基因组尺度高信息量RNA干扰筛选数据分析:一类系统生物学应用中若干模式识别问题的研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
控制论、系统论思想与模式识别相关方法广泛参与诸多交叉学科的研究。控制论、系统论可以指导对各种实际问题的认知,模式识别相关方法则构成了具体的解决方案。本文将控制论、系统论与模式识别相关方法应用于一类系统生物学研究。具体的,以基因在细胞形态变化中的调控作用为主要研究对象,以在果蝇培养细胞种系中进行的大尺度高信息量RNA干扰筛选(RNAi HCS)为应用背景,我们分析并解决了RNAi HCS数据分析中的一系列问题,包括细胞形态表现型在线发现、表现型在线建模与确认、针对不同表现型的特征选择与细胞分类、综合单个细胞分类结果的基因功能建模等。我们将本文设计的一系列方法组合为一套完整的数据分析流程,并协助生物学者对近200万单个细胞图像进行综合分析,提出了“细胞形态表现型具有定型化性质”的生物学假设。
     本文提出利用高斯混合模型对表现型建模,改进了利用间隔统计估计聚类个数的方法、设计了迭代表现型兼并流程以比较新数据集与已知表现型的异同、利用最小分类误差方法实现表现型模型在线更新,最终形成了在线表现型发现算法。这种方法随着新数据的不断产生辨认新颖表现型,并对其进行建模与确认。当前的RNAi HCS数据分析流程大多使用手工挑选的典型表现型及代表细胞作为训练集,但数据集规模的不断扩大使手工分析难以反映整个数据集的完整风貌,我们的方法有效的解决了这一问题。
     为了考察整个数据集中各个细胞与典型表现型的相似程度,我们设计了“支持向量机迭代特征消去-遗传算法”联合特征选择方法,利用精简的特征集合描述表现型形态并使用以高斯径向基函数为核函数的支持向量机进行细胞分类。根据支持向量机对每个细胞形态的分析,我们执行一系列质量控制、统计分析及数据筛选与整合操作,为针对每个基因的RNAi实验挑选出一个带有稳定形态特征的细胞群落;根据可重复性细胞群落的形态特征生成每个基因的量化形态分值,并利用聚类分析辨别在细胞形态变化中发挥不同作用的基因与基因家族。
     本文以控制论、系统论为指导,整个数据分析流程中综合运用多种模式识别、统计分析技术,形成了完整、高效的RNAi HCS数据分析流程。在数据分析方案设计中注重动态与静态分析的对立统一,实现了典型表现型在线发现与在线建模;注重利用统计学方法发掘微观与宏观层面的联系,系统化处理单个细胞形态作为分析基因功能的基础;注重对单一层面分析结果的升华,努力通过特定应用的分析结果掌握普遍规律,提出并初步验证了细胞形态表现型具有定型化特点这一假设。
Cybernetics, systems theory and pattern recognition theory and methodologies are broadly applied to interdesciplinary research. In the context of different applications, cybernetics and systems theory can help dissecting various research topics while pattern recognition technologies form the workflow of solving specific problems. In this thesis, cybernetics, systems theory and pattern recognition theory and methodologies were applied to systems biology research. Specifically, in the context of large scale high content RNAi screening (RNAi HCS) aiming at constructing local regulatory network for Drosophila cell shape change, a series of challenges confronting RNAi HCS data analysis were analyzed and solved. We proposed original solutions for online phenotype discovery, online modeling and validation of novel phenotypes, feature selection, cell classification and modeling of gene functions based on single cell morphology profile. The proposed methods were combined into a complete data analysis workflow, and handled a dataset of more than 2 million single cells. Based on the analysis results from real dataset, we helped biologists propose a biological hypothesis regarding the canalization of cell morphology.
     At present, most RNAi HCS data analysis workflows utilize typical phenotypes and cells identified from expert ground truth labeling as basis of gene function research. However, the growing size of dataset makes it infeasible to cover the property of whole dataset using manually picked training set. We improved gap statistics, a cluster number estimation and cluster validation method; designed iterative phenotype merging, a strategy comparing newly generated dataset and existing phenotypes; used Gaussian mixture model to describe each phenotype and applied minimum classification error method to do online model update; we combined these components and proposed an original online phenotype discovery workflow to discover, model and validate novel morphological dataset as the dataset extended.
