核主成分logistic回归模型在非线性关联分析中的应用  

Applications of the kernel principal component analysis-based logistic regression model on nonlinear association study

作　　者：高青松[1] 薛付忠[1] 

机构地区：[1]山东大学公共卫生学院流行病与卫生统计学研究所,济南250012

出　　处：《山东大学学报（医学版）》2011年第5期140-142,146,共4页Journal of Shandong University:Health Sciences

基　　金：国家自然科学基金资助课题(30871392)

摘　　要：目的将核主成分分析(KPCA)与logistic回归模型相结合,提出一种核主成分logistic(KPCA-based logis-tic)回归模型,用于复杂疾病基因定位的非线性关联分析。方法针对病例对照研究设计的关联分析,对候选基因区域内的单核苷酸多肽性(SNPs)进行核主成分分析,以核主成分为自变量构建logistic回归模型,并对GAW16类风湿关节炎数据中PTPN22和RNF186两个基因区域进行分析,以验证KPCA-based logistic回归模型的有效性和实用性。结果对PTPN22和RNF186两个基因区域的分析结果显示,KPCA-based logistic回归模型既能够检测出单点检验所能发现的区域(PTPN22),也能检测出单点检验所不能发现的区域(RNF186)。结论 KPCA-based logistic回归模型是一种有效的非线性关联分析方法,能够发现更多的易感区域。Objective To combine the kernel principal component analysis（KPCA） and the logistic regression model to propose a KPCA-based logistic regression model for nonlinear association analysis of complex disease gene mapping.Methods For association study of case-control research design,the kernel principal component analysis（KPCA） was performed on single nucleotide polymorphisms（SNPs） of a candidate region to construct the logistic regression model with kernel principal components as independent variables,and then the PTPN22 and RNF186 gene regions of rheumatoid arthritis（RA） data from GAW16 were analyzed to illustrate the effectiveness and practicability of the KPCA-based logistic regression model.Results Application to the PTPN22 and RNF186 gene regions indicated that the KPCA-based logistic regression model could detect regions which could be detected by a single-locus test（PTPN22）,and identify significant regions which could not be identified by a single-locus test（RNF186）.Conclusion As an effective nonlinear association study method,the KPCA-based logistic regression model can identify more susceptible regions.

关 键 词：核主成分分析 LOGISTIC回归 复杂疾病基因定位 关联分析 

分 类 号：R195.1[医药卫生—卫生统计学]