CONTENTS -- Preface -- Part I OVERVIEW -- Chapter 1 Bioinformatics: Mining the Massive Data from High Throughput Genomics Experiments Haixu Tang and Sun Kim -- 1 Introduction -- 2 Recent Development of Classical Topics -- 2.1 Sequence alignment -- 2.2 Genome sequencing and fragment assembly -- 2.3 Gene annotation -- 2.4 RNA folding -- 2.5 Motif finding -- 2.6 Protein structure prediction -- 3 Emerging Topics from New Genome Technologies -- 3.1 Comparative genomics: beyond genome comparison -- 3.2 Pathway reconstruction -- 3.3 Microarray analysis -- 3.4 Proteomics -- 3.5 Protein-protein interaction -- 4 Conclusion -- Acknowledgement -- References -- Chapter 2 An Introduction to Soft Computing Amit Konar and Swagatam Das -- 1 Classical AI and its Pitfalls -- 2 What is Soft Computing? -- 3 Fundamental Components of Soft Computing -- 3.1 Fuzzy sets and fuzzy logic -- 3.2 Neural networks -- 3.3 Genetic algorithms -- 3.4 Belief networks -- 4 Synergism in Soft Computing -- 4.1 Neuro-fuzzy synergism -- 4.2 Neuro-GA synergism -- 4.3 Fuzzy-GA synergism -- 4.4 Neuro-belief network synergism -- 4.5 GA-belief network synergism -- 4.6 Neuro-fuzzy-GA synergism -- 5 Some Emerging Areas of Soft Computing -- 5.1 Artificial life -- 5.2 Particle swarm optimization (PSO) -- 5.3 Artificial immune system -- 5.4 Rough sets and granular computing -- 5.5 Chaos theory -- 5.6 Ant colony systems (ACS) -- 6 Summary -- References -- Part II BIOLOGICAL SEQUENCE AND STRUCTURE ANALYSIS -- Chapter 3 Reconstructing Phylogenies with Memetic Algorithms and Branch-and-Bound José E. Gallardo, Carlos Cotta and Antonio J. Fernández -- 1 Introduction -- 2 A Crash Introduction to Phylogenetic Inference -- 3 Evolutionary Algorithms for the Phylogeny Problem -- 4 A BnB Algorithm for Phylogenetic Inference -- 5 A Memetic Algorithm for Phylogenetic Inference -- 6 A Hybrid Algorithm.

7 Experimental Results -- 7.1 Experimental setting -- 7.2 Sensitivity analysis on the hybrid algorithm -- 7.3 Analysis of results -- 8 Conclusions -- Acknowledgment -- References -- Chapter 4 Classification ofRNASequences with Support Vector Machines Jason T. L. Wang and Xiaoming Wu -- 1 Introduction -- 2 Count Kernels and Marginalized Count Kernels -- 2.1 RNA sequences with known secondary structures -- 2.2 RNA sequences with unknown secondary structures -- 3 Kernel Based on Labeled Dual Graphs -- 3.1 Labeled dual graphs -- 3.2 Marginalized kernel for labeled dual graphs -- 4 A New Kernel -- 4.1 Extracting features for global structural information -- 4.2 Extracting features for local structural information -- 5 Experiments and Results -- 5.1 Data and parameters -- 5.2 Results -- 6 Conclusion -- Acknowledgment -- References -- Chapter 5 Beyond String Algorithms: Protein Sequence Analysis using Wavelet Transforms Arun Krishnan and Kuo-Bin Li -- 1 Introduction -- 1.1 String algorithms -- 1.2 Sequence analysis -- 1.3 Wavelet transform -- 2 Motif Searching -- 2.1 Introduction -- 2.2 Methods -- 2.3 Results -- 2.4 Allergenicity prediction -- 3 Transmembrane Helix Region (HTM) Prediction -- 4 Hydrophobic Cores -- 5 Protein Repeat Motifs -- 6 Sequence Comparison -- 7 Prediction of Protein Secondary Structures -- 8 Disease Related Studies -- 9 Other Functional Prediction -- 10 Conclusion -- References -- Chapter 6 Filtering Protein Surface Motifs Using Negative Instances of Active Sites Candidates Nripendra L. Shrestha and Takenao Ohkawa -- 1 Introduction -- 2 Protein Structural Data and Surface Motifs -- 2.1 Protein structural data -- 2.2 Protein molecular surface data -- 2.3 Functions of a protein and structural motifs -- 2.3.1. Functions of a protein -- 2.3.2. Active sites -- 2.3.3. Protein structural motifs -- 3 Overview of SUMOMO.

