机器学习及其在动物遗传育种中的应用研究进展

doi:10.16431/j.cnki.1671-7236.2024.12.022

摘要/Abstract

摘要： 随着智慧畜牧研究的深入和高通量组学平台的发展，动物育种逐渐进入大数据时代的“育种3.0”，而机器学习是大数据研究不可或缺的有效手段。机器学习亦称计算机自动获取知识，是一门多领域交叉学科，涉及概率论、统计学等多门学科，作为人工智能和数据挖掘中的热门算法之一，具有学习能力强、准确率高和泛化能力强等优势，已经成为生物信息分析领域处理大型数据和进行预测的重要工具。目前广泛用于基因组、转录组、蛋白组、代谢组等多组学数据的整合与分析，尤其在家畜基因组估计育种值(genomic estimated breeding value,GEBV)的计算、基因型数据的填充和蛋白质结构及功能的预测等方面取得重要突破。作者介绍了几种常见的机器学习算法的概念和原理,对机器学习算法在重要家畜(猪、牛、羊)遗传育种方面取得的重要研究成果进行综述,进一步讨论了各种机器学习算法的优缺点、以及应用在动物遗传育种中存在的一些问题。最后,对机器学习的未来发展进行了归纳及展望,旨在提高预测准确性及效率，加快种群遗传进展，快速实现精准育种。

关键词: 机器学习; 大数据; 动物遗传育种; 遗传改良

Abstract: With the progress of research on intelligent animal husbandry and the development of high-throughput omics platforms,animal genetic breeding has been gradually entered the “Breeding 3.0” in the era of big data.Machine learning is an indispensable and effective means of big data research.Machine learning,the automatic acquisition of knowledge by computers,is a multidisciplinary cross-discipline,involving many disciplines such as probability theory and statistics.As one of the popular algorithms in artificial intelligence and data mining,it has many advantages such as high learning rate,good generalization ability and high accuracy.It has been an important tool in the field of bioinformatics analysis for processing big data and making predictions.Nowadays,machine learning is widely used for the integration and analysis of genomic,transcriptomic,proteomic,metabolomic and other multi-omics data,especially in the computing of genomic estimated breeding value (GEBV),genotype imputation,the prediction of protein structure and function of livestock,and other outstanding achievements.Firstly,the author introduced the concepts and principles of several common machine learning algorithms.Besides,the outstanding research results achieved by machine learning algorithms in genetic breeding of important livestock (pigs,cattle,sheep,and goats) were reviewed and further discussed the advantages and disadvantages of certain machine learning algorithms as well as some of the problems in animal genetic breeding.Finally,the future development of machine learning was summarized and prospected,aiming to improve the accuracy and efficiency of estimation,accelerate the genetic progress of populations,and rapidly implement precision breeding.

Key words: machine learning; big data; animal genetics and breeding; genetic improvement

中图分类号:

S813.3

周铂涵, 梅步俊, 吕琦, 王志英, 苏蕊. 机器学习及其在动物遗传育种中的应用研究进展[J]. 中国畜牧兽医, 2024, 51(12): 5348-5358.

ZHOU Bohan, MEI Bujun, LYU Qi, WANG Zhiying, SU Rui. Research Progress of Machine Learning and Its Application in Animal Genetics and Breeding[J]. China Animal Husbandry and Veterinary Medicine, 2024, 51(12): 5348-5358.

