期刊文献+

样条变换偏最小二乘在肝癌数据分类中的应用 被引量:1

The classification of hepatocellular carcinoma data set with partial least squares base on spline transformation
下载PDF
导出
摘要 肝癌是中国最常见的恶性肿瘤之一。基于肿瘤基因表达谱数据的分析与研究是当今研究的热点,对于癌症的早期诊断、治疗具有十分重要的意义。针对高维小样本基因表达谱数据所显现的变量间严重共线性、类别变量与预测变量的非线性关系,采用了基于样条变换的偏最小二乘回归新技术。首先通过筛选法去除基因表达谱数据中的冗余信息,然后以3次B基样条变换实现非线性基因表达谱数据的线性化重构,随后将重构的矩阵交由偏最小二乘法构建类别变量与预测变量间的关系模型。最后,通过对肝癌肿瘤基因表达谱数据的分析,结果显示此分类模型对数据重构稳健,有效的解决了高维小样本基因表达谱数据间的过拟合和变量间的共线性,具有较高的拟合和分类正确率。 Hepatocellular Carcinoma (HCC)is one of the most popular malignant tumors in the world. Recently, the research base on gene expression profile is a hot topic and has strong impact on HCC treatment and diagnosis. Owing to the severe collinearity among variables and the nonlinear relationship between predictor variables and response variables, a novel technology of Partial Least Squares (PLS)base on Spline Transformation (SPLINE-PLS)was adopted. The redundancy in gene expression profile should be eliminated through filter method. Then B-spline function of original non-linear space was transformed into new linear space by using non-linear transformation and the related model between new response variables and predictor variables built with PLS. By analysis of HCC data set, the result showed that this method could yield high accuracy in reconstructing gene data set and overcome the drawback of overfitting and collinearity between variables.
作者 李建更 李辉
出处 《生物学杂志》 CAS CSCD 2011年第6期58-61,共4页 Journal of Biology
基金 北京市自然科学基金(Grant o.4092021) 北京市教育委员会科技计划项目(JC002011200903)
关键词 基因表达谱 样条变换 偏最小二乘 筛选法 过拟合 gene expression profile spline transformation PLS filtering method overfitting
  • 相关文献

参考文献13

  • 1Parkin D M,Bray F,Ferlay J,et al.Global cacer statistics[J].CA Cancer J Clin,2002,55:74-108.
  • 2El-Serag H B.Hepatocellular carcinoma:recent trends in the United States[J].Gastroenterology,2004,127[5 Suppl l]:27-34.
  • 3Yoon S K.Recent advances in tumor marker of human hepatocel-lular carcinoma[J].Intervirology,2008,51 (Suppl 1); 34-41.
  • 4Debruyne E N,Delanghe J R.Diagnosing and monitoring hepatocellular carcinoma with alpha-fetoprotein:new aspects and applications[J].Clin Chim Acta,2008,395(l-2):19-26.
  • 5Sherman M.Hepatocellula cacinoma:epidemiology,risk factors and screening[J].Semin Liver Dis,2005,25:143-154.
  • 6Nguyen D V,Rocke D.Tumor classification by partial least squares using microarray gene expression data[J].Bioinformatics,2002,18:39-50.
  • 7Nguyen D V,Rocke D.Multi -class cancer classification via partial least squares with gene exprssion profiles[J].Bioinformatics,2002,18:1216-1226.
  • 8Boulesteix A L,Strimmer K.Partial least squares:a versatile tool for the analysis of high-dimensional genomic data[J].Brifin gs in Bionfonnatics,2007,8(l):32-44.
  • 9Wang H Q,Wong H S,Zhu H L,et al.A neural network-based biomarker association information extraction approach for cancer classification[J].Journal of Biomedical Informatics,2009,42:654-666.
  • 10Tenenhaus A,Giron A,Viennet E,et al.Kernel logistic PLS:a tool for supervised nonlinear dimensionality reduction and binary classification[J].Computational Statistics & data Analysis,2007,51:4083-4100.

同被引文献22

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部