近红外光谱结合化学计量学评价胚胎发育潜能  

Evaluating Reproductive Potential of Embryos Using Near Infrared Spectroscopy Combined with Chemometric Methods

作　　者：马雯婷[1] 郑开逸[1] 邵娟[2] 刘素英[2] 孙晓溪[2,3] 杜一平[1] 

机构地区：[1]华东理工大学化学与分子工程学院上海市功能材料重点实验室,上海200237 [2]复旦大学附属妇产科医院上海集爱遗传与不育诊疗中心,上海200011 [3]上海市女性生殖内分泌相关疾病重点实验室,上海200011

出　　处：《化学通报》2013年第1期60-64,共5页Chemistry

基　　金：国家自然科学基金项目(20975039)资助

摘　　要：使用近红外光谱分析方法测量培养后的胚胎培养液,结合偏最小二乘判别分析对胚胎发育潜能进行评价,鉴别具有妊娠能力与不具妊娠能力的胚胎。为了提高模型的判别能力,消除无信息变量对模型稳定性影响,分别采用基于蒙特卡罗的无信息变量消除法(MC-UVE)、竞争性自适应加权抽样法(CARS)与基于变量稳定性的竞争性自适应加权抽样法(SCARS),对光谱进行波长选择。结果表明,与采用全谱74%的正判率相比较,采用这3种波长选择方法,模型独立检验集的正判率分别提高至74.24%,77.12%与80.10%,建模使用变量数降至50以内。比较发现,SCARS的模型优化能力和稳定性均好于MC-UVE和CARS方法。采用近红外光谱结合化学计量学方法预测胚胎的发育潜能是可行的。In this paper,NIR spectroscopy combined with partial least square-discriminant analysis（PLS-DA） model was used to evaluate reproductive potential of embryos.In order to improve performance of the model,three variable selection methods including Monte Carlo uninformative variable elimination（MC-UVE）,competitive adaptive reweighted sampling（CARS） and stability competitive adaptive reweighted sampling（SCARS） were applied concerning establishment of a robust PLS-DA model.The results showed that correct classification rates were increased to 74.24%,77.12% and 80.10% respectively after using the three methods,comparing with 74% of using full spectra,and number of the selected variables reduced to less than 50.Compared with other two algorithms,SCARS displayed the best result in model optimization and stabilization.NIR spectroscopy exhibited a potential application in evaluation of the reproductive potential of embryos.

关 键 词：体外受精 胚胎培养液 近红外(NIR)光谱 波长选择 变量稳定性的竞争性自适应加权抽样法(SCARS) 

分 类 号：R714.8[医药卫生—妇产科学]