Machine learning approaches to bioinformatics

This book covers a wide range of subjects in applying machine learning approaches for bioinformatics projects. The book succeeds on two key unique features. First, it introduces the most widely used machine learning approaches in bioinformatics and discusses, with evaluations from real case studies, how they are used in individual bioinformatics projects. Second, it introduces state-of-the-art bioinformatics research methods. The theoretical parts and the practical parts are well integrated for readers to follow the existing procedures in individual research. Unlike most of the bioinformatics books on the market, the content coverage is not limited to just one subject. A broad spectrum of relevant topics in bioinformatics including systematic data mining and computational systems biology researches are brought together in this book, thereby offering an efficient and convenient platform for teaching purposes. An essential reference for both final year undergraduates and graduate students in universities, as well as a comprehensive handbook for new researchers, this book will also serve as a practical guide for software development in relevant bioinformatics projects.

Preface	p. v
1 Introduction	p. 1
1.1 Brief history of bioinformatics	p. 3
1.2 Database application in bioinformatics	p. 6
1.3 Web tools and services for sequence homology Alignment	p. 8
1.3.1 Web tools and services for protein functional site identification	p. 9
1.3.2 Web tools and services for other biological data	p. 10
1.4 Pattern analysis	p. 10
1.5 The contribution of information technology	p. 11
1.6 Chapters	p. 12
2 Introduction to Unsupervised Learning	p. 15
3 Probability Density Estimation Approaches	p. 24
3.1 Histogram approach	p. 24
3.2 Parametric approach	p. 25
3.3 Non-parametric approach	p. 28
3.3.1 K-nearest neighbour approach	p. 28
3.3.2 Kernel approach	p. 29
Summary	p. 36
4 Dimension Reduction	p. 38
4.1 General	p. 38
4.2 Principal component analysis	p. 39
4.3 An application of PCA	p. 42
4.4 Multi-dimensional scaling	p. 46
4.5 Application of the Sammon algorithm to gene data	p. 48
Summary	p. 50
5 Cluster Analysis	p. 52
5.1 Hierarchical clustering	p. 52
5.2 K-means	p. 55
5.3 Fuzzy C-means	p. 58
5.4 Gaussian mixture models	p. 60
5.5 Application of clustering algorithms to the Burkholderia pseudomallei gene expression data	p. 64
Summary	p. 67
6 Self-organising Map	p. 69
6.1 Vector quantization	p. 69
6.2 SOM structure	p. 73
6.3 SOM learning algorithm	p. 75
6.4 Using SOM for classification	p. 79
6.5 Bioinformatics applications of VQ and SOM	p. 81
6.5.1 Sequence analysis	p. 81
6.5.2 Gene expression data analysis	p. 83
6.5.3 Metabolite data analysis	p. 86
6.6 A case study of gene expression data analysis	p. 86
6.7 A case study of sequence data analysis	p. 88
Summary	p. 90
7 Introduction to Supervised Learning	p. 92
7.1 General concepts	p. 92
7.2 General Definition	p. 94
7.3 Model evaluation	p. 96
7.4 Data organisation	p. 101
7.5 Bayes rule for classification	p. 103
Summary	p. 103
8 Linear/Quadratic Discriminant Analysis and K-nearest Neighbour	p. 104
8.1 Linear discriminant analysis	p. 104
8.2 Generalised discriminant analysis	p. 109
8.3 K-nearest neighbour	p. 111
8.4 KNN for gene data analysis	p. 118
Summary	p. 118
9 Classification and Regression Trees, Random Forest Algorithm	p. 120
9.1 Introduction	p. 120
9.2 Basic principle for constructing a classification tree	p. 121
9.3 Classification and regression tree	p. 125
