Weighted Network Analysis

This book offers current methods, software and applications involved in weighted networks, reviewing data mining methods and analysis strategies and showing how to use them in practice. The self-contained presentation requires minimal knowledge of statistics.

High-throughput measurements of gene expression and genetic marker data facilitate systems biologic and systems genetic data analysis strategies. Gene co-expression networks have been used to study a variety of biological systems, bridging the gap from individual genes to biologically or clinically important emergent phenotypes.

This books describes the theory, application, and software of weighted gene co-expression network analysis Serves as an introductory and comprehensive text on gene co-expression network methodology The book includes biologically interesting case studies that describe data analysis strategies and results Includes supplementary material: sn.pub/extras

Klappentext

This book presents state-of-the-art methods, software and applications surrounding weighted networks. Most methods and results also apply to unweighted networks. Although aspects of weighted network analysis relate to standard data mining methods, the intuitive network language and analysis framework transcend any particular analysis method. Weighted networks give rise to data reduction methods, clustering procedures, visualization methods, data exploratory methods, and intuitive approaches for integrating disparate data sets. Weighted networks have been used to analyze a variety of high dimensional genomic data sets including gene expression-, epigenetic-, methylation-, proteomics-, and fMRI- data. Chapters explore the fascinating topological structure of weighted networks and provide geometric interpretations of network methods. Powerful systems-level analysis methods result from combining network- with data mining methods. The book not only describes the WGCNA R package but also other software packages. Weighted gene co-expression network applications, real data sets, and exercises guide the reader on how to use these methods in practice, e.g. in systems-biologic or systems-genetic applications. The material is self-contained and only requires a minimum knowledge of statistics. The book is intended for students, faculty, and data analysts in many fields including bioinformatics, computational biology, statistics, computer science, biology, genetics, applied mathematics, physics, and social science.

Inhalt
Preface.- Networks and fundamental concepts.- Approximately factorizable networks.- Different type of network concepts.- Adjacency functions and their topological effects.- Correlation and gene co-expression networks.- Geometric interpretation of correlation networks using the singular value decomposition.- Constructing networks from matrices.- Clustering Procedures and module detection.- Evaluating whether a module is preserved in another network.- Association and statistical significance measures.- Structural equation models and directed networks.- Integrated weighted correlation network analysis of mouse liver gene expression data.- Networks based on regression models and prediction methods.- Networks between categorical or discretized numeric variables.- Networks based on the joint probability distribution of random variables.- Index.