 张海亮, 王澳, 常瑶, 李珊珊, 郭佳和, 张俊星, 黄越川, 韩丽云, 王瑜, 王雅春. 荷斯坦牛产后首次发情表现性状遗传参数估计[J]. 畜牧兽医学报, 2024, 55(11): 5050-5058.
[12]	吴俊锋, 闫奕源, 杨宁, 孙从佼, 李光奇, 王彬, 吴桂琴, 连玲. 蛋鸡SNP芯片10K到50K基因型填充的准确性研究[J]. 畜牧兽医学报, 2024, 55(10): 4325-4333.
[13]	严晓春, 习海娇, 李金泉, 王志英, 苏蕊. 内蒙古绒山羊绒毛性状基因组育种值估计准确性研究[J]. 畜牧兽医学报, 2024, 55(1): 120-128.
[14]	褚楚, 张静静, 丁磊, 樊懿楷, 包向男, 向世馨, 刘锐, 罗雪路, 任小丽, 李春芳, 刘文举, 王亮, 刘莉, 李永青, 江汉, 李委奇, 孙伟, 李喜和, 温万, 周佳敏, 张淑君. 基于中红外光谱的牛奶中三种氨基酸含量预测模型的建立及应用[J]. 畜牧兽医学报, 2023, 54(8): 3299-3312.
[15]	王万年, 陈思佳, 郜金荣, 温中豪, 袁梦娇, 张洪志, 庞志旭, 乔利英, 刘文忠. 基于多层感知机的绵羊限性性状基因组选择模拟研究[J]. 畜牧兽医学报, 2023, 54(7): 2824-2835.

基于芯片数据的长白猪繁殖性状基因组选择研究

Research on Genomic Selection of Reproductive Traits in Landrace Pigs Based on Chip Data

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 40

相关文章 15

编辑推荐

Metrics

本文评价