9.4 CART for compound pathway involvement prediction	p. 126
9.5 The random forest algorithm	p. 128
9.6 RF for analyzing Burkholderia pseudomallei gene expression profiles	p. 129
Summary	p. 132
10 Multi-layer Perceptron	p. 133
10.1 Introduction	p. 133
10.2 Learning theory	p. 137
10.2.1 Parameterization of a neural network	p. 137
10.2.2 Learning rules	p. 137
10.3 Learning algorithms	p. 145
10.3.1 Regression	p. 145
10.3.2 Classification	p. 146
10.3.3 Procedure	p. 147
10.4 Applications to bioinformatics	p. 148
10.4.1 Bio-chemical data analysis	p. 148
10.4.2 Gene expression data analysis	p. 149
10.4.3 Protein structure data analysis	p. 149
10.4.4 Bio-marker identification	p. 150
10.5 A case study on Burkholderia pseudomallei gene expression data	p. 150
Summary	p. 153
11 Basis Function Approach and Vector Machines	p. 154
11.1 Introduction	p. 154
11.2 Radial-basis function neural network (RBFNN)	p. 156
11.3 Bio-basis function neural network	p. 162
11.4 Support vector machine	p. 168
11.5 Relevance vector machine	p. 173
Summary	p. 176
12 Hidden Markov Model	p. 177
12.1 Markov model	p. 177
12.2 Hidden Markov model	p. 179
12.2.1 General definition	p. 179
12.2.2 Handling HMM	p. 183
12.2.3 Evaluation	p. 184
12.2.4 Decoding	p. 188
12.2.5 Learning	p. 189
12.3 HMM for sequence classification	p. 191
Summary	p. 194
13 Feature Selection	p. 195
13.1 Built-in strategy	p. 195
13.1.1 Lasso regression	p. 196
13.1.2 Ridge regression	p. 199
13.1.3 Partial least square regression (PLS) algorithm	p. 200
13.2 Exhaustive strategy	p. 204
13.3 Heuristic strategy - orthogonal least square approach	p. 204
13.4 Criteria for feature selection	p. 208
13.4.1 Correlation measure	p. 209
13.4.2 Fisher ratio measure	p. 210
13.4.3 Mutual information approach	p. 210
Summary	p. 212
14 Feature Extraction (Biological Data Coding)	p. 213
14.1 Molecular sequences	p. 214
14.2 Chemical compounds	p. 215
14.3 General definition	p. 216
14.4 Sequence analysis	p. 216
14.4.1 Peptide feature extraction	p. 216
14.4.2 Whole sequence feature extraction	p. 222
Summary	p. 224
15 Sequence/Structural Bioinformatics Foundation - Peptide Classification	p. 225
15.1 Nitration site prediction	p. 225
15.2 Plant promoter region prediction	p. 230
Summary	p. 237
16 Gene Network - Causal Network and Bayesian Networks	p. 238
16.1 Gene regulatory network	p. 238
16.2 Causal networks, networks, graphs	p. 241
16.3 A brief review of the probability	p. 242
16.4 Discrete Bayesian network	p. 245
16.5 Inference with discrete Bayesian network	p. 246
16.6 Learning discrete Bayesian network	p. 247
16.7 Bayesian networks for gene regulatory networks	p. 247
16.8 Bayesian networks for discovering Peptide patterns	p. 248
16.9 Bayesian networks for analysing Burkholderia pseudomallei gene data	p. 249
Summary	p. 252
17 S-Systems	p. 253
17.1 Michealis-Menten change law	p. 253
17.2 S-System	p. 256
17.3 Simplification of an S-system	p. 259
17.4 Approaches for structure identification and parameter estimation	p. 260
17.4.1 Neural network approach	p. 260
17.4.2 Simulated annealing approach	p. 261
17.4.3 Evolutionary computation approach	p. 262
17.5 Steady-state analysis of an S-system	p. 262
17.6 Sensitivity of an S-system	p. 267
Summary	p. 268
18 Future Directions	p. 269
18.1 Multi-source data	p. 270
18.2 Gene regulatory network construction	p. 272
18.3 Building models using incomplete data	p. 274
18.4 Biomarker detection from gene expression data	p. 275
Summary	p. 278
References	p. 279
Index	p. 319

Available:*

On Order

Summary

Summary

Table of Contents