基于非线性系统分析与动态复杂网络的医学数据分析与集成
|
摘要
用非线性系统方法与复杂网络对医学数据进行建模,是研究方法从独立法与隔离法到整体法与系统法的重大转变。相比传统的专家经验与线性分析方法,非线性方法对刻画内部关系错综复杂的非线性医学对象方面具有更好的适应性。
本文以非线性系统方法为理论基础,以相空间重构为主要技术手段,针对以下两类医学数据:癫痫患者的EEG脑电数据以及胃癌患者的SELDI-TOF血清蛋白质质谱数据进行非线性分析和分类模型建立,并取得了一系列有价值的成果。本文主要做了如下方面工作:
(1)、以癫痫患者EEG数据为对象进行非线性系统分析与建模。从工程实现的角度出发,本文建立了一体化处理管道——包括数据筛选、预处理、降维、相空间重构、分类模型建立、计算量优化,使得本文提出的建模方法具有完整性、鲁棒性与实时性。
具体而言,本文通过替代数据法对多通道数据进行非线性特征筛选,因子分析法对数据进行降维,进而应用改进的多通道相空间重构技术重构脑电信号奇异吸引子,并通过奇异吸引子关联维数成功建立癫痫期和癫痫间期EEG数据的分类模型。本文同时详细讨论且优化了关联维工程计算的时间复杂度,以满足关联维实时在线计算的需要。
(2)、针对当前蛋白质谱生物标记建模方法的不足,本文提出了基于非线性与系统理论的蛋白质质谱数据建模与判别新思路。
本文对胃癌患者SELDI-TOF血清蛋白质质谱数据进行建模与判别。以相空间重构为主要方法,对20例正常个体和20例癌症个体的质谱数据分别在两个数据区段进行相空间重构,并以这两个区段的关联维数为输入建立线性分类模型,验证了该模型优于单个蛋白生物标记的分类模型。
(3)、在高维复杂医学数据建模领域引入动态复杂网络建模思想。并试着提出了针对超高维的、有连续性的医学数据进行复杂网络建模的一种可行性方法及可能的后续分析思路。
The nonlinear and systematic methods, which describe their research target from a holistic and systematic point of view, show better adaptability when modeling the high-dimensional and complex medical data.
In this paper, two types of data: EEG data of epilepsies patients and SELDI-TOF serum protein mass spectrometry data of patients with gastric cancer are processed based on the nonlinear theory and the technology of phase space reconstruction. Some valuable results were obtained from the data processing and model building procedure. The major works involved in this paper are as follows:
(1) This paper presented the analysis and modeling of a nonlinear system based on the EEG data of epilepsies patients. From the engineering implementation point of view, this paper established a uniform processing channel, including data filtering, preprocessing, dimension reduction, phase space reconstruction, classifier modeling and computational optimization, which make the method complete, robust and real-time.
More specifically, in this paper multi-channel data have been filtered with nonlinear characteristics by method of surrogate data. Factor analysis is used for dimension reduction, Improved multi-channel phase space reconstruction technology is used for reconstruction of the EEG strange attractor. Furthermore, the classifier model of EEG data in illness-period and inter-illness-period has been constructed by the correlation dimension of singular attractors. In the mean time a comprehensive discussion and optimization have been finished on the time-complexity of the correlation dimension computation, in order to satisfy the requirement of real time on-line computation.
(2) Focusing on the insufficiency of the current spectra] modeling of protein biomarkers, this paper proposed a new method for protein mass spectrometry data modeling and discrimination based on the nonlinear theory and systematic methods. This paper carried out the modeling and classification of the SELDI-TOF serum protein mass spectrometry data of patients with gastric cancer. Using phase space reconstruction, the data from 20 normal samples and 20 cancer samples are reconstructed in 2 specific data ranges, based on which a linear classifier model is established. The result verified the superiority over the classifier model of single protein biomarkers.
(3) The concept of dynamic complex network modeling has been introduced to the modeling of high-dimensional, complex medical data. A feasibility study and further work have been proposed according to the complex network modeling of high-dimensional, continuous medical data.
