基于随机森林算法和SRAP分子标记的桂花品种鉴定方法

doi:10.11707/j.1001-7488.20180104

摘要/Abstract

摘要： [目的]为了解决桂花品种难以鉴定以及苗木生产和园林应用中品种混杂、以次充好和常规DNA指纹图谱无法很好地应用于品种鉴定的问题，提出一种基于随机森林算法和SRAP分子标记的桂花品种鉴定方法，以实现桂花品种简便、快速和准确的鉴定。[方法]以45个桂花品种或变异类型为材料，提取DNA，使用90对SRAP引物进行PCR扩增，以毛细管电泳技术采集扩增信息，筛选出多态性强、扩增结果稳定的引物，计算单对引物的多态信息含量（PIC）、带型数、有效带型数、分辨能力（D）、带型分布的卡方值（χ²）和无法区分的样品对数（x）。筛选出能够完全区分所有品种的引物对组合位点数据作为训练集，用于构建基于随机森林算法的分类模型，并根据模型的泛化能力和分类效果选择最优的分类模型。[结果]筛选出10对SRAP引物，平均PIC为0.26，平均带型数为33.9，平均有效带型数为26.6，平均D为0.97，平均χ²为21.07，平均x为28.2。构建了8个分类模型rf1-rf8，每个分类模型均含有2对SRAP引物。所有分类模型都能完全区分所有桂花品种，模型的袋外数据（OOB）误差估计在0.004 4~0.013 9之间，rf5和rf3泛化能力最强，rf8最弱。rf1分类效果最优，rf3、rf4、rf5和rf7其次，rf2、rf6和rf8最差。[结论]分类模型rf1、rf3、rf4、rf5和rf7的分类能力最佳，所用SRAP引物对分别为me1/em3+me9/em6、me4/em5+me9/em6、me4/em8+me9/em6、me6/em9+me9/em6和me5/em5+me9/em6。除引物对的分辨能力外，所选引物对之间的相关性也显著影响模型的分类能力，相关性越弱，模型的分类能力越强。本研究提出的基于随机森林算法和SRAP分子标记的桂花品种鉴定方法，能够实现桂花品种简便、快速、准确的鉴定，满足桂花苗木生产、推广应用和种质资源保护对于品种鉴定的要求。

关键词: 桂花, 品种鉴定, 分类模型, SRAP分子标记, 随机森林算法

Abstract: [Objective] To solve the problem that Osmanthus fragrans cultivars being hardly identified in nursery stock production and landscape application, this study proposed a classification method based on random forest algorithm and SRAP molecular markers, which can be used for easily, quickly and accurately identifying varieties.[Method] DNA of 45 O. fragrans cultivars were extracted, which were applied to PCR amplification, using 90 SRAP primer pairs. The fragments were examined by Capillary Electrophoresis to screen the primer pairs with high polymorphism level and steady amplification. The amplification data were used to calculate polymorphism information content (PIC), numbers of patterns, numbers of effective patterns, the discriminating power (D), chi-square value of patterns distribution (χ²), and pairs of indistinguishable samples (x). The locus data of combination of primer pairs that can discriminate all cultivars were used as training set for construction of classification modes based on random forest algorithm. The models with best classifying ability were selected depending on their generalization ability and classifying quality.[Result] A total of 10 SRAP primer pairs were selected, with mean PIC of 0.26, mean numbers of patterns of 33.9, mean numbers of effective patterns of 26.6, mean D of 0.97, mean χ² of 21.07 and mean x of 28.2. Eight classification models were constructed using 8 combination of 2 prime pairs that can discriminate all cultivars (rf1-rf8). The OOB (out of bag) error rate of these models ranged from 0.004 4-0.013 9. Among of them, rf5 and rf3 had the strongest generalization ability, while rf8 had the weakest. And rf1 had the best classifying quality, rf3, rf4, rf5 and rf7 had better, while rf8 had the worst.[Conclusion] Classification models rf1, rf3, rf4, rf5 and rf7 have the strongest classifying ability, with the combination of SRAP primer pairs of me1/em3+me9/em6, me4/em5+me9/em6, me4/em8+me9/em6, me6/em9+me9/em6 and me5/em5+me9/em6, separately. The weaker correlation of selected primer pairs brings the stronger classifying ability of models. The method proposed in this study can be applied to identity O. fragrans cultivars quickly and accurately.

Key words: Osmanthus fragrans, cultivar identification, classification model, SRAP marker, random forest algorithm

中图分类号:

邱帅, 沈柏春, 李婷婷, 郭娟, 王霁, 孙丽娜, 陈徐平, 胡绍庆. 基于随机森林算法和SRAP分子标记的桂花品种鉴定方法[J]. 林业科学, 2018, 54(1): 32-45.

Qiu Shuai, Shen Baichun, Li Tingting, Guo Juan, Wang Ji, Sun Lina, Chen Xuping, Hu Shaoqing. A Method of Osmanthus fragrans Cultivars Identification Based on Random Forest Algorithm and SRAP Molecular Markers[J]. Scientia Silvae Sinicae, 2018, 54(1): 32-45.