     In order to compare cell morphology with typical phenotypes, we combined "Support vector machine-Recursive feature elimination (SVM-RFE)" and "Genetic Algorithm based on SVM" to form a feature selection scheme. Using the informative feature subsets and SVM with Gaussian Radial Basis function as kernel functions, we quantified the similarity of morphology between single cell and typical phenotypes. Based on the cell classification results, we carried out a series of quality control, statistical analysis, data filtering and consolidation; picked up a group of significantly repeatable cell population to represent the result of RNAi treatment targeting each gene; the quantitative morphology signatures for each single gene are generated based on those cell populations, and we used cluster analysis on those signatures to identify gene families with different functions in regulating cell shape change.
     Guided by cybernetics and systems theory, the whole data analysis workflow implemented various state-of-the-art technologies of pattern recognition and statistical analysis, and showed the capability of automatic data analysis in large scale RNAi HCS. We combined dynamic and static analysis and realized online phenotype discovery, modeling and validation; the relationships between information from micro- and macro- level phenomena were checked and single cell morphology profile were utilized to model gene function; the data analysis results on specific project contributed to the understanding of the general law underlying cell morphology change, and we proposed and validated the hypothesis regarding canalization property of cell morphology based on our data analysis using real RNAi HCS dataset.
引文
1.周春晖,化工过程控制原理(第二版).1998,北京:化学工业出版社.
    2.Bailey,K.,Fifty years of systems science:further reflections.Systems Research and Behavioral Science,2005.22:p.355-361.
    3.Bishop,C.,Pattern Recognition and Machine Learning(Information Science and Statistics).2006:Springer.
    4.边肇祺,张学工,模式识别(第二版).2004,北京:清华大学出版社.
    5.Sauer,U.,Heinemann,M.,Zamboni,N.,GENETICS:Getting Closer to the Whole Picture.2007.p.550-551.
    6.Noble,D.,The Music of Life:Biology beyond the genome.2006,Oxford:Oxford University Press.
    7.Chahrour,M.,Jung,S.Y.,Shaw,C.,Zhou,X.,Wang,S.T.C.,Qin,J.,Zoghbi,H.Y.,MeCP2,a Key Contributor to Neurological Disease,Activates and Represses Transcription.2008.p.1224-1229.
    8.Banerjea,A.,U,M.-J.,Bauer,G.,Remling,L.,Lee,N.-S.,Rossi,J.,Akkina,R.,Inhibition of HIV-1 by Lentiviral Vector-Transduced siRNAs in T Lymphocytes Differentiated in SCID-hu Mice and CD34+ Progenitor Cell-Derived Macrophages.Mol Ther,2003.8(1):p.62-71.
    9.Li,M.-J.,Bauer,G.,Michienzi,A.,Yee,J.-K.,Lee,N.-S.,Kim,J.,Li,S.,Castanotto,D.,Zaia,J.,Rossi,J.J.,Inhibition of HIV-1 Infection by Lentiviral Vectors Expressing pol Ⅲ-promoted anti-HIV RNAs.Mol Ther,2003.8(2):p.196-206.
    10.Fire,A.,Xu,S.,Montgomery,M.K.,Kostas,S.A.,Driver,S.E.,Mello,C.C.,Potent and specific genetic interference by double-stranded RNA in Caenorhabditis elegans.Nature,1998.391(6669):p.806-811.
    11.Echeverri,C.J.Perrimon,N.,High-throughput RNAi screening in cultured cells:a user's guide.Nat Rev Genet,2006.7(5):p.373-384.
    12.Sharma,S.Rao,A.,RNAi screening:tips and techniques.Nat Immunol,2009.10(8):p.799-804.
    13.Castanotto,D.Rossi,J.J.,The promises and pitfalls of RNA-interference-based therapeutics.Nature,2009.457(7228):p.426-433.
    14.NIH.ClinicalTrials.gov.[cited;Available from:http://clinicaltrials.gov/ct2/search.