本文以非线性系统方法为理论基础,以相空间重构为主要技术手段,针对以下两类医学数据:癫痫患者的EEG脑电数据以及胃癌患者的SELDI-TOF血清蛋白质质谱数据进行非线性分析和分类模型建立,并取得了一系列有价值的成果。本文主要做了如下方面工作:
(1)、以癫痫患者EEG数据为对象进行非线性系统分析与建模。从工程实现的角度出发,本文建立了一体化处理管道——包括数据筛选、预处理、降维、相空间重构、分类模型建立、计算量优化,使得本文提出的建模方法具有完整性、鲁棒性与实时性。
具体而言,本文通过替代数据法对多通道数据进行非线性特征筛选,因子分析法对数据进行降维,进而应用改进的多通道相空间重构技术重构脑电信号奇异吸引子,并通过奇异吸引子关联维数成功建立癫痫期和癫痫间期EEG数据的分类模型。本文同时详细讨论且优化了关联维工程计算的时间复杂度,以满足关联维实时在线计算的需要。
(2)、针对当前蛋白质谱生物标记建模方法的不足,本文提出了基于非线性与系统理论的蛋白质质谱数据建模与判别新思路。
本文对胃癌患者SELDI-TOF血清蛋白质质谱数据进行建模与判别。以相空间重构为主要方法,对20例正常个体和20例癌症个体的质谱数据分别在两个数据区段进行相空间重构,并以这两个区段的关联维数为输入建立线性分类模型,验证了该模型优于单个蛋白生物标记的分类模型。
(3)、在高维复杂医学数据建模领域引入动态复杂网络建模思想。并试着提出了针对超高维的、有连续性的医学数据进行复杂网络建模的一种可行性方法及可能的后续分析思路。
The nonlinear and systematic methods, which describe their research target from a holistic and systematic point of view, show better adaptability when modeling the high-dimensional and complex medical data.
In this paper, two types of data: EEG data of epilepsies patients and SELDI-TOF serum protein mass spectrometry data of patients with gastric cancer are processed based on the nonlinear theory and the technology of phase space reconstruction. Some valuable results were obtained from the data processing and model building procedure. The major works involved in this paper are as follows:
(1) This paper presented the analysis and modeling of a nonlinear system based on the EEG data of epilepsies patients. From the engineering implementation point of view, this paper established a uniform processing channel, including data filtering, preprocessing, dimension reduction, phase space reconstruction, classifier modeling and computational optimization, which make the method complete, robust and real-time.
More specifically, in this paper multi-channel data have been filtered with nonlinear characteristics by method of surrogate data. Factor analysis is used for dimension reduction, Improved multi-channel phase space reconstruction technology is used for reconstruction of the EEG strange attractor. Furthermore, the classifier model of EEG data in illness-period and inter-illness-period has been constructed by the correlation dimension of singular attractors. In the mean time a comprehensive discussion and optimization have been finished on the time-complexity of the correlation dimension computation, in order to satisfy the requirement of real time on-line computation.
(2) Focusing on the insufficiency of the current spectra] modeling of protein biomarkers, this paper proposed a new method for protein mass spectrometry data modeling and discrimination based on the nonlinear theory and systematic methods. This paper carried out the modeling and classification of the SELDI-TOF serum protein mass spectrometry data of patients with gastric cancer. Using phase space reconstruction, the data from 20 normal samples and 20 cancer samples are reconstructed in 2 specific data ranges, based on which a linear classifier model is established. The result verified the superiority over the classifier model of single protein biomarkers.
(3) The concept of dynamic complex network modeling has been introduced to the modeling of high-dimensional, complex medical data. A feasibility study and further work have been proposed according to the complex network modeling of high-dimensional, continuous medical data.
引文
[1]Goldberger AL,Rigney DR,West BJ.Chaos and fractals in human physiology.Sci Am 1990;262:42-49.
[2]Bassingthwaighte JB,Liebovitch LS,West BJ.Fractal physiology.New York:Oxford University Press,1994.
[3]Glass L,Mackey MC.From clocks to chaos:the rhythms to life.Princeton:University Press,1988.
[4]Rigney DR,Goldberger AL.Nonlinear mechanics of the beart's swinging during pericardial effusion.Am Physiol 1989;257:H1292-305.
[5]A.C.K.Soong.Evidence of chaotic dynamics underlying the human alpha-rhythm electroencephalogram.Biological Cybernetics 1989;62:55-62.
[6]J.Roschke.The dimensionality of human's electroencephalogram during sleep.Biological Cybernetics 1991;64:307-313.