参考文献

曹廷杰, 谢菁忠, 吴秋红, 等. 2015. 河南省近年审定小麦品种基于系谱和SNP标记的遗传多样性分析. 作物学报, 41(2):197-206.
(Cao T J, Xie J Z, Wu Q H, et al. 2015. Genetic diversity of registered wheat varieties in Henan Province based on pedigree and single-nucleotide polymorphism. Acta Agronomica Sinica, 41(2):197-206.[in Chinese])
陈鹭真, 李振基, 周涵韬. 2002. 福建省桫椤科植物的分子分类学研究. 厦门大学学报:自然科学版, 41(4):481-486.
(Chen L Z, Li Z J, Zhou H T. 2002. Study on molecular taxonomy of 5 species of Cyatheaceae in Fujian. Journal of Xiamen University:Natural Science Edition, 41(4):481-486.[in Chinese])
段一凡,王贤荣, 梁丽丽, 等. 2014. 桂花品种SSR荧光指纹图谱的构建. 南京林业大学学报:自然科学版, 38(s1):1-6.
(Duan Y F, Wang X R, Liang L L, et al. 2014. Fingerprinting and identification of Osmanthus fragrans cultivars using fluorescence-labeled SSR markers. Journal of Nanjing Forestry University:Natural Science Edition, 38(s1):1-6.[in Chinese])
黄秦军, 苏晓华, 张香华. 2002. SSR分子标记与林木遗传育种. 世界林业研究, 15(3):14-21.
(Huang Q J, Su X H, Zhang X H. 2002. Microsatellite marker and its application in tree genetics and breeding. World Forestry Research, 15(3):14-21.[in Chinese])
李欣海. 2013. 随机森林模型在分类与回归分析中的应用. 应用昆虫学报, 50(4):1190-1197.
(Li X H. 2013. Using "random forest" for classification and regression. Chinese Bulletin of Entomology, 50(4):1190-1197.[in Chinese])
李婷婷, 朱锦茹, 邱帅,等. 2016. 基于CE-SRAP标记的榉树优良单株指纹图谱构建. 植物遗传资源学报, 17(1):169-176.
(Li T T, Zhu J R, Qiu S, et al. 2016. Fingerprinting construction for superior individuals of Zelkova schneideriana based on CE-SRAP. Journal of Plant Genetic Resources, 17(1):169-176.[in Chinese])
刘龙昌, 向其柏, 刘玉莲. 2004. RAPD标记在桂花遗传多样性检测和品种鉴定中的应用(英文). 南京林业大学学报:自然科学版, 28(s1):76-82.
(Liu L C, Xiang Q B, Liu Y L. 2004. The application of RAPD markers in diversity detection and cultivars identification of Osmanthus fragrans. Journal of Nanjing Forestry University:Natural Sciences Edition, 28(s1):76-82.[in English])
罗可, 林睦纲, 郗东妹. 2005. 数据挖掘中分类算法综述. 计算机工程, 31(1):3-5.
(Luo K, Lin M G, Xi D M. 2005. Review of classification algorithms in data mining. Computer Engineering, 31(1):3-5.[in Chinese])
马衣努尔姑·吐地, 张延辉, 秦伟, 等. 2016. 基于SSR分子标记技术的新疆苹果资源指纹图谱的构建. 新疆农业大学学报, 39(1):26-34.
(Maynur T, Zhang Y H, Qing W, et al. 2016. Construction of fingerprint of apple resources in Xinjiang based on SSR molecular markers. Journal of Xinjiang Agricultural University, 39(1):26-34.[in Chinese])
乔中全, 王晓明, 李永欣, 等. 2016. 桂花优良品种‘珍珠彩桂’遗传多样性的ISSR分析及指纹图谱构建. 湖南林业科技, 43(3):1-5.
(Qiao Z Q, Wang X M, Li Y X, et al. 2016. Genetic diversity and fingerprint construction of varieties of Osmanthus fragrans ‘Zhenzhu Caigui’ by ISSR markers. Hunan Forestry Science Technology, 43(3):1-5.[in Chinese])
邱帅, 丁信誉, 席梦利, 等. 2013. 东方百合SRAP体系优化及引物筛选. 南京林业大学学报:自然科学版, 37(3):6-10.
(Qiu S, Ding X Y, Xi M L, et al. 2013. Optimization of SRAP PCR system and primers screening of oriental lily hybrids. Journal of Nanjing Forestry University:Natural Science Edition, 37(3):6-10.[in Chinese])
向其柏, 刘玉莲. 2008.中国桂花品种图志. 杭州:浙江科学技术出版社, 2, 8, 80-81, 86.
(Xiang Q B, Liu Y L. 2008. An illustrated monograph of the sweet osmanthus cultivars in China. Hangzhou:Zhejiang Science & Technology Press, 2, 8, 80-81, 86.[in Chinese and English])
杨康民. 2013. 中国桂花. 北京:中国林业出版社, 11-24.
(Yang K M. 2013. Chinese osmanthus. Beijing:China Forestry Publishing House, 11-24.[in Chinese])
钟淦彬, 李维国, 吴春太, 等. 2013. 188份巴西橡胶树种质材料AFLP指纹图谱分析. 热带作物学报, 34(1):1-9.
(Zhong G B, Li W G, Wu C T, et al. 2013. AFLP analysis of 188 germplasm material for rubber tree (Hevea brasiliensis). Chinese Journal of Tropical Crops, 34(1):1-9.[in Chinese])
Akbari M, Wenzl P, Caig V, et al. 2006. Diversity arrays technology (DArT) for high-throughput profiling of the hexaploid wheat genome. Theoretical and Applied Genetics, 113(8):1409-1420.
Akond M, Jin S, Wang X. 2012. Molecular characterization of selected wild species and miniature roses based on SSR markers. Scientia Horticulturae, 147:89-97.
Belaj A, Satovic Z, Cipriani G, et al. 2003. Comparative study of the discriminating capacity of RAPD, AFLP and SSR markers and of their effectiveness in establishing genetic relationships in olive. Theoretical and Applied Genetics, 107(4):736-744.
Bhatia R, Singh K P, Jhang T, et al. 2009. Assessment of clonal fidelity of micropropagated gerbera plants by ISSR markers. Scientia Horticulturae, 119:208-211.
Breiman L. 2001a. Random forests. Machine Learning, 45(1):5-32.
Breiman L. 2001b. Statistical modeling:the two cultures. Statistical Science, 16(3):199-215.
Breiman L. 2002. Manual on setting up, using, and understanding Random Forests V3.1. https://www.stat.berkeley.edu/~breiman/Using_random_forests_V3.1.pdf.
Cutler D R, Edwards T C, Beard K H, et al. 2007. Random forests for classification in ecology. Ecology, 88(1):2783-2792.
Faleiro F G, Cordeiro M C R, Pinto A, et al. 2010. Fingerprinting analysis of Mango (Mangifera indica L.) cultivars introduced in Brazil using RAPD markers. Acta Horticulturae, 864:1127-1132.
Ferrari M, Gori M, Monnanni R, et al. 2005. DNA fingerprinting of Corylus avellana L. accessions revealed by AFLP molecular markers. Acta Horticulturae, 686:125-134.
Han Y H, Kang Y, Torres-Jerez I, et al. 2011. Genome-wide SNP discovery in tetraploid alfalfa using 454 sequencing and high resolution melting analysis. BMC Genomics, 12(1):350.
Li G, Quiros C F. 2001. Sequence-related amplified polymorphism (SRAP), a new marker system based on a simple PCR reaction:its application to mapping and gene tagging in Brassica. Theoretical and Applied Genetics, 103(2):455-461.
Murdoch D. 2017. rgl Overview. https://cran.r-project.org/web/packages/rgl/vignettes/rgl.html.
Reddy M P, Sarla N, Siddiq E A. 2002. Inter simple sequence repeat (ISSR) polymorphism and its application in plant breeding. Euphytica, 128(1):9-17.
Sharma S K, Knox M R, Ellis T H. 1996. AFLP analysis of the diversity and phylogeny of Lens and its comparison with RAPD analysis. Theoretical and Applied Genetics, 93(5):751-758.
Templ M, Alfons A, Filzmoser P. 2012. Exploring incomplete data using visualization techniques. Advances in Data Analysis and Classification, 6(1):29-47.
Tessier C, David J, This P, et al. 1999. Optimization of the choice of molecular markers for varietal identification in Vitis vinifera L. Theoretical and Applied Genetics, 98(1):171-177.
Vos P, Hogers R, Bleeker M, et al. 1995. AFLP:a new technique for DNA fingerprinting. Nucleic Acids Research, 23(21):4407-4414.

