1st Edition

Meta-analysis and Combining Information in Genetics and Genomics

By Rudy Guerra, Darlene R. Goldstein Copyright 2010
    360 Pages 55 B/W Illustrations
    by Chapman & Hall

    360 Pages 55 B/W Illustrations
    by Chapman & Hall

    Novel Techniques for Analyzing and Combining Data from Modern Biological Studies
    Broadens the Traditional Definition of Meta-Analysis

    With the diversity of data and meta-data now available, there is increased interest in analyzing multiple studies beyond statistical approaches of formal meta-analysis. Covering an extensive range of quantitative information combination methods, Meta-analysis and Combining Information in Genetics and Genomics looks at how to analyze multiple studies from a broad perspective.

    After presenting the basic ideas and tools of meta-analysis, the book addresses the combination of similar data types: genotype data from genome-wide linkage scans and data derived from microarray gene expression experiments. The expert contributors show how some data combination problems can arise even within the same basic framework and offer solutions to these problems. They also discuss the combined analysis of different data types, giving readers an opportunity to see data combination approaches in action across a wide variety of genome-scale investigations.

    As heterogeneous data sets become more common, biological understanding will be significantly aided by jointly analyzing such data using fundamentally sound statistical methodology. This book provides many novel techniques for analyzing data from modern biological studies that involve multiple data sets, either of the same type or multiple data sources.

    Introductory Material

    A brief introduction to meta-analysis, genetics, and genomics Darlene R. Goldstein and Rudy Guerra

    Similar Data Types I: Genotype Data

    Combining information across genome-wide linkage scans Carol J. Etzel and Tracy J. Costello

    Genome search meta-analysis (GSMA): a nonparametric method for meta-analysis of genome-wide linkage studies Cathryn M. Lewis

    Heterogeneity in meta-analysis of quantitative trait linkage studies Hans C. van Houwelingen and Jérémie J.P. Lebrec

    An empirical Bayesian framework for QTL genome-wide scans Kui Zhang, Howard Wiener, T. Mark Beasley, Christopher I. Amos, and David B. Allison

    Similar Data Types II: Gene Expression Data

    Composite hypothesis testing: an approach built on intersection-union tests and Bayesian posterior probabilities Stephen Erickson, Kyoungmi Kim, and David B. Allison

    Frequentist and Bayesian error pooling methods for enhancing statistical power in small sample microarray data analysis Jae K. Lee, Hyung Jun Cho, and Michael O’Connell

    Significance testing for small microarray experiments Charles Kooperberg, Aaron Aragaki, Charles C. Carey, and Suzannah Rutherford

    Comparison of meta-analysis to combined analysis of a replicated microarray study Darlene R. Goldstein, Mauro Delorenzi, Ruth Luthi-Carter, and Thierry Sengstag

    Alternative probe set definitions for combining microarray data across studies using different versions of Affymetrix oligonucleotide arrays Jeffrey S. Morris, Chunlei Wu, Kevin R. Coombes, Keith A. Baggerly, Jing Wang, and Li Zhang

    Gene ontology-based meta-analysis of genome-scale experiments Chad A. Shaw

    Combining Different Data Types

    Combining genomic data in human studies Debashis Ghosh, Daniel Rhodes, and Arul Chinnaiyan

    An overview of statistical approaches for expression trait loci mapping Christina Kendziorski and Meng Chen

    Incorporating GO annotation information in expression trait loci mapping J. Blair Christian and Rudy Guerra

    A misclassification model for inferring transcriptional regulatory networks Ning Sun and Hongyu Zhao

    Data integration for the study of protein interactions Fengzhu Sun, Ting Chen, Minghua Deng, Hyunju Lee, and Zhidong Tu

    Gene trees, species trees, and species networks Luay Nakhleh, Derek Ruths, and Hideki Innan




    Rudy Guerra is a professor of statistics at Rice University.

    Darlene R. Goldstein is a member of the Chair of Statistics research group in the Institut de Mathématiques at the École Polytechnique Fédérale de Lausanne (EPFL).

    For someone who is interested in either metaanalysis or genomics, this book provides a great overview of both. … Guerra and Goldstein have done a wonderful job in introducing the material and in organizing the collection coherently. … the material is very accessible to readers of Biometrics … this book is well worth having as a reference book for those interested in metaanalysis and/or genomics. … Guerra and Goldstein have done an admirable job putting the collection together.
    —Peter H. Westfall, Biometrics, December 2011

    There is a particularly good chapter comparing different methods for analysing two similar microarray studies… The book would be suitable for someone who is new to the analysis of high dimensional genomic data.
    —S.E. Lazic and F. Hoffmann-La Roche, Journal of the Royal Statistical Society: Series A, Vol. 174, October 2011

    … the book will be most useful for students and researchers who wish to see what developments are currently in progress in this important area. That said, there is a wealth of material here for the non-expert wishing to move into the area. And, unlike some edited tomes in past ages, the articles here have clearly been carefully meshed to give a coherent picture.
    International Statistical Review (2011), 79, 1