高密度遗传图谱单标记选择的随机森林法
|
摘要
高密度图谱上的分子标记数量众多,属于典型的高维数据,用传统的回归分析方法难以筛选。随机森林是一种基于决策树的算法,通过对决策树进行汇总,提高了模型的预测精度,可以用来解决回归问题与分类问题。本研究采用随机森林中的变量重要性评分的方法来对高密度遗传图谱上的与性状相关的单个标记进行选择,对不同遗传率、不同群体大小的情况进行了模拟研究,每个参数组合模拟100次,计算选出标记位置的均值与标准差,统计选择正确的次数,模拟结果表明该方法是一种行之有效的方法。
The number of molecular markers on the high-density map is numerous and belongs to typical high-dimensional data, which is difficult to screen by traditional regression analysis methods. Random forest is a decision tree-based algorithm. By summarizing the decision tree, the prediction accuracy of the model is improved, which can be used to solve the regression problem and classification problem. In this study, the random forest algorithm is applied to the marker selection of high-density maps. Through simulation studies, it is found that the random forest algorithm has a better effect on single genetic marker selection on high-density genetic maps.
The number of molecular markers on the high-density map is numerous and belongs to typical high-dimensional data, which is difficult to screen by traditional regression analysis methods. Random forest is a decision tree-based algorithm. By summarizing the decision tree, the prediction accuracy of the model is improved, which can be used to solve the regression problem and classification problem. In this study, the random forest algorithm is applied to the marker selection of high-density maps. Through simulation studies, it is found that the random forest algorithm has a better effect on single genetic marker selection on high-density genetic maps.
引文
[1]张剑锋,罗朝鹏,何声宝,等.应用SNP标记分析24份烟草品种的遗传多样性.烟草科技,2017(11):6-13
[2]张恒,刘众杰,樊秀彩,张川,崔力文,刘崇怀,房经贵.葡萄果粒形状简化基因组关联分析.园艺学报,2017,44(10):1959-1968
[3]高星,李永祥,杨明涛,等.基于高密度遗传图谱的玉米籽粒灌浆特性遗传解析.中国农业科学,2017(21):39-51
[4]李玮,宋国琦,陈明丽,等.小麦分子标记数据库的建立.山东农业科学,2017(11):7-18
[5]Edward KJ,Poole RL,Barker GL.Plant genotyping II:SNP technology.CABI publishing,2008,12,21
[6]金名捺,潘英华,丘式浚,等.基于全基因组芯片开发水稻HRM特异分子标记.植物遗传资源学报,2018,19(06):41-49
[7]王振玉,李威,周晓箭,等.棉花单核苷酸多态性标记研究进展.棉花学报,2016,28(4):399-406
[8]王晨,马宁,郭春和,等.基于SNP芯片分析的蓝塘猪遗传群体结构.广东农业科学,2018,45(6):110-115,173
[9]刘冉冉,赵桂苹,文杰.鸡基因组育种和保种用SNP芯片研发及应用.中国家禽,2018,40(15):6-11
[10]Davey JW,Blaxter ML.RADseq:next-generation population genetics.Brief Funct Genomics,2010(9):416-423
[11]Davery JW,Hohenlohe PA,Etter PD,et al.Genome-wide enetic marker discovery and genotyping using next-generation sequencing.Nat Rev Genet,2011(12):499-510
[12]Sun XW,Liu DY,Zhang XF,et al.SLAF-seq:An efficient method of large-scale De Novo SNP discovery and genotyping using high-throughput sequencing.PLOS ONE,2013,8(3):e58700
[13]Breiman L.Random Forests.Machine Learn,2001(45):5-32
[14]S.Naderi,T.Yin,S.K?nig.Random forest estimation of genomic breeding values for disease susceptibility over different disease incidences and genomic architectures in simulated cow calibration groups.J Dairy Sci.2016 Sep,99(9):7261-7273