[1]	刘传泽, 王霄, 陈龙现, 郭慧, 罗瑞, 周玉成. 基于随机森林算法的纤维板表面缺陷识别[J]. 林业科学, 2018, 54(11): 121-126.
[2]	梁慧玲, 林玉蕊, 杨光, 苏漳文, 王文辉, 郭福涛. 基于气象因子的随机森林算法在塔河地区林火预测中的应用[J]. 林业科学, 2016, 52(1): 89-98.
[3]	李楠;柳新红;李因刚;李海波;盛炜彤;惠刚盈;郑勇奇. 白花树天然群体的遗传多样性[J]. 林业科学, 2012, 48(11): 49-56.
[4]	何飞;刘兴良马钦彦史作民陈俊华. 横断山区野桂花林群落特征*[J]. 林业科学, 2009, 12(6): 153-157.
[5]	刘志远;范卫红;沈世华. 构树SRAP分子标记*[J]. 林业科学, 2009, 12(12): 54-58.
[6]	黄玉霞许东蓓蒲肃. SVM方法在森林火险预测中的应用[J]. 林业科学, 2007, 43(10): 77-82.
[7]	闫文德田大伦陈书军向建林向东. 4个树种茎流养分特征研究[J]. 林业科学, 2005, 41(6): 50-56.