    15.Kaiser,P.K.,Antivascular Endothelial Growth Factor Agents and Their Development:Therapeutic Implications in Ocular Diseases.American Journal of Ophthalmology,2006.142(4):p.660-668.e1.
    16.McCaffrev,A.P.,Nakai,H.,Pandev,K.,Huang,Z.,Salazar,F.H.,Xu,H.,Wieland,S.F.,Marion,P.L.,Kay,M.A.,Inhibition of hepatitis B virus in mice by RNA interference.Nat Biotech,2003.21(6):p.639-644.
    17.Xu,Z.Xia,X.G.,RNAi therapy:Dominant disease gene gets silenced.Gene Ther,2005.12(15):p.1159-1160.
    18.Lopez,J.C.,ALS meets RNAi.Nat Rev Neurosci,2005.6(4):p.266-266.
    19.Derek,W.B.Mark,E.D.,Impact of tumor-specific targeting and dosing schedule on tumor growth inhibition ofter intravenous administration of siRNA-containing nanoparticles.2008.p.975-985.
    20.Heidel,J.D.,Liu,J.Y.-C.,Yen,Y.,Zhou,B.,Heale,B.S.E.,Rossi,J.J.,Bartlett,D.W.,Davis,M.E.,Potent siRNA Inhibitors of Ribonucleotide Reductose Subunit RRM2 Reduce Cell Proliferation In vitro and In viva.2007.p.2207-2215.
    21.O'Neill,G.,Australia tackles bird flu using RNAi.Nat Biotech,2007.25(6):p.605-606.
    22.Tompkins,S.M.,Lo,C.-Y.,Tumpey,T.M.,Epstein,S.L.,Protection against lethal influenza virus challenge by RNA interference in vivo.2004.p.8682-8686.
    23.Grimm,D.,Streetz,K.L.,Jopling,C.L.,Storm,T.A.,Pandey,K.,Davis,C.R.,Marion,P.,Salazar,F.,Kay,M.A.,Fatality in mice due to oversaturation of cellular microRNA/short hairpin RNA pathways.Nature,2006.441(7092):p.537-541.
    24.Zhou,H.,Xu,M.,Huang,Q.,Gates,A.T.,Zhang,X.D.,Castle,J.C.,Stec,E.,Ferrer,M.,Strulovici,B.,Hazuda,D.J.,Espeseth,A.S.,Genome-Scale RNAi Screen for Host Factors Required.for HIV Replication.2008.4(5):p.495-504.
    25.Bakal,C.,Linding,R.,Llense,F.,Heffern,E.,Martin-Blanco,E.,Pawson,T.,Perrimon,N.,Phosphorylation Networks Regulating JNK Activity in Diverse Genetic Backgrounds.2008.p.453-456.
    26.Luo,J.,Emanuele,M.J.,Li,D.,Creighton,C.J.,Schlabach,M.R.,Westbrook,T.F.,Wang,K.-K.,Elledge,S.J.,A Genome-wide RNAi Screen Identifies Multiple Synthetic Lethal Interactions with the Ras Oncogene.2009.137(5):p.835-848.
    27.Reiter,L.,Potocki,L.,Chien,S.,Gribskov,M.,Bier,E.,A systematic analysis of human disease-associated gene sequences in Drosophilia melanogaster.Genome Research,2001.11(6):p.1114-1125.
    28.McManus,M.T.,Haines,S.S.,Dillon,C.P.,Whitehurst,C.E.,van Parijs,L.,Chen,J.,Sharp,P.A.,Small Interfering RNA-Mediated Gene Silencing in T Lymphocytes.2002.p.5754-5760.
    29.Perrimon,N.Mathey-Prevot,S.,Applications of high-throughput RNAi screens to problems in cell and developmental biology.Genetics,2007.175:p.7-16.
    30.Friedman,A.Perrimon,N.,functional genomic RNAi screen,for novel regulators of RTK/ERK signaling.Nature,2006.444:p.230-234.
    31.Carpenter,A.E.Sabatini,D.M.,Systematic genome-wide screens of gene function.Nat Rev Genet,2004.5(1):p.11-22.