参考文献

[1] BAŞTANLAR Y, OZUYSAL M.Introduction to machine learning[J]. Methods in Molecular Biology, 2014, 1107(1):105-128.
[2] NAYERI S, SARGOLZAEI M, TULPAN D.A review of traditional and machine learning methods applied to animal breeding[J].Animal Health Research Reviews, 2019, 20(1):31-46.
[3] REEL P S, REEL S, PEARSON E, et al.Using machine learning approaches for multi-omics data analysis:A review[J].BiotechnologyAdvance, 2021, 25(3):49-56.
[4] GONZÁLEZ-CAMACHO J M, ORNELLA L, PÉREZ-RODRÍGUEZ P, et al.Applications of machine learning methods to genomic selection in breeding wheat for rust resistance[J].Plant Genome, 2018, 11(2):61-69.
[5] POIRION O B, JING Z, CHAUDHARY K, et al.DeepProg:An ensemble of deep-learning and machine-learning models for prognosis prediction using multi-omics data[J].Genome Medicine, 2021, 13(1):112-118.
[6] CHEN C, POWELL O, DINGLASAN E, et al.Genomic prediction with machine learning in sugarcane, a complex highly polyploid clonally propagated crop with substantial non-additive variation for key traits[J].Plant Genome, 2023, 16(4):120-131.
[7] CORTES C, VAPNIK V.Support-vector networks[J].Machine Learning, 1995, 20(3):273-297.
[8] ALEX J, SCHÖLKOPF B.A tutorial on support vector regression[J].Statistics and Computing, 2004, 14(6):199-222.
[9] HUANG Y.Improved SVM-based soil-moisture-content prediction model for tea plantation[J].Plants (Basel), 2023, 12(12):23-32.
[10] LONG N, GIANOLA D, ROSA G J, et al.Application of support vector regression to genome-assisted prediction of quantitative traits[J].Theoretical and Applied Genetics, 2011, 123(7):1065-1074.
[11] ANDREAS C, XIANG D, ZHOU D X.Total stability of kernel methods[J].Neurocomputing, 2018, 289(3):101-118.
[12] GAUTAM B, KOUSHIK G, ANANDA S, et al.An affinity-based new local distance function and similarity measure for KNN algorithm[J].Pattern Recognition Letters, 2012, 33(3):356-363.
[13] LIANG M, AN B, LI K, et al.Improving genomic prediction with machine learning incorporating TPE for hyperparameters optimization[J].Biology, 2022, 11(11):1647-1667.
[14] BREIMAN L.Random forests[J].Machine Learning, 2001, 45(1):25-32.
[15] 吕红燕, 冯倩.随机森林算法研究综述[J].河北省科学院学报, 2019, 36(3):37-41.LYU H Y, FENG Q.A review of random forests algorithm[J].Journal of the Hebei Academy of Sciences, 2019, 36(3):37-41.
[16] GHOSH D, CABRERA J.Enriched random forest for high dimensional genomic data[J]. Institute of Electrical and Electronics Engineers, 2021, 19(5):2817-2828.
[17] WANG K, YANG B, LI Q, et al.Systematic evaluation of genomic prediction algorithms for genomic prediction and breeding of aquatic animals[J].Genes (Basel), 2022, 13(12):2247-2256.
[18] XIANG T, LI T, LI J, et al.Using machine learning to realize genetic site screening and genomic prediction of productive traits in pigs[J].FASEB Journal, 2023, 37(6):229-236.
[19] DASARATHY B V, SHEELA B V.A composite classifier system design:Concepts and methodology[J].Proceedings of the Institute of Electrical and Electronics Engineers, 1979, 67(5):708-713.
[20] BREIMAN L.Bagging predictors[J].Machine Learning, 1996, 24(3):123-140.
[21] SCHAPIRE R E.The boosting approach to machine learning：An overview[J].Springer New York, 2002, 171(3):149-171.
[22] SIGLETOS G, PALIOURAS G, SPYROPULOS C D, et al.Combining information extraction systems using voting and stacked generalization[J].Journal of Machine Learning Research, 2005, 6(3):1751-1782.
[23] LI W, YIN Y, QUAN X, et al.Gene expression value prediction based on XGBoost algorithm[J].Frontiers Genetics, 2019, 12(10):1065-1077.
[24] AHSAN F, YAN Z, PRECUP D, et al.PhyloPGM:Boosting regulatory function prediction accuracy using evolutionary information[J].Bioinformatics, 2022, 38(1):1299-1306.
