运用近邻传播聚类分析进行SELDI-TOF蛋白质谱特征选择

doi:10.3969/j.issn.0258-8021.2013.01.003

摘要
图/表
参考文献
相关文章 (2)

全文: PDF (773 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对如何有效分析高通量SELDITOF质谱数据以及筛选与肿瘤相关的蛋白质位点，提出一种基于近邻传播聚类分析的特征选择方法。首先利用ttest对SELDI数据进行初筛，然后利用近邻传播聚类分析以及零空间LDA对数据进行降维和去相关处理，最后采用SVMRFE进行特征选择，筛选出与肿瘤判别相关的蛋白质位点。利用SVM、KNN、NB及J4.8等4个分类器，估算算法的分类性能。结果表明，在卵巢癌公共数据集OC.WCX2a和OC.WCX2b以及浙江省肿瘤医院乳腺癌数据集BC-WCX2a上显示该算法，在上述3个数据集中分类率分别达到96.43%、99.66%、90.88%，敏感性分别达到97.00%、100%、96.17%，特异性分别达到95.85%、99.08%、81.92%，并分别挑选出与肿瘤判别相关的10个蛋白位点。所提出的算法能够获得较好的分类率，有效提取出具有较好判别效果的蛋白质谱位点，有助于癌症的辅助诊断。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	任玉强¹李丽杨合龙¹祝磊<

关键词 ：蛋白质质谱, 近邻传播聚类分析, 特征选择, 生物标志物

Abstract：To analysis high throughput and high resolution mass spectrometry data effectively and capture the cancer related protein feature from the mass spectrometry data, diagnosis called a feature selection based on affinity propagation clustering of mass spectrometry was proposed in this paper. Firstly, the ttest was used on mass spectrometry data, followed by feature selection based on affinity propagation clustering. Next, affinity propagtion clustering and NS-LDA was used for reducing dimensions and correlation. Thirdly, SVM-RFE was used to select the features. Finally, we used four classifiers to estimate the performance of the algorithm. The proposed method was tested and evaluated on the ovarian cancer database OC-WCX2a, OC-WCX2b, and breast cancer database BC-WCX2a. Classification was achieved 96.43 %, 99.66 % and 90.88 %, sensitivity was achieved 97.00 %, 100 % and 96.17 %, specificity was achieved 95.85 %, 99.08 % and 81.92 %, respectively. And 10 m/z features were selected for each dataset. The experimental results showed good performance of the method, and the method is expected to be used in cancer diagnosis.

Key words： mass spectrometry affinity propagation clustering feature selection biomarker

基金资助:国家自然科学基金（60801054, 60801055）；国家杰出青年基金（60788101）

引用本文:

任玉强¹李丽杨合龙¹祝磊<. 运用近邻传播聚类分析进行SELDI-TOF蛋白质谱特征选择[J]. 中国生物医学工程学报, 2013, 32(1): 14-20.
REN Yu Qiang¹LI Li Ming^1*CHAI Xin Yu¹REN Qiu Shi²YANG He Long^{1 &. Feature Selection and Sample Classification for SELDITOF Mass Spectrometry Data Based on Affinity Propagation Clustering. journal1, 2013, 32(1): 14-20.}

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2013.01.003 或 http://cjbme.csbme.org/CN/Y2013/V32/I1/14

［1］Jemal A, Sieg el R, Ward E, et al. Cancer statistics ［J］. A Cancer Journal of Clinicians, 2011, (61): 212-236.
［2］Bruce A, Julian L, Martin R, et al. Molecular biology of the cell, fourth edition ［M］. New York: Garland Science, 2004.
［3］Shin H, Sheu B, Joseph M, et al. Guiltbyassociation feature selection: identifying biomakers from proteomic profiles ［J］. Biomed Inform, 2008, 41: 124-136.

［4］Somorjai RL, Dolenko B, Baumgartner R. Class prediction and discovery using gene microarray and proteomics mass spectroscopy data: curses, caveats, cautions ［J］. Bioinformatics， 2003, 19(12): 1484-1491.
［5］Thomas A, Tourassi GD, Elmaghraby AS, et al. Data mining in proteomic mass spectrometry［J］. Clinical Proteomics, 2006, 2(1): 13-21.
［6］Hanczar B, Courtine M, Benis A, et al. Improving classification of microarray data using prototypebased feature selection［J］. SIGKDD Exploration, 2003, 5: 23-30.
［7］Wang Yuhang, Fillia Makedon, James Ford, et al. HykGene: a hybrid approach for selecting marker genes for phenotype classification using microarray gene expression data［J］. Bioinformatics, 2005, 218): 1530-1537.
［8］Yang Pengyi, Zhang Zili, Zhou Bingbing, et al. A clustering based hybrid system for biomaker selection and sample classification of mass spectrometry data［J］. Neurocomputing, 2010, 73(13-16): 2317-2331.
［9］Yang Pengyi, Zhang Zili. A clustering based hybrid system for mass spectrometry data analysis［J］. Pattern Recognition in Bioinformatics, Lecture Notes in Bioinformatics, 2008, 5265: 98-109.
［10］Huang Rui, Liu Qingshan, Lu Hanqing, et al. Solving the small sample size problem of LDA ［J］. Pattern Recognition, 2002, 3: 29-32.
［11］Dueck D, Frey BJ. Clustering by passing messages between data points［J］. Science, 2007, 315(5814): 972-976.
［12］李伟红，龚卫国，陈伟民，等. 基于SVMRFE的人脸特征选择方法［J］. 光电工程, 2006, 33(5): 113-117.
［13］王尧佳，祝磊，韩斌. 基于递归零空间线性判别分析算法的蛋白质质谱数据特征选择［J］. 航天医学与医学工程, 2010, 23(5): 324-328.
［14］孟辉，洪文学. 蛋白质组学质谱数据预处理技术综述［J］. 中国生物医学工程学报, 2009, 28(3): 469-475.