    32.Bakal,C.,Aach,J.,Church,G.,Perrimon,N.,Quantitative morphological signatures define local signaling networks regulating cell morphology.Science,2007.316:p.1753-1756.
    33.Perlman,Z.,Slack,M.,Feng,Y.,Mitchison,T.,Wu,L,Altschuler,S.,Multidimensional drug profiling by automated microscopy.Science,2004.306:p.1194-1198.
    34.O'Gorman,L.,Sanderson,A.C.,Preston,K.,A System,for Automated Liver Tissue Image Analysis:Methods and Results.Biomedical Engineering,IEEE Transactions on,1985.BME-32(9):p.696-706.
    35.Sahoo,P.K.,Soltani,S.,Wang,A.K.C.,Chen,Y.C.,A survey of thresholding techniques.1988,Academic Press Professional,Inc.p.233-260.
    36.Pun,T.,Entropic thresholding,a new approach.Computer graphics and image processing,1981.16(3):p.210-239.
    37.Zhou,X.,Li,F.H.,Yan,J.,Wang,S.T.C.,A Novel Cell Segmentation Method and Cell Phase Identification Using Markov Model.Information Technology in Biomedicine,IEEE Transactions on,2009.13(2):p.152-157.
    38.Joakim,L.,Carolina,W.,Ewert,B.,Alla,Z.,Image analysis for automatic segmentation of cytoplasms and classification of Racl activation.2004.p.22-33.
    39.Malpica,N.,de Solezano,C.,Vasquero J.J.,Santos,A.,Valcorba,I.,Garcia-sagredo,J.,del Pozo,F.,Applying watershed algorithms to the segmentation of clustered nuclei.1997.p.289-297.
    40.Carolina,W.,Joakim,L.,Mikael,V.,Ewert,B.,Lennart,B.,Algorithms for cytoplasm segmentation of fluorescence labelled cells.Analytical Cellular Pathology,2002.24(2):p.101-111.
    41.Kapur,R.,Giuliano,K.A.,Campana,M.,Adams,T.,Olson,K.,Jung,D.,Mrksich,M.,Vasudevan,C.,Taylor,D.L.,Streamlining the Drug Discovery Process by Integrating Miniaturization,High Throughput Screening,High Content Screening,and Automation on the CellChip~(TM) System.Biomedical Microdevices,1999.2:p.99-109.
    42.Jones,T.,Carpenter,A.,Golland,P.,Voronoi-Bosed Segmentation of Cells on Image Manifolds,in Computer Vision for Biomedical Image Applications.2005.p.535-543.
    43.Morelock MM,H.E.,Moran TJ,Heynen S,Laris C,Thieleking M,Akong M,Mikicl,Callaway S,DeLeon RP,Goodacre A,Zacharias D,Price JH.,Statistics of assay validation in high throughput cell imaging of nuclear factor koppoB nuclear tronslocotion.Assay Drug Development Technology 2005.3(5):p.483-499.
    44.Zhou,X.,Liu,K.Y.,Bradley,P.,Perrimon,N.,Wong,S.T.C.,Towards automated cellular image segmentation for RNAi genome-wide screening.Lecture Notes in Computer Science(MICCAI 2005),2005.3749:p.885-892.
    45.Xiong,G.,Zhou,X.,Ji,L.,Bradley,P.,Perrimon,N.,Wang,S.T.C.,Automated segmentation of Drosophila RNAi fluorescence cellular images using deformable models.IEEE Transactions on Circuit and Sysrems,2006.53:p.2415-2424.
    46.Li,F.H.,Zhou,X.,Wang,S.T.C.,An automated feedback system with the hybrid model of scoring and classification for solving over-segmentation problems in RNAi high content screening.Journal of Microscopy,2007.226(2):p.121-132.
    47.Yan,P.,Zhou,X.,Shah,M.,Wang,S.T.C.,Automatic segmentation of RNAi fluorescent cellular images with interaction model.IEEE Transactions on Information Technology in Biomedicine,2008.12(1):p.109-117.