[25] MOTA L F M, GIANNUZZI D, BISUTTI V, et al.Real-time milk analysis integrated with stacking ensemble learning as a tool for the daily prediction of cheese-making traits in Holstein cattle[J].Journal Dairy Science, 2022, 105(5):4237-4255.
[26] ABDOLLAHI-ARPANAHI R, GIANOLA D, PEÑAGARICANO F.Deep learning versus parametric and ensemble methods for genomic prediction of complex phenotypes[J].Genetics Selection Evolution, 2020, 52(1):12-24.
[27] SHI Y, MA L, CHEN X, et al.Prediction model of obstructive sleep apnea-related hypertension:Machine learning-based development and interpretation study[J].Frontiers in Cardiovascular Medicine, 2022, 12(9):1042-1062.
[28] FREUND Y, SCHAPIRE R E.Experiments with a new boosting algorithm[J].International Conference on Machine Learning, 1996, 12(5):148-156.
[29] SHRESTHA D L, SOLOMATINE D P.Experiments with AdaBoost.RT, an improved boosting scheme for regression[J]. Neural Computation, 2006, 18(7):1678-1710.
[30] WANG J, XUE W, SHI X, et al.Adaboost-based machine learning improved the modeling robust and estimation accuracy of pear leaf nitrogen concentration by in-Field VIS-NIR spectroscopy[J].Sensors (Basel), 2021, 21(18):60-72.
[31] MCCULLOCH W S, PITTS W.A logical calculus of the ideas immanent in nervous activity[J]. Bulletin of Mathematical Biophysics, 1943, 5(4):115-133.
[32] ZAREBIDAKI M, ALLAHYARI E, ZEINALI T, et al.Occurrence and risk factors of brucellosis among domestic animals:An artificial neural network approach[J].Tropical Animal Health and Production, 2022, 14(1):54-62.
[33] XU L, GUO Z, LIU X.Prediction of essential genes in prokaryote based on artificial neural network[J].Genes and Genomics, 2020, 42(1):97-106.
[34] BONICELLI L, TRACHTMAN A R, ROSAMILIA A, et al.Training convolutional neural networks to score pneumonia in slaughtered pigs[J].Animals (Basel), 2021, 11(5):78-90.
[35] WANG L, HU Q, WANG L, et al.Predicting the growth performance of growing-finishing pigs based on net energy and digestible lysine intake using multiple regression and artificial neural networks models[J].Journal Animal Science and Biotechnology, 2022, 13(1):57-63.
[36] 李娅兰, 吴珍芳, 蔡更元.母猪繁殖力性状的特点及选择方法[J].华南农业大学学报, 2019, 40(1):132-138.LI Y L, WU Z F, CAI G Y.The characteristics and selection methods of reproductive traits of sow[J].Journal of South China Agricultural University, 2019, 40(1):132-138.(in Chinese)
[37] WANG X, SHI S, WANG G, et al.Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs[J]. Journal of Animal Science and Biotechnology, 2022, 13(1):60-72.
[38] 李信颉, 王海燕, 蒋贝加，等.基于机器学习方法预测母猪产仔数性状[J].华中农业大学学报, 2020, 39(4):63-68.LI X J, WANG H Y, JIANG B J, et al.Prediction of sow litter size trait based on machine learning approaches[J].Journal of Huazhong Agricultural University, 2020, 39(4):63-68.(in Chinese)
[39] ZHOU X, GUAN R, CAI H, et al.Machine learning based personalized promotion strategy of piglets weaned per sow per year in large-scale pig farms[J].Porcine Health Management, 2022, 8(1):37-48.
[40] LIU H, XING K, JIANG Y, et al.Using machine learning to identify biomarkers affecting fat deposition in pigs by integrating multisource transcriptome information[J].Journal of Agricultural and Food Chemistry, 2022, 70(33):10359-10370.
[41] BAKOEV S, TRASPOV A, GETMANTSEVA L, et al.Detection of genomic regions associated malformations in newborn piglets:A machine-learning approach[J]. PeerJ, 2021, 9(3):98-115.
[42] TUSELL L, BERGSMA R, GILBERT H, et al.Machine learning prediction of crossbred pig feed efficiency and growth rate from single nucleotide polymorphisms[J].Frontiers in Genetics, 2020, 11(5):67-78.
[43] XU W, VAN KNEGSEL A T M, VERVOORT J J M, et al.Prediction of metabolic status of dairy cows in early lactation with on-farm cow data and machine learning algorithms[J].Journal of Dairy Science, 2019, 102(11):10186-10201.
