文献类型：期刊文献

英文题名：Proteomic profile analysis and biomarker discovery from mass spectra using independent component analysis combined with uncorrelated linear discriminant analysis

作者：Zhang, Mingjin[1,2,4];Tong, Peijin[1,4];Wang, Wenming[1,4];Geng, Jinpei[3];Du, Yiping[1,4]

机构：[1]E China Univ Sci & Technol, Shanghai Key Lab Funct Mat Chem, Shanghai 200237, Peoples R China;[2]Qinghai Normal Univ, Dept Chem, Xining 810008, Peoples R China;[3]Yantai Entry Exit Inspect & Quarantine Bur, Yantai 264000, Peoples R China;[4]E China Univ Sci & Technol, Res Ctr Anal & Test, Shanghai 200237, Peoples R China

年份：2011

卷号：105

期号：2

起止页码：207

外文期刊名：CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS

收录：;EI(收录号：20242716589702);WOS:【SCI-EXPANDED(收录号:WOS:000288818500008)】；

基金：This work was supported by Science and Technology Commission of Shanghai Municipality (No. 10142201600) and the National Basic Research Priorities Program (No. 2007CB914100).

语种：英文

外文关键词：Independent Component Analysis (ICA); Uncorrelated linear discriminant analysis (ULDA); Mass spectra; Biomarker; Classification

摘要：A strategy based on Independent Component Analysis (ICA) and Uncorrelated linear discriminant analysis (ULDA) was proposed for proteomic profile analysis and potential biomarker discovery from proteomic mass spectra of cancer and control samples. The method mainly includes 3 steps: (1) ICA decomposition for the mass spectra; (2) selection of discriminatory independent components (ICs) using nonparametric Mann-Whitney U-test; and (3) selection of special peaks (m/z locations) as potential biomarkers by executing of ULDA on a mass spectra data set which was reconstructed with the m/z locations that collected from the selected discriminatory ICs. A colorectal cancer data set and an ovarian cancer data set were analyzed with the proposed method. As results. 9 and 10 m/z locations were selected as potential biomarkers for the colorectal and ovarian cancer data set respectively. The classification results of ULDA using the selected potential biomarkers yielded better results than fisher discriminant analysis (FDA) and principal component analysis (PCA), and could distinguish the disease samples from healthy controls on the independent test sets with 100% of sensitivities and specificities for the colorectal cancer dataset and 100% of sensitivity and 96.77% of specificity for the ovarian cancer dataset. (C) 2011 Elsevier B.V. All rights reserved.