    48.Tibshirani,R.,Walther,G.,Hastie,T.,Estimating the number of dusters in o dotoset via the gap statistic.Journal of Royal Statistics Society,2001.32(2):p.411-423.
    49.Sugar,C.James,G.,Finding the number of dusters in a dotoset:An informationtheoretic approach.Journal of the American Statistical Association,2003.98(463):p.750-763.
    50.Yan,M.Ye,K.,Determining the number of clusters using the weighted gap statistics.Biometrics,2007.63:p.1031-1037.
    51.Dudoit,S.Fridlyand,J.,A Prediction-based resompling method to estimate the number of dusters in o dotoset.Genome Biology,2002.3(7):p.research 0036.1-0036.21.
    52.Tibshirani,R.Walther,G.,Cluster validation by prediction strength.Journal of Computational and Graphical Statistics,2005.14(3):p.511-528.
    53.Guo,P.,Chen,P.,Lyu,M.,Cluster number selection for a small set of samples using the Bayesian Ying-Yong model.IEEE Transactions on Neural Networks,2002.13(3):p.757-763.
    54.Gangnon,R.Clayton,M.,Cluster detection using Bayes factors from overparometerized cluster models.Environmental and Ecological Statistics,2007.14:p.69-82.
    55.Bickel,D.,Robust cluster analysis of microorroy gene expression data with the number of clusters determined biologically.Bioinformatics,2003.19(7):p.818-824.
    56.Calinski,R.Harabasz,J.,A dendrite method for duster analysis.Communications in statistics,1974.3:p.1-27.
    57.Krzanowski,W.Lai,Y.,A criterion for determining the number of groups in a data set using sum of squares clustering.Biometrics,1985.44:p.23-34.
    58.Kaufman,L.Rousseeuw,P.,Finding groups in data:an introduction to cluster analysis.1990.
    59.Hartigan,J.,Clustering algorithms.1975,New York:Wiley.
    60.Dunn,J.,Well separated clusters and optimal fuzzy partitions.Journal of Cybern,1974.4:p.95-104.
    61.Davies,D.Bouldin,D.,A cluster separation measure.IEEE Transaction of Pattern Analysis and Machine Intellegence,1979.1(4):p.224-227.
    62.Hubert,L.Schultz,J.,Quadratic assignment as a general data-analysis strategy.British Journal of Mathematical and Statistical Psychologie,1976.29:p.190-241.
    63.Goodman,L.Kruskal,W.,Measures of associations for cross-validations.Journal of American Statistics Associan,1954.49:p.732-764.
    64.Jain,A.Dubes,R.,Algorithms,for clustering data.1988,Englewood Cliffs,NJ:Prentice-Hall.
    65.Jaccard,P.,The distribution of flora in the alpine zone.New Phytologist,1912.11:p.37-50.
    66.Rand,W.,Objective criteria for the evaluation of clustering methods.Journal of the American Statistical Association,1971.66:p.846-850.
    67.Hubert,L.Arabia,P.,Comparing partitions.Journal of Classification,1985.2(1):p.193-218.
    68.Fowlkes,E.Mallows,C.,Journal of American Statistics Association.1983,A method for comparing two hierarchical clusterings.78:p.553-584.
    69.Filippone,M.Sanguinetti,G.,Information theoretic novelty detection.Pattern Recognition,2009.
    70.Scholkopf,B.,Platt,J.,Shawe-Taylor,J.,Smola,A.,Williamson,R.,Estimating the support of a high dimensional distribution.Neural Computation,2001.13:p.1443-1471.
    71.Huang,K.,Velliste,M.,Murphy,R.F.,Feature reduction for improved recognition of subcellular location patterns in fluorescence microscope images.Proceedings of SPIE,2003.4692:p.307-318.
    72.Young,D.,Bender,A.,Hoyt,J.,McWhinnie,E.,Chirn,G.,Tao,C.Y.,Tallarico,J.,Labow,M.,Jenkins,J.,Mitchison,T.,Feng,Y.,Integrating high-content screening and ligand-target prediction to identify mechanism of action.Nature Chemical Biology,2008.4(1):p.59-68.