[44] LIANG M, MIAO J, WANG X, et al.Application of ensemble learning to genomic selection in Chinese Simmental beef cattle[J]. Journal of Animal Breeding and Genetics, 2021, 138(3):291-299.
[45] ALVES A A C, ESPIGOLAN R, BRESOLIN T, et al.Genome-enabled prediction of reproductive traits in Nellore cattle using parametric models and machine learning methods[J].Animal Genetics, 2021, 52(1):32-46.
[46] LIANG M, CHANG T, AN B, et al.A stacking ensemble learning framework for genomic prediction[J].Frontiers in Genetics, 2021, 4(1):45-54.
[47] AN B, LIANG M, CHANG T, et al.KCRR:A nonlinear machine learning with a modified genomic similarity matrix improved the genomic prediction efficiency[J].Briefings in Bioinformatics, 2021, 22(6):132-143.
[48] MOTA L F M, PEGOLO S, BABA T, et al.Evaluating the performance of machine learning methods and variable selection methods for predicting difficult-to-measure traits in Holstein dairy cattle using milk infrared spectral data[J].Journal of Dairy Science, 2021, 104(7):8107-8121.
[49] ALONSO J, VILLA A, BAHAMONDE A.Improved estimation of bovine weight trajectories using support vector machine classification[J].Computers and Electronics in Agriculture, 2015, 110(6):36-41.
[50] HUMA Z I, QBAL F.Predicting the body weight of Balochi sheep using a machine learning approach[J].Turkish Journal of Veterinary and Animal Sciences, 2019, 43(4):500-506.
[51] TIRINK C, PIWCZY AN＇G SKI D, KOLENDA M, et al.Estimation of body weight based on biometric measurements by using random forest regression, support vector regression and CART algorithms[J]. Animals, 2023, 13(5):798-809.
[52] ALI M, EYDURAN E, TARIQ M, et al.Comparison of artificial neural network and decision tree algorithms used for predicting live weight at post weaning period from some biometrical characteristics in Harnai sheep[J]. Pakistan Journal of Zoology, 2015, 47(5):1579-1585.
[53] COŞKUN G, ŞAHIN Ö, AYTEKIN I.Final fattening live weight prediction in Anatolian Merinos lambs from some body characteristics at the initial of fattening by using some data mining algorithms[J].Black Sea Journal of Agriculture, 2022, 22(6):115-123.
[54] IQBAL F, WAHEED A, FARAZ A.Comparing the predictive ability of machine learning methods in predicting the live body weight of Beetal goats of Pakistan[J]. Pakistan Journal of Zoology, 2022, 54(1):231-238.
[55] HAMADANI A, GANAI N A, MUDASIR S, et al.Comparison of artificial intelligence algorithms and their ranking for the prediction of genetic merit in sheep[J].Scientific Reports, 2022, 12(1):187-196.
[56] SALEH S, KHAMA K, LEWIS K.Prediction of sheep carcass traits from early-life records using machine learning[J].Computers and Electronics in Agriculture, 2019, 156(5):159-177.
[57] SHAHINFAR S, KAHN L.Machine learning approaches for early prediction of adult wool growth and quality in Australian Merino sheep[J].Computers and Electronics in Agriculture, 2018, 148(2):72-81.
[58] LIU Y, MUNTEANU C R, YAN Q, et al.Machine learning classification models for fetal skeletal development performance prediction using maternal bone metabolic proteins in goats[J].PeerJ, 2019, 7(8):40-49.
[59] MVLLER A C, GUIDO S.Introduction to Machine Learning with Python:A Guide for Data Scientists[M].California:O’Reilly Media, 2017.
[60] MONTESINOS-LÓPEZ O A, GONZALEZ H N, MONTESINOS-LÓPEZ A, et al.Comparing gradient boosting machine and Bayesian threshold BLUP for genome-based prediction of categorical traits in wheat breeding[J]. Plant Genome, 2022，15(3):202-214.
[61] ZHANG H, YIN L, WANG M, et al.Factors affecting the accuracy of genomic selection for agricultural economic traits in maize, cattle, and pig populations[J].Frontiers in Genetics, 2019, 14(10):189-201.
