Contents -- Preface -- 1 Introduction -- 1.1 Brief history of bioinformatics -- 1.2 Database application in bioinformatics -- 1.3 Web tools and services for sequence homology Alignment -- 1.3.1 Web tools and services for protein functional site identification -- 1.3.2 Web tools and services for other biological data -- 1.4 Pattern analysis -- 1.5 The contribution of information technology -- 1.6 Chapters -- 2 Introduction to Unsupervised Learning -- 3 Probability Density Estimation Approaches -- 3.1 Histogram approach -- 3.2 Parametric approach -- 3.3 Non-parametric approach -- 3.3.1 K-nearest neighbour approach -- 3.3.2 Kernel approach -- Summary -- 4 Dimension Reduction -- 4.1 General -- 4.2 Principal component analysis -- 4.3 An application of PCA -- 4.4 Multi-dimensional scaling -- 4.5 Application of the Sammon algorithm to gene data -- Summary -- 5 Cluster Analysis -- 5.1 Hierarchical clustering -- 5.2 K-means -- 5.3 Fuzzy C-means -- 5.4 Gaussian mixture models -- 5.5 Application of clustering algorithms to the Burkholderia pseudomallei gene expression data -- Summary -- 6 Self-organising Map -- 6.1 Vector quantization -- 6.2 SOM structure -- 6.3 SOM learning algorithm -- 6.4 Using SOM for classification -- 6.5 Bioinformatics applications of VQ and SOM -- 6.5.1 Sequence analysis -- 6.5.2 Gene expression data analysis -- 6.5.3 Metabolite data analysis -- 6.6 A case study of gene expression data analysis -- 6.7 A case study of sequence data analysis -- Summary -- 7 Introduction to Supervised Learning -- 7.1 General concepts -- 7.2 General definition -- 7.3 Model evaluation -- 7.4 Data organisation -- 7.5 Bayes rule for classification -- Summary -- 8 Linear/Quadratic Discriminant Analysis and K-nearest Neighbour -- 8.1 Linear discriminant analysis -- 8.2 Generalised discriminant analysis -- 8.3 K-nearest neighbour.

8.4 KNN for gene data analysis -- Summary -- 9 Classification and Regression Trees, Random Forest Algorithm -- 9.1 Introduction -- 9.2 Basic principle for constructing a classification tree -- 9.3 Classification and regression tree -- 9.4 CART for compound pathway involvement prediction -- 9.5 The random forest algorithm -- 9.6 RF for analyzing Burkholderia pseudomallei gene expression profiles -- Summary -- 10 Multi-layer Perceptron -- 10.1 Introduction -- 10.2 Learning theory -- 10.2.1 Parameterization of a neural network -- 10.2.2 Learning rules -- 10.3 Learning algorithms -- 10.3.1 Regression -- 10.3.2 Classification -- 10.3.3 Procedure -- 10.4 Applications to bioinformatics -- 10.4.1 Bio-chemical data analysis -- 10.4.2 Gene expression data analysis -- 10.4.3 Protein structure data analysis -- 10.4.4 Bio-marker identification -- 10.5 A case study on Burkholderia pseudomallei gene expression data -- Summary -- 11 Basis Function Approach and Vector Machines -- 11.1 Introduction -- 11.2 Radial-basis function neural network (RBFNN) -- 11.3 Bio-basis function neural network -- 11.4 Support vector machine -- 11.5 Relevance vector machine -- Summary -- 12 Hidden Markov Model -- 12.1 Markov model -- 12.2 Hidden Markov model -- 12.2.1 General definition -- 12.2.2 Handling HMM -- 12.2.3 Evaluation -- 12.2.4 Decoding -- 12.2.5 Learning -- 12.3 HMM for sequence classification -- Summary -- 13 Feature Selection -- 13.1 Built-in strategy -- 13.1.1 Lasso regression -- 13.1.2 Ridge regression -- 13.1.3 Partial least square regression (PLS) algorithm -- 13.2 Exhaustive strategy -- 13.3 Heuristic strategy - orthogonal least square approach -- 13.4 Criteria for feature selection -- 13.4.1 Correlation measure -- 13.4.2 Fisher ratio measure -- 13.4.3 Mutual information approach -- Summary -- 14 Feature Extraction (Biological Data Coding) -- 14.1 Molecular sequences.

14.2 Chemical compounds -- 14.3 General definition -- 14.4 Sequence analysis -- 14.4.1 Peptide feature extraction -- 14.4.2 Whole sequence feature extraction -- Summary -- 15 Sequence/Structural Bioinformatics Foundation - Peptide Classification -- 15.1 Nitration site prediction -- 15.2 Plant promoter region prediction -- Summary -- 16 Gene Network - Causal Network and Bayesian Networks -- 16.1 Gene regulatory network -- 16.2 Causal networks, networks, graphs -- 16.3 A brief review of the probability -- 16.4 Discrete Bayesian network -- 16.5 Inference with discrete Bayesian network -- 16.6 Learning discrete Bayesian network -- 16.7 Bayesian networks for gene regulartory networks -- 16.8 Bayesian networks for discovering peptide patterns -- 16.9 Bayesian networks for analysing Burkholderia pseudomallei gene data -- Summary -- 17 S-Systems -- 17.1 Michealis-Menten change law -- 17.2 S-system -- 17.3 Simplification of an S-system -- 17.4 Approaches for structure identification and parameter estimation -- 17.4.1 Neural network approach -- 17.4.2 Simulated annealing approach -- 17.4.3 Evolutionary computation approach -- 17.5 Steady-state analysis of an S-system -- 17.6 Sensitivity of an S-system -- Summary -- 18 Future Directions -- 18.1 Multi-source data -- 18.2 Gene regulatory network construction -- 18.3 Building models using incomplete data -- 18.4 Biomarker detection from gene expression data -- Summary -- References -- Index.