    73.Loo,L.,Wu,L.,Altshuler,S.,Image based multivariate profiling of drug responses from single cells.Nature Methods,2007.4(5):p.445-453.
    74.Wang,J.,Zhou,X.,Bradley,P.L.,Chang,S.-F.,Perrimon,N.,Wang,S.T.C.,Cellular Phenotype Recognition for High-Content RNA Interference Genome-Wide Screening.Journal of Molecular Screening,2008.13(1):p.29-39.
    75.Mitra,P.,Murthy,CA.,Pal,S.,Unsupervised feature selection using feature similarity.IEEE Transaction on Pattern Analysis and Machine Intelligence,2002.24(3):p.301-312.
    76.Wang,M.,Zhou,X.,Li,F.,Huckins,J.,King,R.W.,Wang,S.T.C.,Novel cell segmentation and online SVM for cell cycle phase identification in automated microscopy.BMC Bioinformatics,2008.24(1):p.94-101.
    77.Yoav,F.Robert,E.S.,A decision-theoretic generalization of on-line learning and an application to boosting,in Proceedings of the Second European Conference on Computational Learning Theory.1995,Springer-Verlag.
    78.Slack,M.,Martinez,E.,Wu,L.,Altshculer,S.,Characterizing heterogeneous cellular responses to perturbations.Proceedings of the National Academy of Science 2008.105(49):p.19306-19311.
    79.Yoo,C.B.Jones,P.A.,Epigenetic therapy of cancer:past,present and future.Nat Rev Drug Discov,2006.5(1):p.37-50.
    80.Birmingham,A.,Selfors,L.M.,Forster,T.,Wrobel,D.,Kennedy,C.J.,Shanks,E.,Santoyo-Lopez,J.,Dunican,D.J.,Long,A.,Kelleher,D.,Smith,Q.,Beijersbergen,R.L.,Ghazal,P.,Shamu,C.E.,Statistical methods for analysis of high-throughput RHA interference screens.Nat Meth,2009.6(8):p.569-575.
    81.Li,F.H.,Zhou,X.,Zhu,J.,Ma,J.,Huang,X.,Wang,S.T.C.,High content image analysis for human H4 neurogliomo cells exposed to CuO nanoparticles.BMC Biotechnology,2007.7:p.66.
    82.Yin,Z.(尹征),Zhou,X.,Bakal,C.,Li,F.,Sun,Y.,Perrimon,N.,Wang,S.,Using iterative cluster merging with improved gap statistics to perform online phenotype discovery in the context of high-throughput RHAi screens.BMC Bioinformatics,2008.9(1):p.264.
    83.Yin,Z.(尹征),Zhou,X.,Sun,Y.,Wang,S.T.C.,Online phenotype discovery based on minimum classification error model.Pattern Recognition,2009.42{4):p.509-522.
    84.Wang,J.,Zhou,X.,Li,F.,Bradley,P.L.,Chang,S.-F.,Perrimon,N.,Wang,S.T.C.,An image score inference system for RNAi genome-wide screening based on fuzzy mixture regression modeling.Journal of Biomedical Informatics,2009.42(1):p.32-40.
    85.Drosophila RNAi Screening Center(DRSC) at Harvard Medical School.
    86.聂俊,杨冬芝,杨晶编.细胞分子生物学.2009,化学工业出版社:北京.
    87.左伋编.医学细胞生物学(第四版).2008,复旦大学出版社:上海.
    88.Otsu,N.,A threshold selection method from gray-level histograms.IEEE Transactions on Systems,Man and Cybernetics,1979.9(1):p.62-66.
    89.Lindblad,J.,Wahlby,C.,Bengtsson,E.,Zaltsman,A.,Image analysis for automatic segmentation of cytoplasms and classification of Racl activation.Cytometry A,2004.57(1):p.22-33.
    90.Wahlby,C.,Lindblad,J.,Vondrus,M.,Bengtsson,E.,Bjorkesten,L.,Algorithms for cytoplasm segmentation of fluorescence labelled cells.Analytical Cellular Pathology,2002.24(2-3):p.101-11.