3.1 Surface motif extraction -- 3.1.1. Unit surfaces construction -- 3.1.2. Sorting of vector pairs using buckets -- 3.1.3. Merging of candidate motifs -- 3.2 Filtering using similarity between local surfaces -- 3.2.1. Similarity focused on adjacent motif sets -- 3.2.2. Significance of surface motifs -- 3.3 Problems with SUMOMO -- 4 Filtering Surface Motifs using Negative Instances of Protein Active Sites Candidates -- 4.1 Survey on the features to distinguish real active sites from the active sites candidates -- 4.1.1. Dissimilarity -- 4.1.2. Procedure -- 4.1.3. Results -- 4.2 Ranking active sites candidates -- 5 Evaluations -- 6 Conclusions and Future Works -- References -- Chapter 7 Distill: A Machine Learning Approach to Ab Initio Protein Structure Prediction Gianluca Pollastri, Davide Baú and Alessandro Vullo -- 1 Introduction -- 2 Structural Features -- 2.1 One-dimensional structural features -- 2.1.1. Secondary structure -- 2.1.2. Solvent accessibility -- 2.1.3. Contact density -- 2.2 Two-dimensional structural features -- 2.2.1. Contact maps -- 2.2.2. Coarse topologies -- 3 Review of Statistical Learning Methods Applied -- 3.1 RNNs for undirected graphs -- 3.2 1D DAG-RNN -- 3.2.1. Ensembling 1D DAG-RNNs -- 3.3 2D DAG-RNN -- 4 Predictive Architecture -- 4.1 Data set generation -- 4.2 Training protocols -- 4.3 One-dimensional feature predictors -- 4.3.1. Porter -- 4.3.2. Pale Ale -- 4.3.3. Brown Ale -- 4.4 Two-dimensional feature predictors -- 4.4.1. XXStout -- 4.4.2. XStout -- 5 Modeling Protein Backbones -- 5.1 Protein representation -- 5.2 Constraints-based pseudo energy -- 5.3 Optimization algorithm -- 6 Reconstruction Results -- 7 Conclusions -- Acknowledgment -- References -- Chapter 8 In Silico Design of Ligands using Properties of Target Active Sites Sanghamitra Bandyopadhyay, Santanu Santra, Ujjwal Maulik and Heinz Muehlenbein.

1 Introduction -- 2 Relevance of Genetic Algorithm for Drug Design -- 3 Basic Issues -- 3.1 Core formation -- 3.2 Chromosome representation -- 3.3 Fitness computation -- 4 Main Algorithm -- 5 Experimental Results -- 6 Discussion -- References -- Part III GENE EXPRESSION AND MICROARRAY DATA ANALYSIS -- Chapter 9 Inferring Regulations in a Genomic Network from Gene Expression Profiles Nasimul Noman and Hitoshi Iba -- 1 Introduction -- 2 Modeling Gene Regulatory Networks by S-system -- 2.1 Canonical model description -- 2.2 Genetic network inference problem by S-system -- 2.3 Decoupled S-system model -- 2.4 Fitness function for skeletal network structure -- 3 Inference Method -- 3.1 Trigonometric Differential Evolution (TDE) -- 3.2 Proposed algorithm -- 3.2.1. Mutation phase -- 3.3 Local search procedure -- 4 Simulated Experiment -- 4.1 Experiment 1: inferring small scale network in noise free environment -- 4.1.1. Experimental setup -- 4.1.2. Result -- 4.2 Experiment 2: inferring small scale network in noisy environment -- 4.2.1. Experimental setup -- 4.2.2. Results -- 4.3 Experiment 3: inferring medium scale network in noisy environment -- 4.3.1. Experimental setup -- 4.3.2. Results -- 5 Analysis of Real Gene Expression Data -- 5.1 Experimental data set -- 5.1.1. Results -- 6 Discussion -- 7 Conclusion -- References -- Chapter 10 A Reliable Classification of Gene Clusters for Cancer Samples Using a Hybrid Multi- Objective Evolutionary Procedure Kalyanmoy Deb, A. Raji Reddy and Shamik Chaudhuri -- 1 Introduction -- 2 Class Prediction Procedure -- 2.1 Two-class classification -- 2.2 Multi-class classification -- 3 Evolutionary Gene Selection Procedure -- 3.1 The optimization problem -- 3.2 A multi-objective evolutionary algorithm -- 3.3 A multi-modal NSGA-II -- 3.4 Genetic operators and modified domination operator.

3.5 NSGA-II search using a fixed classifier size -- 3.6 Overall procedure -- 4 Simulation Results -- 4.1 Complete leukemia study -- 4.2 Diffuse large B-cell lymphoma dataset -- 4.3 Colon cancer dataset -- 4.4 NCI60 multi-class tumor dataset -- 5 Conclusions -- References -- Chapter 11 Feature Selection for Cancer Classification using Ant Colony Optimization and Support Vector Machines A. Gupta, V. K. Jayaraman and B. D. Kulkarni -- 1 Introduction -- 2 Ant Colony Optimization -- 3 Support Vector Machines -- 4 Proposed Ant Algorithm -- 4.1 State transition rules -- 4.2 Evaluation procedure -- 4.3 Global updating rule -- 4.4 Local updating rule -- 5 Algorithm Outline -- 6 Experiments -- 6.1 Datasets -- 6.1.1. Colon cancer dataset -- 6.1.2. Brain cancer dataset -- 6.1.3. Leukemia dataset -- 6.2 Preprocessing -- 6.3 Experimental setup -- 7 Results and Discussion -- 8 Conclusions -- Acknowledgments -- References -- Chapter 12 Sophisticated Methods for Cancer Classifi- cation using Microarray Data Sung-Bae Cho and Han-Saem Park -- 1 Introduction -- 2 Backgrounds -- 2.1 DNA microarray -- 2.1.1. DNA microarray -- 2.1.2. Oligonucleotide microarray -- 2.2 Feature selection methods -- 2.3 Base classifiers -- 2.4 Classifier ensemble methods -- 3 Sophisticated Methods for Cancer Classification -- 3.1 Ensemble with negatively correlated features -- 3.2 Combinatorial ensemble -- 3.3 Searching optimal ensemble with GA -- 4 Experiments -- 4.1 Datasets -- 4.2 Ensemble with negative correlated features -- 4.3 Combinatorial ensemble -- 4.4 Optimal ensemble with GA -- 5 Conclusions -- Acknowledgement -- References -- Chapter 13 Multiobjective Evolutionary Approach to Fuzzy Clustering of Microarray Data Anirban Mukhopadhyay, Ujjwal Maulik and Sanghamitra Bandyopadhyay -- 1 Introduction -- 2 Structure of Gene Expression Data Sets -- 3 Cluster Analysis -- 3.1 K-means.

3.2 K-medoids.