Computational Intelligence in Bioinformatics

by Fogel, Gary B.; Corne, David W.; Pan, Yi

• ISBN13: 9780470105269
• ISBN10: 0470105267
• Edition: 1st
• Format: Hardcover
• Copyright: 2007-12-10
• Publisher: Wiley-IEEE Press

Summary

Combining biology, computer science, mathematics, and statistics, the field of bioinformatics has become a hot new discipline with profound impacts on all aspects of biology and industrial application. Now, Computational Intelligence in Bioinformatics offers an introduction to the topic, covering the most relevant and popular CI methods, while also encouraging the implementation of these methods to readers' research.

Author Biography

Gary B. Fogel, PhD, is Vice President of Natural Selection, Inc., and his current research interests focus on the application of computational intelligence methods to problems in the biomedical sciences. He is a senior member of the IEEE and serves as an Associate Editor on three IEEE journals.

David W. Corne holds a Chair in Computer Science at Heriot-Watt University, Edinburgh, Scotland, and his research interests include evolutionary computation, multi-objective optimization, bioinformatics, telecommunications, and general aspects and applications of nature-inspired computation.

Yi Pan, PhD, is Chair and Professor of Computer Science at Georgia State University and his research interests include high-performance computing, networking, and bioinformatics. Dr. Pan has coedited over twenty books and his recent research has been supported by the NSF, NIH, NSFC, AFOSR, AFRL, JSPS, IISF, and the states of Georgia and Ohio.

Table of Contents

Preface	p. xi
Contributors	p. xvii
Gene Expression Analysis and Systems Biology
Hybrid of Neural Classifier and Swarm Intelligence in Multiclass Cancer Diagnosis with Gene Expression Signatures	p. 3
Introduction	p. 3
Methods and Systems	p. 4
Experimental Results	p. 12
Conclusions	p. 17
References	p. 18
Classifying Gene Expression Profiles with Evolutionary Computation	p. 21
DNA Microarray Data Classification	p. 21
Evolutionary Approach to the Problem	p. 25
Gene Selection with Speciated Genetic Algorithm	p. 28
Cancer Classifiction Based on Ensemble Genetic Programming	p. 31
Conclusion	p. 37
References	p. 38
Finding Clusters in Gene Expression Data Using EvoCluster	p. 41
Introduction	p. 41
Related Work	p. 43
Evolutionary Clustering Algorithm	p. 44
Experimental Results	p. 51
Conclusions	p. 61
References	p. 63
Gene Networks and Evolutionary Computation	p. 67
Introduction	p. 67
Evolutionary Optimization	p. 70
Computational Network Modeling	p. 76
Extending Reach of Gene Networks	p. 85
Network Topology Analysis	p. 88
Summary	p. 90
References	p. 91
Sequence Analysis and Feature Detection
Fuzzy-Granular Methods for Identifying Marker Genes from Microarray Expression Data	p. 99
Introduction	p. 99
Traditional Algorithms for Gene Selection	p. 100
New Fuzzy-Granular-Based Algorithm for Gene Selection	p. 102
Simulation	p. 107
Conclusions	p. 112
References	p. 113
Evolutionary Feature Selection for Bioinformatics	p. 117
Introduction	p. 117
Evolutionary Algorithms for Feature Selection	p. 119
Feature Selection for Clustering in Bioinformatics	p. 122
Feature Selection for Classification in Bioinformatics	p. 127
Frameworks and Data Sets	p. 133
Conclusion	p. 136
References	p. 136
Fuzzy Approaches for the Analysis CpG Island Methylation Patterns	p. 141
Introduction	p. 141
Methods	p. 144
Biological Significance	p. 158
Conclusions	p. 162
References	p. 163
Molecular Structure and Phylogenetics
Protein-Ligand Docking with Evolutionary Algorithms	p. 169
Introduction	p. 169
Biochemical Background	p. 170
The Docking Problem	p. 176
Protein-Ligand Docking Algorithms	p. 179
Evolutionary Algorithms	p. 182
Effect of Variation Operators	p. 185
Differential Evolution	p. 186
Evaluating Docking Methods	p. 189
Comparison between Docking Methods	p. 189
Summary	p. 190
Future Research Topics	p. 191
References	p. 191
RNA Secondary Structure Prediction Employing Evolutionary Algorithms	p. 197
Introduction	p. 197
Thermodynamic Models	p. 200
Methods	p. 206
Results	p. 209
Conclusion	p. 219
References	p. 221
Machine Learning Approach for Prediction of Human Mitochondrial Proteins	p. 225
Introduction	p. 225
Methods and Systems	p. 229
Results and Discussion	p. 231
Conclusions	p. 234
References	p. 235
Phylogenetic Inference Using Evolutionary Algorithms	p. 237
Introduction	p. 237
Background in Phylogenetics	p. 238
Challenges and Opportunities for Evolutionary Computation	p. 244
One Contribution of Evolutionary Computation: Graphyl	p. 245
Some Other Contributions of Evolutionary computation	p. 256
Open Questions and Opportunities	p. 258
References	p. 260
Medicine
Evolutionary Algorithms for Cancer Chemotherapy Optimization	p. 265
Introduction	p. 265
Nature of Cancer	p. 266
Nature of Chemotherapy	p. 267
Models of Tumor Growth and Response	p. 268
Constraints on Chemotherapy	p. 270
Optimal Control Formulations of Cancer Chemotherapy	p. 271
Evolutionary Algorithms for Cancer Chemotherapy Optimization	p. 275
Encoding and Evaluation	p. 276
Applications of EAs to Chemotherapy Optimization Problems	p. 280
Related Work	p. 288
Oncology Workbench	p. 291
Conclusion	p. 293
References	p. 294
Fuzzy Ontology-Based Text Mining System for Knowledge Acquisition, Ontology Enhancement, and Query Answering from Biomedical Texts	p. 297
Introduction	p. 297
Brief Introduction to Ontologies	p. 303
Information Retrieval form Biological Text Documents: Related Work	p. 305
Ontology-Based IE and Knowledge Enhancement System	p. 309
Document Processor	p. 311
Biological Relation Extractor	p. 313
Relation-Based Query Answering	p. 318
Evaluation of the Biological Relation Extraction Process	p. 321
Biological Relation Characterizer	p. 323
Determining Strengths of Generic Biological Relations	p. 331
Enhancing GENIA to Fuzzy Relational Ontology	p. 334
Conclusions and Future Work	p. 334
References	p. 336
Feasible Biological Relations	p. 338
Index	p. 341
Table of Contents provided by Ingram. All Rights Reserved.