    91.Vincent,L.Soille,P.,Watersheds in digital spaces:an efficient algorithm based on immersion simulations.IEEE Transactions on Pattern Analysis and Machine Intelligence,1991.13(6):p.583-598.
    92.Borgefors,G.,Distance transformations in digital images.Computer Vision,Graphics,and Image Processing,1986.34:p.344-371.
    93.Manjunatha,B.S.Ma,W.Y.,Texture features for browsing and retrieval of image data.IEEE Transactions on Pattern Analysis and Machine Intelligenece,1996.18:p.837-842.
    94.Cohen,A.,Daubechies,I.,Feauveau,J.C.,Bi-orthogonol bases of compactly supported wavelets.Communications on Pure and Applied Mathematics,1992.45:p.485-560.
    95.Zernike,F.,Beugungstheorie des schneidencerfarhens undseiner verbesserten form,der phasenkontrastmethode.Physica,1934.1:p.689-704.
    96.Haralick,R.M.,Shanmugam,K.,Dinstein,I.,Textural features.for image classification.IEEE Transactions on Systems,Man and Cybernetics,1973.6:p.610-620.
    97.Bovik,A.C.,Clark,M.,Geisler,W.S.,Multichannel texture analysis using localized spatial filters.Pattern Analysis and Machine Intelligence,IEEE Transactions on,1990.12(1):p.55-73.
    98.Daugman,J.G.,Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression.Acoustics,Speech and Signal Processing,IEEE Transactions on,1988.36(7):p.1169-1179.
    99.Vapnik,V.,The Nature of Statistical Learning Theory.1995:New York,NY:Springer-Verlag.
    100.Cortes,C.Vapnik,V.,Support-vector network.Machine Learning,1995.20:p.273-297.
    101.Chang,C.-C.Lin,C.-J.,LIBSVM:a library for support vector machines.2001.p.Software available at http://csie.ntu.edu.tw/cjlin/libsvm.
    102.Zhou,X.Wang,X.,Optimisation of Gaussian mixture model for satellite image classification,IEE Proceedings-Vision,Image and Signal Process,2006.153(3):p.349-356.
    103.Bonferroni,C.,Teoria statistica delle classi e calcolo defle probabilita.Pubblicazioni del R Istituto Superiore di Scienze Economiche e Commerciali di Firenze 1936.8:p.3-62.
    104.Thalamuthu,A.,Mukhopadhyay,I.,Zheng,X.,Tseng,G.,Evaluation and comparison of gene clustering methods in microarray analysis.Bioinformatics,2006.22(19):p.2405-2412.
    105.Koch,W.,Coordinaring ERK/MAPK signalling through scaffolds and inhibitors.Nature Reviews Molecular Cell Biology,2005.6(11):p.827-838.
    106.Zhao,Y.,Zhuang,X.,Ting,S.-J.,Gaussian mixture density modeling of non-Gaussian source for autoregressive process.Signal Processing,IEEE Transactions on,1995.43(4):p.894-903.
    107.Guyon,I.,Weston,J.,Barnhill,S.,Vapnik,V.,Gene Selection for Cancer Classification using Support Vector Machines.Machine Learning,2002.46(1-3):p.389-422.
    108.Yin,Z.(尹征),Zhou,X.,Wang,H.,Sun,Y.,Wang,S.T.C.Detecting Biomarkers for Major Adverse Cardiac Events using SVM with PLS Feature Selection and Extraction.in 4th International Symposium on Neural Networks,ISNN 2007.2007.Nanjing,China:Springer.
    109.Li,G.Z.,Yang,J.,Liu,G.P.,Xue,L.Feature selection for multi-class problems using support vector machines.2004:Springer-Verlag Berlin.
    110.Holland,J.,Adoption in Natural and Artifical Systems.1975,Ann Arbor,MI:The University of Michigan Press.
    111.Goldberg,D.,Genetic Algorithms in Search,Optimization and Machine Learning.1989,Boston,MA:Kluwer Academic Publishers.
    112.Keerthi,S.Lin,C.,Asymptotic behaviors of support vector machines with Gaussian kernel.Neural Computation,2003.15(7):p.1667-1689.