[7]A.Babloyantz and A.Destexhe.Is the normal heart a periodic oscillator? Biological Cybernetics 1988:58:203-211.
[8]Bifurcations and Intrinsic Chaotic and 1/f Dynamics in an Isolated Perfused Rat Heart.Biological Cybernetics.1989:61:371-378.
[9]Goldberger AL.Fractal mechanisms in the electrophysiology of the heart[J].IEEE Eng Med Biol Mag.,1992,11(2):47-52
[10]Goldberger AL,Rigney DR,West BJ.Chaos and fractals in human physiology.Sci Am.,1990,262:42-49
[11]Goldberger AL,Non-linear dynamics for clinicians:Chaos theory,fractals,and complexity at the bedside.The Lancet 1996:347:1312-14.
[12]Nader Rifal,Michael A Gillette,Steven A Carr:Protein biomarker discovery and validation:the long and uncertain path to clinical utility.Nature Biotechnology.Vol 24,No.8.August 2006,971-983.
[13]KA Baggerly.JS Morris,KR Coombers:Reproducibility of SELDI-TOF Protein Patterns in Serum Comparing Data Sets from Different Experiments.Bioinfomatics Advance Access published January 29,2004.
[14]Luciano da F.Costa,Francisco A.Rodrigues and Alexandre S.Cristino:Complex networks:The key to system biology.Genetics and Molecular Biology,31,3,591-601(2008).
[15]Voglstein B,Lane D and Levine AJ(2000) Surfing the p53 network.Nature 408:307-310.
[16]Franklin D,Godfrey V,O'Brien D,Deng C and Xiong Y(2000) Functional collaboration between different cyclin-dependent kinase inhibitors suppresses tomor growth with distinct tissue specificity.Mol Cell Biol 20:6147-6158.
[17]Berg J,Lassing M and Wagner A(2004) Structure and evolution of protein interaction networks:A statistical model for link dynamics and gene duplications.BMC Evol Biol 4:51.
[18]Giot L,Bader J,Brouwer C,Chaudhuri A,Kuang B,Li Y,Hao Y,Ooi C,Godwin B,Vitols E,et al.(2003) A protein interaction map of Drosophila melanogaster.Science 302:1727-1736.
[19]Rain J,Selig L,De Reuse H,Battaglia V,Reverdyy C,Simon S,Lenzen G,Peter F,Wojcik J,Schacchter V,et al.(2001) The protein-protein interaction map of Helicobater pylori.Nature 409:211-215.
[20]Duesberg Peter:Chromosomal chaos and cancer.Scientific American,Vol 296,52-59,2007.
[21]Barabasi AL and Albert R(1999) Emergence of scaling in random networks.Science 286:509-512.
[22]Diestel R(2000) Graph Theory.Springer-Verlag,Heidelberg,431 pp.
[23]Pijn,J.P,Van Neerven,J.Noest,A.Lopes da Silva,Chaos or noise in EEG signals:dependence on state and brain site.Electroenceph.clin.Neurophysiol,1991,79L371-381.
[24]Gorman.M:Classification of high-demensional chaotic dynamics using power spectra.In:B.Jansen and M.Brandt(Eds.),Nonlinear Dynamical Analysis of the EEG.World Scientific,Singapore,1993.pp 3-12.
[25]Molinari.L and Dumermuth.G:Once more:dimension and Lyapunov exponents for the human EEG.In:B.Jansen and M.Brandt(Eds.):Nonlinear Dynamical Analysis of the EEG.World Scientific,Singapore,1993,pp 140-165.
[26]Jurgen Fell,Joachim Roschke,Klaus Mann,Cornelius Schaffner:Discrimination of sleep stages:a comparison between spectral and nonlinear EEG measures.Electroencephalography and clinical Neurophysiology 98(1996):401-410.
[27]J.Martinerie,C.Adam,M.Le Van Quyen:Epileptic seizures can be anticipated by non-linear analysis.Nature Medicine.Vol.4,No.10,October 1998:1173-1176.
[28]Theiler J,Rapp P.E:RE-examination of the evidence for low dimentional nonlinear structure in the human electroencephalogram.EEG ClinNeurophysiol,1996,98:213-222.
[29]Jean-Philippe Lachaux,Laurent Pezard,Line Garnero:Spatial Extension of Brain Activity Fools the Single-Channel Reconstruction of EEG Dynamics.Human Brain Mapping 5:26-47(1997).
