Integrative Cluster Analysis in Bioinformatics E-Book

Basel Abu-Jamous

• Herausgeber: John Wiley & Sons
• Kategorie: Wissenschaft und neue Technologien
• Sprache: Englisch

Seitenzahl: 819

Veröffentlichungsjahr: 2015

Beschreibung

Clustering techniques are increasingly being put to use in the analysis of high-throughput biological datasets. Novel computational techniques to analyse high throughput data in the form of sequences, gene and protein expressions, pathways, and images are becoming vital for understanding diseases and future drug discovery.

This book details the complete pathway of cluster analysis, from the basics of molecular biology to the generation of biological knowledge. The book also presents the latest clustering methods and clustering validation, thereby offering the reader a comprehensive review of clustering analysis in bioinformatics from the fundamentals through to state-of-the-art techniques and applications.

Key Features:

• Offers a contemporary review of clustering methods and applications in the field of bioinformatics, with particular emphasis on gene expression analysis
• Provides an excellent introduction to molecular biology with computer scientists and information engineering researchers in mind, laying out the basic biological knowledge behind the application of clustering analysis techniques in bioinformatics
• Explains the structure and properties of many types of high-throughput datasets commonly found in biological studies
• Discusses how clustering methods and their possible successors would be used to enhance the pace of biological discoveries in the future
• Includes a companion website hosting a selected collection of codes and links to publicly available datasets