    113.Lin,H.Lin,C.,A study on sigmoid kernels for SVM and the training of non-PSD kernels by SMO-type methods.2003,Department of Computer Science,National Taiwan University.
    114.Mahalanobis,P.C.,On the generalized distance in statistics.Proceedings of the National Institute of Science of India,1936.2(1):p.49-55.
    115.de Hoon,M.J.L.,Imoto,S.,Nolan,J.,Miyano,S.,Open source clustering software.2004.p.1453-1454.
    116.Saldanha,A.J.,Java Treeview-extensible visuolizotion of microarroy data.2004.p.3246-3248.
    117.Waddington,C.H.,Experiments on conolizing selection.Genetic Research,1960.1:p.140-150.
    118.Lees,A.D.Waddington,C.H.,The development of the bristles in normol ond some mutont types of Drosophilo melonogoster.Proceedings of the Royal Society of London,1942.131:p.87-110.
    119.Waddington,C.H.,The strotegy of the genes.1957,New York:Macmillan.
    120.Rutherford,S.L.Lindquist,S.,Hsp90 as a copocitor for morphologicol evolution.Nature,1998.396(6709):p.336-342.
    121.Chakravarti,I.,Laha,R.,Roy,J.,Hondbook of Methods of Applied Stotistics.1967,John Wiley and Sons:New York.p.392-394.
    122.Rendel,J.,Canalization ond gene control.1967,N.Y.and Longdon:Logos Press.
    123.Lehner,C.F.O'Farrell,P.H.,Drosophilo cdc2 homologs:a functional homolog is coexpressed with a cognote voriont.The EMBO Journal,1990.9:p.3573-3581.
    124.D'Avino,P.P.,Savoian,M.S.,Glover,D.M.,Cleavage furrow formatinn and ingression during animal cytokinesis:a microtubule legocy.2005.p.1549-1558.
    125.Kiger,A.A.,Baum,B.,Jones,S.,Jones,M.R.,Coulson,A.,Echeverri,C.,Perrimon,N.,A functional genomic analysis of cell morphology using RNA interference.2003.p.27.
    126.Bettencourt-Dias,M.,Giet,R.,Sinka,R.,Mazumdar,A.,Lock,W.G.,Balloux,F.,Zafiropoulos,P.J.,Yamaguchi,S.,Winter,S.,Carthew,R.W.,Cooper,M.,Jones,D.,Frenz,L.,Glover,D.M.,Genome-wide survey of protein kinoses required for cell cycle progression.Nature,2004.432(7020):p.980-987.
    127.Siegrist,S.E.Doe,C.Q.,Microtubule-induced Pins/G alpha i corticol polority in Drosophila neuroblasts.Cell,2005.123(7):p.1323-1335.
    128.Goshima,G.,Wollman,R.,Goodwin,S.S.,Zhang,N.,Scholey,J.M.,Vale,R.D.,Stuurman,N.,Genes Required for Mitotic Spindle Assembly in Drosophilo S2 Cells.2007.p.417-421.
    129.Olesen,C.,Sorensen,T.L.-M.,Nielsen,R.C.,Moller,J.V.,Nissen,P.,Dephosphorylotion of the Calcium Pump Coupled to Counterion Occlusion.2004.p.2251-2255.
    130.Sousa-Nunes,R.,Chia,W.,Somers,W.G.,Protein phosphotose 4 mediotes localization of the Miranda complex during Drosophila neuroblast asymmetric divisions.Genes &Development,2009.23(3):p.359-372.
    131.Carreno,S.,Kouranti,I.,Glusrnan,E.S.,Fuller,M.T.,Echard,A.,Payre,F.,Moesin ond its activating kinose Silk are required for corticol stobility ond microtubule organization in mitotic cells.Journal of Cell Biology,2008.180(4):p.739-746.
    132.Kunda,P.,Pelling,A.E.,Liu,T.,Baum,B.,Moesin controls corticol rigidity,cell rounding,ond spindle morphogenesis during mitosis.Current Biology,2008.18(2):p.91-101.
    133.Chi,K.R.,The year of sequencing.Nat Meth,2008.5(1):p.11-14.