[30]S.A.R.B.Rombouts,R.W.M.Keunen,C.J.Stam:Investigation of nonlinear structure in multichannel EEG.Physics Letters A 202(1995) 352-358.
[31]张庆平,卢广文:癫痫多导脑电非线性分析.第一军医大学学报,2005;25(3):345-348.
[32]David A.Rew:Tumour biology,chaos and non-linear dynamics.European Journal of Surgical Oncology 1999;25;86-89.
[33]Mattfeldt T.:Nonlinear deterministic analysis of tissue texture:A stereological study on mastopathic and mamary cancer tissue using chaos theory.Journal of microscopy-oxford Vol 185,47-66,Jan,1997
[34]Roland Sedivy and Robert M.Mader:Fractals,Chaos,and Cancer:Do They Coincide? Cancer Investigation,15(6),601-607(1997)
[35]Joerg Peter,Menber,IEEE,and Wolfhard Semmler:Integrating Kinetic Models for Simulating Tumor Growth in Monte Carlo Simulation of ECT Systems.IEEE Transactions on nuclear science,Vol 51,No.5,October 2004
[36]Yuri Mansury,Thomas S.Deiboeck:Simulating the time series of a selected gene expression profile in an agent-based tumor model.Physica D 196(2004) 193-204
[37]Schena M.Shalon D.Davis RW and Brown PO(1995):Quantitative monitoring of gene expressiong patterns with a complementary DNA microarray.Science 270:467-470.
[38]Eleftherios P.Diamandis:Mass Spectrometry as a Dianostic and a Cancer Biomarker Discovery Tool---Opportunities and Potential Limications.Molecular &Cellular Proteomics 3:367-378,2004.
[39]Wulfkuhle J D,Liotta L A,Petricoin E F.Proteomic applications for the early detection of cancer.Natrue Reviews Cancer,2003,3(4):267-275
[40]Petricoin EF,Ardekani AM,Hitt BA,Levine PJ,Fusaro VA,Steinberg SM,Mills GB,Simone C,Fishman DA,Kohn EC,Liotta LA.Use of proteomic patterns in serum to identify ovarian cancer.Lancet,2002,359(9306):572-577
[41]Sridhar Ramaswamy,Pablo Tamayo,Ryan Rifkin,et al:Multiclass cancer diagnosis using tumor gene expressioin signatures.Proceedings of the National Academy of Sciences of the United States of America.December 18,2001,Vol.98,No.26,15149-15154.
[42]Huerta A.M,Salgado H,Thieffry D and Collado Vides J(1998):A database on transcriptional regulation in Eschericahia coli.Nucleic Acids Res 26:55-59.
[43]Ihmels J,Friedlander G,Bergmann S,Saring O,Ziv Y and Barkai N(2002):Revealing modular organization in the yeast transcriptional network.Nat Genet 31:370-377.
[44]N.H.Packard,J.P.Crutchfield.et al:Geometry from a Time Series.Phy.Rev.Lett,September 1980,Vol 45,No.9:712-716.
[45]Floris Takens:Detecting strange attractors in turbulence.Lecture Notes in Mathematics,Berlin:Springer,1981,898:366-381.
[46]Buzug T,Reimers T,Pfister G.Optimal reconstruction of strange attractors from purely geometrical arguments.Europhys.Lett.,1990,13:605-607
[47]Zhenzhou Wang,Xinbao Ning,Yu Zhang and Gonghuan Du.Nonlinear dynamic characteristics analysis of synchronous 12-lead ECG signals.IEEE Eng Med Biol Mag.,2000,19(5):110-115
[48]Fraser AM,Swinney HL.Independent coordinates for strange attractors from mutual information.Physical Review A,1986,33:1134-1140
[49]Kennel M B,Brown R,Abarbanel H D,et al.Determining embedding dimension for phase-space reconstruction using a geometrical construction.Physical Review A.1992,45(6):3403-4311.
[50]Cao Liangyue.Practical method for determining the minimum embedding dimension of a scalar time series.Physica D,1997,110(5):43-50
[51]HS Kim,R.Eykholt,JD Salas.Nonlinear dynamics delay times and embedding windows.Physica D,1999,127:48-60
[52]A.M.Albano,J.Muench and C.Schwartz:Singular-value decomposition and Grassberger-Procaccia algorithm.Phys.Rev.A 38,3017-3026.
[53]J.Theiler,Phys.Rev.A 34,2427-2432(1986).
[54]A.R.Osborne and A.Provenzale,Physica(Amsterdam) 35D,357-381(1989).
[55]Ilya Levner:Proteomic Pattern Recognition.,University of Alberta,2004.
[56]Trevor Hastie Robert Tibshirani Jerome Friedman著,范明,柴玉梅等译:统计学习基础——数据挖掘,推理与预测,电子工业出版社,2004.
[57]Donoho,D.L.and Johnstone,I.M.Adapting to UnknownSmoothness via Wavelet Shrinkage,Journal of the AmericanStatistical Association,90,(1995),1200-1224.
[58]Coombes,K.R.,Fritsche,H.A.Jr,Clarke,C.,Chen,J.N.,Baggerly,K.,A.,Morris,J.S.,Xiao,L.C.,Hung,M.C.,andKuerer,H.M.Quality control and peak finding for proteomicsdata collected from nipple aspirate fluid by surface-enhanced laser desorption and ionization.Clin Chem.49,10(2003),1615-1623.
[59]Neal Jeffries:Algorithms for alignment of mass spectrometry proteomic data BIOINFORMATICS Vol.21 no.14 2005,pages 3066-3073
[60]吕金虎,陆君安,等.混沌时间序列分析及其应用.武汉:武汉大学出版社,2002.1-92
[61]Rosenstein,M.T.,Collins,J.J.,De Luca,C.J:Reconstruction expansion as a geometry-based framework for choosing proper delay times.Physica D 73,82-98(1994)
[62]樊重俊,王浣尘:度量两个序列非线性相关性的一种方法,信息与控制,Vol.27.No.3,June,1998:185-188
[2]Bassingthwaighte JB,Liebovitch LS,West BJ.Fractal physiology.New York:Oxford University Press,1994.
[3]Glass L,Mackey MC.From clocks to chaos:the rhythms to life.Princeton:University Press,1988.
[4]Rigney DR,Goldberger AL.Nonlinear mechanics of the beart's swinging during pericardial effusion.Am Physiol 1989;257:H1292-305.
[5]A.C.K.Soong.Evidence of chaotic dynamics underlying the human alpha-rhythm electroencephalogram.Biological Cybernetics 1989;62:55-62.
[6]J.Roschke.The dimensionality of human's electroencephalogram during sleep.Biological Cybernetics 1991;64:307-313.
[7]A.Babloyantz and A.Destexhe.Is the normal heart a periodic oscillator? Biological Cybernetics 1988:58:203-211.
[8]Bifurcations and Intrinsic Chaotic and 1/f Dynamics in an Isolated Perfused Rat Heart.Biological Cybernetics.1989:61:371-378.
[9]Goldberger AL.Fractal mechanisms in the electrophysiology of the heart[J].IEEE Eng Med Biol Mag.,1992,11(2):47-52
[10]Goldberger AL,Rigney DR,West BJ.Chaos and fractals in human physiology.Sci Am.,1990,262:42-49
[11]Goldberger AL,Non-linear dynamics for clinicians:Chaos theory,fractals,and complexity at the bedside.The Lancet 1996:347:1312-14.
[12]Nader Rifal,Michael A Gillette,Steven A Carr:Protein biomarker discovery and validation:the long and uncertain path to clinical utility.Nature Biotechnology.Vol 24,No.8.August 2006,971-983.
[13]KA Baggerly.JS Morris,KR Coombers:Reproducibility of SELDI-TOF Protein Patterns in Serum Comparing Data Sets from Different Experiments.Bioinfomatics Advance Access published January 29,2004.
[14]Luciano da F.Costa,Francisco A.Rodrigues and Alexandre S.Cristino:Complex networks:The key to system biology.Genetics and Molecular Biology,31,3,591-601(2008).
[15]Voglstein B,Lane D and Levine AJ(2000) Surfing the p53 network.Nature 408:307-310.
[16]Franklin D,Godfrey V,O'Brien D,Deng C and Xiong Y(2000) Functional collaboration between different cyclin-dependent kinase inhibitors suppresses tomor growth with distinct tissue specificity.Mol Cell Biol 20:6147-6158.
[17]Berg J,Lassing M and Wagner A(2004) Structure and evolution of protein interaction networks:A statistical model for link dynamics and gene duplications.BMC Evol Biol 4:51.
[18]Giot L,Bader J,Brouwer C,Chaudhuri A,Kuang B,Li Y,Hao Y,Ooi C,Godwin B,Vitols E,et al.(2003) A protein interaction map of Drosophila melanogaster.Science 302:1727-1736.
[19]Rain J,Selig L,De Reuse H,Battaglia V,Reverdyy C,Simon S,Lenzen G,Peter F,Wojcik J,Schacchter V,et al.(2001) The protein-protein interaction map of Helicobater pylori.Nature 409:211-215.
[20]Duesberg Peter:Chromosomal chaos and cancer.Scientific American,Vol 296,52-59,2007.
[21]Barabasi AL and Albert R(1999) Emergence of scaling in random networks.Science 286:509-512.
[22]Diestel R(2000) Graph Theory.Springer-Verlag,Heidelberg,431 pp.
[23]Pijn,J.P,Van Neerven,J.Noest,A.Lopes da Silva,Chaos or noise in EEG signals:dependence on state and brain site.Electroenceph.clin.Neurophysiol,1991,79L371-381.
[24]Gorman.M:Classification of high-demensional chaotic dynamics using power spectra.In:B.Jansen and M.Brandt(Eds.),Nonlinear Dynamical Analysis of the EEG.World Scientific,Singapore,1993.pp 3-12.
[25]Molinari.L and Dumermuth.G:Once more:dimension and Lyapunov exponents for the human EEG.In:B.Jansen and M.Brandt(Eds.):Nonlinear Dynamical Analysis of the EEG.World Scientific,Singapore,1993,pp 140-165.
[26]Jurgen Fell,Joachim Roschke,Klaus Mann,Cornelius Schaffner:Discrimination of sleep stages:a comparison between spectral and nonlinear EEG measures.Electroencephalography and clinical Neurophysiology 98(1996):401-410.
[27]J.Martinerie,C.Adam,M.Le Van Quyen:Epileptic seizures can be anticipated by non-linear analysis.Nature Medicine.Vol.4,No.10,October 1998:1173-1176.
[28]Theiler J,Rapp P.E:RE-examination of the evidence for low dimentional nonlinear structure in the human electroencephalogram.EEG ClinNeurophysiol,1996,98:213-222.
[29]Jean-Philippe Lachaux,Laurent Pezard,Line Garnero:Spatial Extension of Brain Activity Fools the Single-Channel Reconstruction of EEG Dynamics.Human Brain Mapping 5:26-47(1997).
[30]S.A.R.B.Rombouts,R.W.M.Keunen,C.J.Stam:Investigation of nonlinear structure in multichannel EEG.Physics Letters A 202(1995) 352-358.
[31]张庆平,卢广文:癫痫多导脑电非线性分析.第一军医大学学报,2005;25(3):345-348.
[32]David A.Rew:Tumour biology,chaos and non-linear dynamics.European Journal of Surgical Oncology 1999;25;86-89.
[33]Mattfeldt T.:Nonlinear deterministic analysis of tissue texture:A stereological study on mastopathic and mamary cancer tissue using chaos theory.Journal of microscopy-oxford Vol 185,47-66,Jan,1997
[34]Roland Sedivy and Robert M.Mader:Fractals,Chaos,and Cancer:Do They Coincide? Cancer Investigation,15(6),601-607(1997)
[35]Joerg Peter,Menber,IEEE,and Wolfhard Semmler:Integrating Kinetic Models for Simulating Tumor Growth in Monte Carlo Simulation of ECT Systems.IEEE Transactions on nuclear science,Vol 51,No.5,October 2004
[36]Yuri Mansury,Thomas S.Deiboeck:Simulating the time series of a selected gene expression profile in an agent-based tumor model.Physica D 196(2004) 193-204
[37]Schena M.Shalon D.Davis RW and Brown PO(1995):Quantitative monitoring of gene expressiong patterns with a complementary DNA microarray.Science 270:467-470.
[38]Eleftherios P.Diamandis:Mass Spectrometry as a Dianostic and a Cancer Biomarker Discovery Tool---Opportunities and Potential Limications.Molecular &Cellular Proteomics 3:367-378,2004.
[39]Wulfkuhle J D,Liotta L A,Petricoin E F.Proteomic applications for the early detection of cancer.Natrue Reviews Cancer,2003,3(4):267-275
[40]Petricoin EF,Ardekani AM,Hitt BA,Levine PJ,Fusaro VA,Steinberg SM,Mills GB,Simone C,Fishman DA,Kohn EC,Liotta LA.Use of proteomic patterns in serum to identify ovarian cancer.Lancet,2002,359(9306):572-577
[41]Sridhar Ramaswamy,Pablo Tamayo,Ryan Rifkin,et al:Multiclass cancer diagnosis using tumor gene expressioin signatures.Proceedings of the National Academy of Sciences of the United States of America.December 18,2001,Vol.98,No.26,15149-15154.
[42]Huerta A.M,Salgado H,Thieffry D and Collado Vides J(1998):A database on transcriptional regulation in Eschericahia coli.Nucleic Acids Res 26:55-59.
[43]Ihmels J,Friedlander G,Bergmann S,Saring O,Ziv Y and Barkai N(2002):Revealing modular organization in the yeast transcriptional network.Nat Genet 31:370-377.
[44]N.H.Packard,J.P.Crutchfield.et al:Geometry from a Time Series.Phy.Rev.Lett,September 1980,Vol 45,No.9:712-716.
[45]Floris Takens:Detecting strange attractors in turbulence.Lecture Notes in Mathematics,Berlin:Springer,1981,898:366-381.
[46]Buzug T,Reimers T,Pfister G.Optimal reconstruction of strange attractors from purely geometrical arguments.Europhys.Lett.,1990,13:605-607
[47]Zhenzhou Wang,Xinbao Ning,Yu Zhang and Gonghuan Du.Nonlinear dynamic characteristics analysis of synchronous 12-lead ECG signals.IEEE Eng Med Biol Mag.,2000,19(5):110-115
[48]Fraser AM,Swinney HL.Independent coordinates for strange attractors from mutual information.Physical Review A,1986,33:1134-1140
[49]Kennel M B,Brown R,Abarbanel H D,et al.Determining embedding dimension for phase-space reconstruction using a geometrical construction.Physical Review A.1992,45(6):3403-4311.
[50]Cao Liangyue.Practical method for determining the minimum embedding dimension of a scalar time series.Physica D,1997,110(5):43-50
[51]HS Kim,R.Eykholt,JD Salas.Nonlinear dynamics delay times and embedding windows.Physica D,1999,127:48-60
[52]A.M.Albano,J.Muench and C.Schwartz:Singular-value decomposition and Grassberger-Procaccia algorithm.Phys.Rev.A 38,3017-3026.
[53]J.Theiler,Phys.Rev.A 34,2427-2432(1986).
[54]A.R.Osborne and A.Provenzale,Physica(Amsterdam) 35D,357-381(1989).
[55]Ilya Levner:Proteomic Pattern Recognition.,University of Alberta,2004.
[56]Trevor Hastie Robert Tibshirani Jerome Friedman著,范明,柴玉梅等译:统计学习基础——数据挖掘,推理与预测,电子工业出版社,2004.
[57]Donoho,D.L.and Johnstone,I.M.Adapting to UnknownSmoothness via Wavelet Shrinkage,Journal of the AmericanStatistical Association,90,(1995),1200-1224.
[58]Coombes,K.R.,Fritsche,H.A.Jr,Clarke,C.,Chen,J.N.,Baggerly,K.,A.,Morris,J.S.,Xiao,L.C.,Hung,M.C.,andKuerer,H.M.Quality control and peak finding for proteomicsdata collected from nipple aspirate fluid by surface-enhanced laser desorption and ionization.Clin Chem.49,10(2003),1615-1623.
[59]Neal Jeffries:Algorithms for alignment of mass spectrometry proteomic data BIOINFORMATICS Vol.21 no.14 2005,pages 3066-3073
[60]吕金虎,陆君安,等.混沌时间序列分析及其应用.武汉:武汉大学出版社,2002.1-92
[61]Rosenstein,M.T.,Collins,J.J.,De Luca,C.J:Reconstruction expansion as a geometry-based framework for choosing proper delay times.Physica D 73,82-98(1994)
[62]樊重俊,王浣尘:度量两个序列非线性相关性的一种方法,信息与控制,Vol.27.No.3,June,1998:185-188