Intelligent Bioinformatics (eBook)

Edward Keedwell is an Associate Professor in Computer Science. He joined the Computer Science discipline in 2006 having previously been a Research Fellow in the Centre for Water Systems and was appointed as a lecturer in Computer Science in 2009. Ajit Narayanan is the inventor of FreeSpeech, a picture language with a deep grammatical structure. He's also the inventor of Avaz, India's first Augmentative and Alternative Communication device for children with disabilities.

Intelligent Bioinformatics 3
Contents 7
Preface 11
Acknowledgement 13
PART 1 INTRODUCTION 15
1 Introduction to the Basics of Molecular Biology 17
1.1 Basic cell architecture 17
1.2 The structure, content and scale of deoxyribonucleic acid (DNA) 18
1.3 History of the human genome 23
1.4 Genes and proteins 24
1.5 Current knowledge and the ‘central dogma’ 35
1.6 Why proteins are important 37
1.7 Gene and cell regulation 38
1.8 When cell regulation goes wrong 40
1.9 So, what is bioinformatics? 41
1.10 Summary of chapter 42
1.11 Further reading 43
2 Introduction to Problems and Challenges in Bioinformatics 45
2.1 Introduction 45
2.2 Genome 45
2.3 Transcriptome 54
2.4 Proteome 64
2.5 Interference technology, viruses and the immune system 71
2.6 Summary of chapter 77
2.7 Further reading 78
3 Introduction to Artificial Intelligence and Computer Science 79
3.1 Introduction to search 79
3.2 Search algorithms 80
3.3 Heuristic search methods 86
3.4 Optimal search strategies 90
3.5 Problems with search techniques 97
3.6 Complexity of search 98
3.7 Use of graphs in bioinformatics 100
3.8 Grammars, languages and automata 104
3.9 Classes of problems 110
3.10 Summary of chapter 112
3.11 Further reading 113
PART 2 CURRENT TECHNIQUES 115
4 Probabilistic Approaches 117
4.1 Introduction to probability 117
4.2 Bayes’ Theorem 119
4.3 Bayesian networks 125
4.4 Markov networks 130
4.5 Summary of chapter 139
4.6 References 140
5 Nearest Neighbour and Clustering Approaches 141
5.1 Introduction 141
5.2 Nearest neighbour method 144
5.3 Nearest neighbour approach for secondary structure protein folding prediction 146
5.4 Clustering 149
5.5 Advanced clustering techniques 152
5.6 Application guidelines 158
5.7 Summary of chapter 159
5.8 References 160
6 Identification (Decision) Trees 161
6.1 Method 161
6.2 Gain criterion 166
6.3 Over fitting and pruning 171
6.4 Application guidelines 174
6.5 Bioinformatics applications 177
6.6 Background 183
6.7 Summary of chapter 184
6.8 References 184
7 Neural Networks 187
7.1 Method 187
7.2 Application guidelines 199
7.3 Bioinformatics applications 201
7.4 Background 206
7.5 Summary of chapter 207
7.6 References 207
8 Genetic Algorithms 209
8.1 Single-objective genetic algorithms – method 209
8.2 Single-objective genetic algorithms – example 216
8.3 Multi-objective genetic algorithms – method 219
8.4 Application guidelines 221
8.5 Genetic algorithms – bioinformatics applications 224
8.6 Summary of chapter 231
8.7 References and further reading 231
PART 3 FUTURE TECHNIQUES 233
9 Genetic Programming 235
9.1 Method 235
9.2 Application guidelines 244
9.3 Bioinformatics applications 246
9.4 Background 250
9.5 Summary of chapter 250
9.6 References 251
10 Cellular Automata 253
10.1 Method 253
10.2 Application guidelines 259
10.3 Bioinformatics applications 261
10.4 Background 265
10.5 Summary of chapter 266
10.6 References and further reading 266
11 Hybrid Methods 269
11.1 Method 269
11.2 Neural-genetic algorithm for analysing gene expression data 270
11.3 Genetic algorithm and k nearest neighbour hybrid for biochemistry solvation 276
11.4 Genetic programming neural networks for determining gene – gene interactions in epidemiology 279
11.5 Application guidelines 282
11.6 Conclusions 282
11.7 Summary of chapter 283
11.8 References and further reading 283
Index 285

"... coverage of problems and techniques are such that more advanced practitioners' might clearly find interest in parts of this book." (Genetic Programming in Evolvable Machinery, Oct 2006)