黑河地区55份大豆品种资源农艺性状和营养成分的聚类分析  

Cluster Analysis of Agronomic Characters and Nutrition Composition of 55 Soybean Accessions from Heihe Area

作　　者：罗珊[1] 康玉凡[1] 濮绍京[2] 张丽[1] 李振华[1] 肖伶俐[1] 李永华[1] 

机构地区：[1]中国农业大学芽菜研究中心,北京100193 [2]北京农学院红小豆研究中心,北京102206

出　　处：《大豆科学》2009年第3期421-425,共5页Soybean Science

基　　金：国家农业行业专项基金资助项目(nyhyzx07-017)

摘　　要：收集黑河地区55份大豆品种资源材料,以豆芽厂原料大豆S135为对照。采用SPSS15.0软件对大豆品种的15个农艺性状及营养成分进行相关分析、主成分分析和非系统聚类分析。结果表明:单株产量与生育期和单株荚数呈极显著正相关(P<0.01),与营养生长期和百粒重呈显著正相关(P<0.05),与底荚高呈极显著负相关(P<0.01);粗脂肪与粗蛋白呈极显著负相关(P<0.01),与粗纤维、营养生长期呈显著负相关(P<0.05)。在主成分分析中,选取方差累计贡献率为84.49%的前5个主成分来评价黑河地区大豆品种资源。进一步通过非系统聚类分析,将参试的55份品种资源分为5类,其中5个品种与对照品种S135为第一类群,从农艺性状和大豆的营养成分来考虑,第一类适合作芽用大豆品种;且5个类群性状之间的差异较明显,这有利于育种亲本材料的选择,同时为进一步选育和筛选优良的芽用大豆品种提供理论依据。To select soybean varieties suitable for sprouts production,55 soybean accessions from Heihe area including control variety S135 were used, and 15 agronomic characters and nutrition composition were analyzed with the method of correlation analysis and principal component analysis（PCA） and K-means Cluster（KCA） of SPSS15.0. Correlation analysis indicated that single-plant yield correlated significantly positive with growth period and pods per plant（ P 〈 0.01 ） and vegetative period and 100- seed weight（ P 〈 0.05 ）, singleplant yield correlated significantly negative with bottompod height（ P 〈 0. 01 ）. Crude fat correlated significantly negative with crude protein（P 〈0.01 ）and crude fibre and vegetative period（P 〈 0. 05 ）. PCA results showed that 5 Eigenvalues of cumulative variance proportion 84.49 % were selected for evaluation of soybean varieties in Heihe. By the KCA ,55 soybean varieties was classified into 5 clusters ,five varieties and S135 belonged to first clusters , which could be used to grow soybean sprouts. The selected 6 soybean varieties would be useful for breeding and selecting good soybean sprouts varieties.

关 键 词：大豆 相关分析 主成分分析 聚类分析 

分 类 号：S565.1[农业科学—作物学]