High Dimensional Microarray Data Analysis

This book shows how to decompose high-dimensional microarrays into small subspaces (Small Matryoshkas, SMs), statistically analyze them, and perform cancer gene diagnosis. The information is useful for genetic experts, anyone who analyzes genetic data, and students to use as practical textbooks. Discriminant analysis is the best approach for microarray consisting of normal and cancer classes. Microarrays are linearly separable data (LSD, Fact 3). However, because most linear discriminant function (LDF) cannot discriminate LSD theoretically and error rates are high, no one had discovered Fact 3 until now. Hard-margin SVM (H-SVM) and Revised IP-OLDF (RIP) can find Fact3 easily. LSD has the Matryoshka structure and is easily decomposed into many SMs (Fact 4). Because all SMs are small samples and LSD, statistical methods analyze SMs easily. However, useful results cannot be obtained. On the other hand, H-SVM and RIP can discriminate two classes in SM entirely. RatioSV is the ratio of SV distance and discriminant range. The maximum RatioSVs of six microarrays is over 11.67%. This fact shows that SV separates two classes by window width (11.67%). Such easy discrimination has been unresolved since 1970. The reason is revealed by facts presented here, so this book can be read and enjoyed like a mystery novel. Many studies point out that it is difficult to separate signal and noise in a high-dimensional gene space. However, the definition of the signal is not clear. Convincing evidence is presented that LSD is a signal. Statistical analysis of the genes contained in the SM cannot provide useful information, but it shows that the discriminant score (DS) discriminated by RIP or H-SVM is easily LSD. For example, the Alon microarray has 2,000 genes which can be divided into 66 SMs. If 66 DSs are used as variables, the result is a 66-dimensional data. These signal data can be analyzed to find malignancy indicators by principal component analysis and cluster analysis.

Praise for the First Edition “...extremely well written...a comprehensive and up-to-date overview of this important field.” – Journal of Environmental Quality Exploration and Analysis of DNA Microarray and Other High-Dimensional Data, Second Edition provides comprehensive coverage of recent advancements in microarray data analysis. A cutting-edge guide, the Second Edition demonstrates various methodologies for analyzing data in biomedical research and offers an overview of the modern techniques used in microarray technology to study patterns of gene activity. The new edition answers the need for an efficient outline of all phases of this revolutionary analytical technique, from preprocessing to the analysis stage. Utilizing research and experience from highly-qualified authors in fields of data analysis, Exploration and Analysis of DNA Microarray and Other High-Dimensional Data, Second Edition features: A new chapter on the interpretation of findings that includes a discussion of signatures and material on gene set analysis, including network analysis New topics of coverage including ABC clustering, biclustering, partial least squares, penalized methods, ensemble methods, and enriched ensemble methods Updated exercises to deepen knowledge of the presented material and provide readers with resources for further study The book is an ideal reference for scientists in biomedical and genomics research fields who analyze DNA microarrays and protein array data, as well as statisticians and bioinformatics practitioners. Exploration and Analysis of DNA Microarray and Other High-Dimensional Data, Second Edition is also a useful text for graduate-level courses on statistics, computational biology, and bioinformatics.

Multivariate analysis is a mainstay of statistical tools in the analysis of biomedical data. It concerns with associating data matrices of n rows by p columns, with rows representing samples (or patients) and columns attributes of samples, to some response variables, e.g., patients outcome. Classically, the sample size n is much larger than p, the number of variables. The properties of statistical models have been mostly discussed under the assumption of fixed p and infinite n. The advance of biological sciences and technologies has revolutionized the process of investigations of cancer. The biomedical data collection has become more automatic and more extensive. We are in the era of p as a large fraction of n, and even much larger than n. Take proteomics as an example. Although proteomic techniques have been researched and developed for many decades to identify proteins or peptides uniquely associated with a given disease state, until recently this has been mostly a laborious process, carried out one protein at a time. The advent of high throughput proteome-wide technologies such as liquid chromatography-tandem mass spectroscopy make it possible to generate proteomic signatures that facilitate rapid development of new strategies for proteomics-based detection of disease. This poses new challenges and calls for scalable solutions to the analysis of such high dimensional data. In this volume, we will present the systematic and analytical approaches and strategies from both biostatistics and bioinformatics to the analysis of correlated and high-dimensional data.

This book focuses on the development and application of the latest advanced data mining, machine learning, and visualization techniques for the identification of interesting, significant, and novel patterns in gene expression microarray data.Biomedical researchers will find this book invaluable for learning the cutting-edge methods for analyzing gene expression microarray data. Specifically, the coverage includes the following state-of-the-art methods:• Gene-based analysis: the latest novel clustering algorithms to identify co-expressed genes and coherent patterns in gene expression microarray data sets• Sample-based analysis: supervised and unsupervised methods for the reduction of the gene dimensionality to select significant genes. A series of approaches to disease classification and discovery are also described• Pattern-based analysis: methods for ascertaining the relationship between (subsets of) genes and (subsets of) samples. Various novel pattern-based clustering algorithms to find the coherent patterns embedded in the sub-attribute spaces are discussed• Visualization tools: various methods for gene expression data visualization. The visualization process is intended to transform the gene expression data set from high-dimensional space into a more easily understood two- or three-dimensional space.

Microarray Image and Data Analysis: Theory and Practice is a compilation of the latest and greatest microarray image and data analysis methods from the multidisciplinary international research community. Delivering a detailed discussion of the biological aspects and applications of microarrays, the book: Describes the key stages of image processing, gridding, segmentation, compression, quantification, and normalization Features cutting-edge approaches to clustering, biclustering, and the reconstruction of regulatory networks Covers different types of microarrays such as DNA, protein, tissue, and low- and high-density oligonucleotide arrays Examines the current state of various microarray technologies, including their availability and affordability Explains how data generated by microarray experiments are analyzed to obtain meaningful biological conclusions An essential reference for academia and industry, Microarray Image and Data Analysis: Theory and Practice provides readers with valuable tools and techniques that extend to a wide range of biological studies and microarray platforms.

Considered highly exotic tools as recently as the late 1990s, microarrays are now ubiquitous in biological research. Traditional statistical approaches to design and analysis were not developed to handle the high-dimensional, small sample problems posed by microarrays. In just a few short years the number of statistical papers providing approaches

Microarrays for simultaneous measurement of redundancy of RNA species are used in fundamental biology as well as in medical research. Statistically, a microarray may be considered as an observation of very high dimensionality equal to the number of expression levels measured on it. In Statistical Methods for Microarray Data Analysis: Methods and Protocols, expert researchers in the field detail many methods and techniques used to study microarrays, guiding the reader from microarray technology to statistical problems of specific multivariate data analysis. Written in the highly successful Methods in Molecular Biology series format, the chapters include the kind of detailed description and implementation advice that is crucial for getting optimal results in the laboratory. Thorough and intuitive, Statistical Methods for Microarray Data Analysis: Methods and Protocols aids scientists in continuing to study microarrays and the most current statistical methods.

This book constitutes the thoroughly refereed post-proceedings of the First VLDB 2006 International Workshop on Data Mining and Bioinformatics, VDMB 2006, held in Seoul, Korea in September 2006 in conjunction with VLDB 2006. The 15 revised full papers cover various topics in the areas of microarray data analysis, bioinformatics system and text retrieval, application of gene expression data, and sequence analysis.