Leseprobe

CONTENTS

Cover

Title page

Preface

List of Symbols

About the Authors

Part One: Introduction

1 Introduction to Bioinformatics

1.1 Introduction

1.2 The “Omics” Era

1.3 The Scope of Bioinformatics

1.4 What Do Information Engineers and Biologists Need to Know?

1.5 Discussion and Summary

References

2 Computational Methods in Bioinformatics

2.1 Introduction

2.2 Machine Learning and Data Mining

2.3 Optimisation

2.4 Image Processing: Bioimage Informatics

2.5 Network Analysis

2.6 Statistical Analysis

2.7 Software Tools and Technologies

2.8 Discussion and Summary

References

Part Two: Introduction to Molecular Biology

3 The Living Cell

3.1 Introduction

3.2 Prokaryotes and Eukaryotes

3.3 Multicellularity

3.4 Cell Components

3.5 Discussion and Summary

References

4 Central Dogma of Molecular Biology

4.1 Introduction

4.2 Central Dogma of Molecular Biology Overview

4.3 Proteins

4.4 DNA

4.5 RNA

4.6 Genes

4.7 Transcription and Post-transcriptional Processes

4.8 Translation and Post-translational Processes

4.9 Discussion and Summary

References

Part Three: Data Acquisition and Pre-processing

5 High-throughput Technologies

5.1 Introduction

5.2 Microarrays

5.3 Next-generation Sequencing (NGS)

5.4 ChIP on Microarrays and Sequencing

5.5 Discussion and Summary

References

6 Databases, Standards and Annotation

6.1 Introduction

6.2 NCBI Databases

6.3 The EBI Databases

6.4 Species-specific Databases

6.5 Discussion and Summary

References

7 Normalisation

7.1 Introduction

7.2 Issues Tackled by Normalisation

7.3 Normalisation Methods

7.4 Discussion and Summary

References

8 Feature Selection

8.1 Introduction

8.2 FS and FG – Problem Definition

8.3 Consecutive Ranking

8.4 Individual Ranking

8.5 Principal Component Analysis

8.6 Genetic Algorithms and Genetic Programming

8.7 Discussion and Summary

References

9 Differential Expression

9.1 Introduction

9.2 Fold Change

9.3 Statistical Hypothesis Testing – Overview

9.4 Statistical Hypothesis Testing – Methods

9.5 Discussion and Summary

References

Part Four: Clustering Methods

10 Clustering Forms

10.1 Introduction

10.2 Proximity Measures

10.3 Clustering Families

10.4 Clusters and Partitions

10.5 Discussion and Summary

References

11 Partitional Clustering

11.1 Introduction

11.2

k

-Means and its Applications

11.3

k

-Medoids and its Applications

11.4 Discussion and Summary

References

12 Hierarchical Clustering

12.1 Introduction

12.2 Principles

12.3 Discussion and Summary

References

13 Fuzzy Clustering

13.1 Introduction

13.2 Principles

13.3 Discussion

References

14 Neural Network-based Clustering

14.1 Introduction

14.2 Algorithms

14.3 Discussion

References

15 Mixture Model Clustering

15.1 Introduction

15.2 Finite Mixture Models

15.3 Infinite Mixture Models

15.4 Discussion

References

16 Graph Clustering

16.1 Introduction

16.2 Basic Definitions

16.3 Graph Clustering

16.4 Resources

16.5 Discussion

References

17 Consensus Clustering

17.1 Introduction

17.2 Overview

17.3 Consensus Functions

17.4 Discussion

References

18 Biclustering

18.1 Introduction

18.2 Overview

18.3 Biclustering Methods

18.4 Discussion

References

19 Clustering Methods Discussion

19.1 Introduction

19.2 Hierarchical Clustering

19.3 Fuzzy Clustering

19.4 Neural Network-based Clustering

19.5 Mixture Model-based Clustering

19.6 Graph-based Clustering

19.7 Consensus Clustering

19.8 Biclustering

19.9 Summary

References

Part Five: Validation and Visualisation

20 Numerical Validation

20.1 Introduction

20.2 External Criteria

20.3 Internal Criteria

20.4 Relative Criteria

20.5 Discussion and Summary

References

21 Biological Validation

21.1 Introduction

21.2 GO Analysis

21.3 Upstream Sequence Analysis

21.4 Gene-network Analysis

21.5 Discussion and Summary

References

22 Visualisations and Presentations

22.1 Introduction

22.2 Methods and Examples

22.3 Summary

References

Part Six: New Clustering Frameworks Designed for Bioinformatics

23 Splitting-Merging Awareness Tactics (SMART)

23.1 Introduction

23.2 Related Work

23.3 SMART Framework

23.4 Implementations

23.5 Enhanced SMART

23.6 Examples

23.7 Discussion

References

24 Tightness-tunable Clustering (UNCLES)

24.1 Introduction

24.2 Bi-CoPaM Method

24.3 UNCLES Method - Other Types of External Specifications

24.4 M–N Scatter Plots Technique

24.5 Parameter-free UNCLES with M–N Plots

24.6 Discussion and Summary

References

Appendix

High-throughput Data Resources

Normalisation Methods

Feature-selection Methods

Differential Expression Methods

Partitional Clustering Algorithms

MATLAB Linkage Functions

Fuzzy Clustering Algorithms

Neural Network-based Clustering Methods

Mixture Model-based Clustering Methods

Graphs and Networks File Formats and Storage

Graph-clustering Algorithms

Consensus Clustering Algorithms

Biclustering Algorithms

References

Index

End User License Agreement

List of Tables

Chapter 04

Table 4.1 The 20 amino acids

Table 4.2 The genetic code: mapping the three-base mRNA codons to their corresponding amino acids

Chapter 06

Table 6.1 High-throughput data resources

Chapter 07

Table 7.1 Normalisation software packages

Chapter 08

Table 8.1 Resources for feature selection and FG methods

Chapter 09

Table 9.1 Contingency matrix for Fisher’s exact test over the

j

th gene

Table 9.2 Differential expression analysis software packages

Chapter 10

Table 10.1 Summary of the dissimilarity and the similarity measures of continuous feature objects

Chapter 11

Table 11.1 The basic procedure of

k

-means

Table 11.2 The Kaufman approach (KA)

Table 11.3 Examples of popular kernel functions

Table 11.4 The basic procedure of spherical

k

-means

Table 11.5 Summary of genetic

k

-means

Table 11.6 Summary of all partitional clustering algorithms introduced in this chapter

Chapter 12

Table 12.1 Specifications of all agglomerative hierarchical clustering methods

Table 12.2 The general procedure of agglomerative hierarchical clustering

Table 12.3 Specifications of all agglomerative hierarchical clustering methods

Chapter 13

Table 13.1 The procedure of fuzzy

c

-means

Table 13.2 Summary of the publicly accessible resources of fuzzy clustering algorithms

Chapter 14

Table 14.1 Summary of the clustering process of SOM by Kohonen (1990)

Table 14.2 Summary of the variants of ART

Table 14.3 Summary of theSOON-1 algorithm

Table 14.4 Summary of the SOON-2 algorithm

Table 14.5 Collection of publicly accessible resources for neural network-based clustering

Chapter 15

Table 15.1 Ten covariance structures are characterised based on the parameterisations

Table 15.2 Eight covariance structures are characterised based on the constraints

Table 15.3 Summary of mixture model-based clustering algorithms

Table 15.4 Collection of publicly accessible resources for mixture model-based clustering

Chapter 16

Table 16.1 Summary of the normalised cut graph partitioning algorithm

Table 16.2 Summary of the spectral clustering algorithm by Ng, Jordan and Weiss (2001)

Table 16.3 Summary of spectral modularity optimisation algorithm by Newman (2006)

Table 16.4 Summary of file formats as a storage of graphs and network

Table 16.5 Summary of graph clustering algorithms mentioned in this chapter

Chapter 17

Table 17.1 Summary of consensus clustering algorithms mentioned in this chapter

Chapter 18

Table 18.1 Summary of biclustering algorithms

Chapter 20

Table 20.1 Contingency table

Table 20.2 Summarisation of the capabilities and limitations of all CV introduced in this chapter. The capabilities that we refer to are what validation work they can do and what requirements they need; namely, (G) if the

g

round truth is needed, (A) if the clustering

a

lgorithms can be validated, (P) if the

p

artitions can be validated, (F) if the

f

uzzy partitions can be validated, (C) if the

c

risp partitions can be validated, (K) if the number of clusters

K

can be estimated, (O) if the

o

bject validity can be provided, (SC) if the

s

ingle-

c

luster validity can be provided, (NR) if it has

n

oise-

r

esistance ability, (MB) if it is probabilistic

m

odel-

b

ased criterion, and what the level of its computational complexity is. In this table, ‘Yes’ means that the validation algorithm has the capability and ‘No’ means it has not. ‘?’ Means that it is not a definite ‘Yes’ or ‘No’