[15]Jonathan A.Atkinson,Guillaume Lobet,Manuel Noll,Patrick E.Meyer,Marcus Griffiths,Darren M.Wells;Combining semi-automated image analysis techniques with machine learning algorithms to accelerate large-scale genetic studies,Giga Science,Volume 6,Issue 10,1 October 2017,Pages 1-7,https://doi.org/10.1093/gigascience/gix084
[16]Animesh Acharjee,Bjorn Kloosterman,Richard G.F.Visser.Integration of multi-omics data for prediction of phenotypic traits using random forest.BMC Bioinformatics,2016,17(5):363
[17]冯盼峰,温永仙.基于随机森林算法的两阶段变量选择研究.系统科学与数学,2018,38(1):119-130
[18]Vincent B,Gilles L,Pierre G,et al.Exploiting SNP Correlations within Random Forest for Genome-Wide Association Studies.PLo SONE,2014,9(4):e93379
[19]Sinoquet C.A method combining a random forest-based technique with the modeling of linkage disequilibrium through latent variables,to run multilocus genome-wide association studies.Bmc Bioinformatics,2018,19(1):106
[2]张恒,刘众杰,樊秀彩,张川,崔力文,刘崇怀,房经贵.葡萄果粒形状简化基因组关联分析.园艺学报,2017,44(10):1959-1968
[3]高星,李永祥,杨明涛,等.基于高密度遗传图谱的玉米籽粒灌浆特性遗传解析.中国农业科学,2017(21):39-51
[4]李玮,宋国琦,陈明丽,等.小麦分子标记数据库的建立.山东农业科学,2017(11):7-18
[5]Edward KJ,Poole RL,Barker GL.Plant genotyping II:SNP technology.CABI publishing,2008,12,21
[6]金名捺,潘英华,丘式浚,等.基于全基因组芯片开发水稻HRM特异分子标记.植物遗传资源学报,2018,19(06):41-49
[7]王振玉,李威,周晓箭,等.棉花单核苷酸多态性标记研究进展.棉花学报,2016,28(4):399-406
[8]王晨,马宁,郭春和,等.基于SNP芯片分析的蓝塘猪遗传群体结构.广东农业科学,2018,45(6):110-115,173
[9]刘冉冉,赵桂苹,文杰.鸡基因组育种和保种用SNP芯片研发及应用.中国家禽,2018,40(15):6-11
[10]Davey JW,Blaxter ML.RADseq:next-generation population genetics.Brief Funct Genomics,2010(9):416-423
[11]Davery JW,Hohenlohe PA,Etter PD,et al.Genome-wide enetic marker discovery and genotyping using next-generation sequencing.Nat Rev Genet,2011(12):499-510
[12]Sun XW,Liu DY,Zhang XF,et al.SLAF-seq:An efficient method of large-scale De Novo SNP discovery and genotyping using high-throughput sequencing.PLOS ONE,2013,8(3):e58700
[13]Breiman L.Random Forests.Machine Learn,2001(45):5-32
[14]S.Naderi,T.Yin,S.K?nig.Random forest estimation of genomic breeding values for disease susceptibility over different disease incidences and genomic architectures in simulated cow calibration groups.J Dairy Sci.2016 Sep,99(9):7261-7273
[15]Jonathan A.Atkinson,Guillaume Lobet,Manuel Noll,Patrick E.Meyer,Marcus Griffiths,Darren M.Wells;Combining semi-automated image analysis techniques with machine learning algorithms to accelerate large-scale genetic studies,Giga Science,Volume 6,Issue 10,1 October 2017,Pages 1-7,https://doi.org/10.1093/gigascience/gix084
[16]Animesh Acharjee,Bjorn Kloosterman,Richard G.F.Visser.Integration of multi-omics data for prediction of phenotypic traits using random forest.BMC Bioinformatics,2016,17(5):363
[17]冯盼峰,温永仙.基于随机森林算法的两阶段变量选择研究.系统科学与数学,2018,38(1):119-130
[18]Vincent B,Gilles L,Pierre G,et al.Exploiting SNP Correlations within Random Forest for Genome-Wide Association Studies.PLo SONE,2014,9(4):e93379
[19]Sinoquet C.A method combining a random forest-based technique with the modeling of linkage disequilibrium through latent variables,to run multilocus genome-wide association studies.Bmc Bioinformatics,2018,19(1):106
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |