杨琼,刘青云,李强勇,彭敏,杨春玲,童艳梅,曾地刚,陈秀荔,陈晓汉,赵永贞

• 1:广西壮族自治区水产科学研究院/广西水产遗传育种与健康养殖重点实验室

摘要(Abstract)：

【目的】探讨逆传播人工神经网络（BPANN）算法用于预测分子标记育种值的可行性。【方法】采用高通量测序技术对284尾F1代凡纳滨对虾及其父母本进行特定长度扩增片段测序（SLAF-seq），随机取200尾对虾样品的数量性状基因座（QTL）基因型和体质量数据，构建BPANN预测模型，利用该模型分别对其余84尾凡纳滨对虾进行体质量性状预测。【结果】构建了1个高密度的单核苷酸多态性（SNP）遗传连锁图谱，鉴定出6个与体质量相关的QTL，对此QTL的BPANN育种值预测结果显示，育种值的平均误差为0.032 0±0.006 4，低于贝叶斯线性回归模型预测的平均误差值（0.0462±0.0056）。【结论】BPANN用于预测凡纳滨对虾分子标记育种值效果良好。

关键词(KeyWords)： 人工神经网络;凡纳滨对虾;分子标记;育种值

Abstract:

Keywords:

基金项目(Foundation): 广西创新驱动发展专项资金项目(桂科AA17204080);; 国家现代农业产业技术体系广西创新团队建设任务书（nycytxgxcxtd-14-01）;; 国家虾产业技术体系建设任务书（CARS-48）

作者(Author): 杨琼,刘青云,李强勇,彭敏,杨春玲,童艳梅,曾地刚,陈秀荔,陈晓汉,赵永贞

参考文献(References)：

• [1]孙效文,鲁翠云,贾智英,等.水产动物分子育种研究进展[J].中国水产科学, 2009, 16(6):981-990.
• [2] MEUWISSEN T H E, HAYES B J, GODDARD M E.Prediction of total genetic value using genome-wide dense marker maps[J]. Genetics, 2001, 157(4):1819-1829.
• [3] OKUT H, WU X L, ROSA G J M, et al. Predicting expected progeny difference for marbling score in Angus cattle using artificial neural networks and Bayesian regression models[J]. Genetics, Selection, Evolution:GSE,2013, 45(1):34.
• [4] GIANOLA D, DE LOS CAMPOS G, HILL W G, et al.Additive genetic variability and the Bayesian alphabet[J].Genetics, 2009, 183(1):347-363.
• [5] ARYA S, HO CHUNG Y. Artificial neural network estimation of data and channel characteristics in free-space ultraviolet communications[J]. Applied Optics, 2020,59(13):3806-3818.
• [6] YAO L T, ZHONG Y F, WU J Y, et al. Multivariable logistic regression and back propagation artificial neural network to predict diabetic retinopathy[J]. Diabetes, Metabolic Syndrome and Obesity:Targets and Therapy, 2019, 12:1943-1951.
• [7] CHON K H, COHEN R J. Linear and nonlinear ARMA model parameter estimation using an artificial neural network[J]. IEEE Transactions on Bio-Medical Engineering, 1997, 44(3):168-174.
• [8] ZHANG W, BAO Z M, JIANG S, et al. An artificial neural network-based algorithm for evaluation of fatigue crack propagation considering nonlinear damage accumulation[J].Materials(Basel, Switzerland), 2016, 9(6):483.
• [9] TA L E B I N, N A S R A B A D I A M, M O H A M M A DREZAZADEH I, et al. nCREANN:nonlinear causal relationship estimation by artificial neural network; applied for autism connectivity study[J]. IEEE Transactions on Medical Imaging, 2019, 38(12):2883-2890.
• [10] OKUT H, GIANOLA D, ROSA G J M, et al. Prediction of body mass index in mice using dense molecular markers and a regularized neural network[J]. Genetics Research,2011, 93(3):189-201.
• [11] GIANOLA D, OKUT H, WEIGEL K A, et al. Predicting complex quantitative traits with Bayesian neural networks:a case study with Jersey cows and wheat[J]. BMC Genetics, 2011, 12:87.
• [12] LIU D Y, MA C X, HONG W G, et al. Construction and analysis of high-density linkage map using high-throughput sequencing data[J]. PLo S One, 2014,9(6):e98855.
• [13] MAUGHAN P J, BONIFACIO A, JELLEN E N, et al. A genetic linkage map of quinoa(Chenopodium quinoa)based on AFLP, RAPD, and SSR markers[J]. TAG Theoretical and Applied Genetics Theoretische and Angewandte Genetik, 2004, 109(6):1188-1195.
• [14] KUIPER M T. Building a high-density genetic map using the AFLP technology[J]. Methods in Molecular Biology(Clifton, N J), 1998, 82:157-171.
• [15] SUN X W, LIU D Y, ZHANG X F, et al. SLAF-seq:an efficient method of large-scale de novo SNP discovery and genotyping using high-throughput sequencing[J].PLoS One, 2013, 8(3):e58700.
• [16] BROMAN K W, GATTI D M, SIMECEK P, et al. R/qtl2:software for mapping quantitative trait loci with high-dimensional data and multiparent populations[J].Genetics, 2019, 211(2):495-502.
• [17] GARCIA D K, DHAR A K, ALCIVAR-WARREN A.Molecular analysis of a RAPD marker(B20)reveals two microsatellites and differential m RNA expression in Penaeus vannamei[J]. Molecular Marine Biology and Biotechnology, 1996, 5(1):71-83.
• [18] PéREZ F, ORTIZ J, ZHINAULA M, et al. Development of EST-SSR markers by data mining in three species of shrimp:Litopenaeus vannamei, Litopenaeus stylirostris,and Trachypenaeus birdy[J]. Marine Biotechnology(New York, N Y), 2005, 7(5):554-569.
• [19] ANDRIANTAHINA F, LIU X L, HUANG H. Genetic map construction and quantitative trait locus(QTL)detection of growth-related traits in Litopenaeus vannamei for selective breeding applications[J]. PLoS One, 2013, 8(9):e75206.
• [20] ZHANG L S, YANG C J, ZHANG Y, et al. A genetic linkage map of Pacific white shrimp(Litopenaeus vannamei):sex-linked microsatellite markers and high recombination rates[J]. Genetica, 2007, 131(1):37-49.
• [21] YU Y, ZHANG X, YUAN J, et al. Genome survey and high-density genetic map construction provide genomic and genetic resources for the Pacific White Shrimp Litopenaeus vannamei[J]. Scientific Reports, 2015, 5:15612.
• [22] GONZáLEZ-RECIO O, WEIGEL K A, GIANOLA D, et al. L2-Boosting algorithm applied to high-dimensional problems in genomic selection[J]. Genetics Research,2010, 92(3):227-237.
• [23] YAO C, SPURLOCK D M, ARMENTANO L E, et al.Random Forests approach for identifying additive and epistatic single nucleotide polymorphisms associated with residual feed intake in dairy cattle[J]. Journal of Dairy Science, 2013, 96(10):6716-6729.
• [24] EHRET A, HOCHSTUHL D, GIANOLA D, et al.Application of neural networks with back-propagation to genome-enabled prediction of complex traits in Holstein-Friesian and German Fleckvieh cattle[J].Genetics, Selection, Evolution:GSE, 2015, 47(1):22.