[62] SUL J H, MARTIN L S, ESKIN E.Population structure in genetic studies:Confounding factors and mixed models[J].PLoS Genetics, 2018, 14(12):e1007309.
[63] NADERI S, YIN T, KÖNIG S.Random forest estimation of genomic breeding values for disease susceptibility over different disease incidences and genomic architectures in simulated cow calibration groups[J].Journal of Dairy Science, 2016, 99(9):7261-7273.
[64] WHALEN S, POLLARD K S.Reply to 'Inflated performance measures in enhancer-promoter interaction-prediction methods’[J].Nature Genetics.2019, 51(8):1198-1200.
[65] EID F E, ELMARAKEBY H A, CHAN Y A, et al.Systematic auditing is essential to debiasing machine learning in biology[J].Communications Biology, 2021, 4(1):183-196.
[66] FRANZINI S, DI STEFANO M, MICHELETTI C.EssHi-C:Essential component analysis of Hi-C matrices[J].Bioinformatics, 2021, 37(15):2088-2094.
[67] DINCER A B, JANIZEK J D, LEE S I.Adversarial deconfounding autoencoder for learning robust gene expression embeddings[J]. Bioinformatics, 2020, 36(2):573-582.
[68] HOWARD R, CARRIQUIRY A L, BEAVIS W D.Parametric and nonparametric statistical methods for genomic selection of traits with additive and epistatic genetic architectures[J].G3(Bethesda), 2014, 4(6):1027-1046.
[69] AGUILAR I, MISZTAL I, JOHNSON D L, et al.Hot topic:A unified approach to utilize phenotypic, full pedigree, and genomic information for genetic evaluation of Holstein final score[J].Journal of Dairy Science, 2010, 93(3):743-752.
[70] 梁忙.基于机器学习算法的全基因组选择研究[D].北京：中国农业科学院, 2021.LIANG M.The algorithm research for genomic selection study based on machine learning[D].Beijing:Chinese Academy of Agricultural Sciences, 2021.(in Chinese)
[71] AZODI C B, BOLGER E, MCCARREN A, et al.Benchmarking parametric and machine learning models for genomic prediction of complex traits[J].G3(Bethesda), 2019, 9(11):3691-3702.
[72] MONTESINOS-LÓPEZ O A, MONTESINOS-LÓPEZ A, PÉREZ-RODRÍGUEZ P, et al.A review of deep learning applications for genomic selection[J]. BMC Genomics, 2021, 22(1):19-31.
[73] GONZÁLEZ-RECIO O, GUILHERME J M R, DANIEL G.Machine learning methods and predictive ability metrics for genome-wide prediction of complex traits[J].Livestock Science, 2014, 166(5):217-231.
[74] LUBKE G, LAURIN C, WALTERS R, et al.Gradient boosting as a SNP filter:An evaluation using simulated and hair morphology data[J].Journal of Data Mining in Genomics and Proteomics, 2013, 20(4):115-120.
[75] GRINBERG N F, ORHOBOR O I, KING R D.An evaluation of machine-learning for predicting phenotype:Studies in yeast, rice, and wheat[J]. Marching Learning, 2020, 109(2):251-277.
[76] GONZALEZ-RECIO O, COFFEY M P, PRYCE J E.On the value of the phenotypes in the genomic era[J].Journal of Dairy Science, 2014, 12(10):7905-7915.
[77] YOOSEFZADEH N M, ESKANDARI M, TORABI S, et al.Machine-learning-based genome-wide association studies for uncovering QTL underlying soybean yield and its components[J].International Journal of Molecular Sciences, 2022, 23(10):55-67.
[78] SHI Q, CHEN W, HUANG S, et al.Deep learning for mining protein data[J].Briefings in Bioinformatics, 2021, 22(1):194-218.
[79] UDDIN S, KHAN A, HOSSAIN M E, et al.Comparing different supervised machine learning algorithms for disease prediction[J].BMC Medical Informatics and Decision Making, 2019, 19(1):281-292.
[80] PICARD M, SCOTT-BOYER M P, BODEIN A, et al.Integration strategies of multi-omics data for machine learning analysis[J].Computational and Structural Biotechnology Journal, 2021, 19(10):3735-3746.
[81] CHAFAI N, HAYAH I, HOUAGA I, et al.A review of machine learning models applied to genomic prediction in animal breeding[J].Frontiers in Genetics, 2023, 14(11):50-59.