Algorithmic and Artificial Intelligence Methods for Protein Bioinformatics

✍ Scribed by Yi Pan, Jianxin Wang, Min Li

• Publisher: Wiley-IEEE Computer Society Pr
• Year: 2013
• Tongue: English
• Leaves: 708
• Edition: 1
• Category: Library

✦ Synopsis

An in-depth look at the latest research, methods, and applications in the field of protein bioinformatics

This book presents the latest developments in protein bioinformatics, introducing for the first time cutting-edge research results alongside novel algorithmic and AI methods for the analysis of protein data. In one complete, self-contained volume, Algorithmic and Artificial Intelligence Methods for Protein Bioinformatics addresses key challenges facing both computer scientists and biologists, arming readers with tools and techniques for analyzing and interpreting protein data and solving a variety of biological problems.

Featuring a collection of authoritative articles by leaders in the field, this work focuses on the analysis of protein sequences, structures, and interaction networks using both traditional algorithms and AI methods. It also examines, in great detail, data preparation, simulation, experiments, evaluation methods, and applications. Algorithmic and Artificial Intelligence Methods for Protein Bioinformatics:

• Highlights protein analysis applications such as protein-related drug activity comparison
• Incorporates salient case studies illustrating how to apply the methods outlined in the book
• Tackles the complex relationship between proteins from a systems biology point of view
• Relates the topic to other emerging technologies such as data mining and visualization
• Includes many tables and illustrations demonstrating concepts and performance figures

Algorithmic and Artificial Intelligence Methods for Protein Bioinformatics is an essential reference for bioinformatics specialists in research and industry, and for anyone wishing to better understand the rich field of protein bioinformatics.

✦ Table of Contents

Cover......Page 1
Series......Page 12
Title Page......Page 13
Copyright......Page 14
Preface......Page 16
Contributors......Page 22
Part I: From Protein Sequence to Structure......Page 26
1.1 Introduction......Page 27
1.2 Evolutionary Developmental (Evo-Devo) Roles in Embryogenesis of Plants (in Developmental Plant Genetic Toolkit Formation)......Page 28
1.3 Phases in Embryogenesis in Arabidopsis Thaliana......Page 29
1.4 Analysis......Page 48
1.5 Conclusions......Page 60
References......Page 62
Bibliography......Page 67
2.1 Introduction......Page 70
2.2 Granule Computing Approaches......Page 72
2.3 Experimental Setup......Page 76
2.4 Protein Sequence Motif Information Discovered by FGK Model......Page 81
References......Page 86
3.1 Introduction......Page 89
3.2 Methods......Page 91
3.3 Results and Discussion......Page 101
3.4 Conclusion......Page 104
References......Page 105
4.1 Introduction......Page 108
4.2 Protein and Methylation......Page 109
4.3 Related Works on Methylation Prediction......Page 111
4.4 Conclusion......Page 127
References......Page 129
5.1 Introduction......Page 134
5.2 Musite: A Machine Learning Approach......Page 138
5.3 Musite Implementation......Page 144
5.4 Summary......Page 147
References......Page 148
Part II: Protein Analysis and Prediction......Page 156
6.2 Structural Cluster Approach......Page 157
6.3 Sequence Cluster Approach......Page 158
6.4 Support Vector Machines for Local Protein Structure Prediction......Page 159
6.5 Clustering Support Vector Machines for Local Protein Structure Prediction......Page 160
6.6 Experimental Results......Page 166
References......Page 173
7.1 Introduction......Page 176
7.2 Background......Page 177
7.3 New Binary Classifiers for Protein Structural Boundary Prediction......Page 182
References......Page 205
8.1 Introduction......Page 210
8.2 Background......Page 211
8.3 Framework of Prediction......Page 213
8.4 Description Features of Protein RNA Binding Sites......Page 216
8.5 Existing Methods......Page 224
8.6 Feature Analysis and Comparison Study......Page 225
8.7 Conclusion......Page 229
References......Page 230
9.1 Introduction......Page 234
9.2 Determining Disulfide Bonds from Sequence Information: Formulations, Features, and Algorithmic Frameworks......Page 236
9.3 Algorithmic Methods for Determining Disulfide Bonds Using Mass Spectrometry......Page 246
9.4 Experimental Results......Page 264
9.5 Conclusions and Future Directions......Page 271
References......Page 273
10.1 Introduction......Page 277
10.2 Correlated protein properties......Page 278
10.3 Other contact measurements......Page 279
10.4 Contact order calculation......Page 283
10.5 Contact order prediction by homology......Page 284
10.6 Contact order prediction from sequence......Page 285
10.7 The public contact order web server......Page 287
References......Page 288
11.1 Introduction......Page 293
11.2 Survey of Previous Efforts to Predict Bonding State of Cysteine Residues on Protein Via Computational Approaches......Page 296
References......Page 307
12.1 Introduction......Page 312
12.2 Iterative image reconstruction methods......Page 314
12.3 Adaptive simultaneous algebraic reconstruction technique (ASART)......Page 318
12.4 Multilevel parallel strategy for iterative reconstruction algorithm......Page 325
12.5 Experimental results and discussion......Page 331
12.6 Summary......Page 337
References......Page 339
Part III: Protein Structure Alignment and Assessment......Page 343
13.2 Biological Motivation of Protein Structure Alignment......Page 344
13.3 Mathematical Frameworks......Page 350
13.4 More Recent Advances with Database Queries......Page 357
References......Page 377
14.1 Introduction......Page 380
14.2 Protein Structure......Page 381
14.3 Protein Databases......Page 385
14.4 Vector Space Model......Page 387
14.5 Suffix Trees......Page 390
14.6 Indexing 3D Protein Structures......Page 393
14.7 Protein Similarity Algorithm......Page 396
References......Page 399
15.1 Introduction......Page 405
15.2 Structural Alignment......Page 407
15.3 Global Sequence Order–Independent Structural Alignment......Page 409
15.4 Local Sequence Order–Independent Structural Alignment......Page 416
15.5 Conclusion......Page 425
References......Page 426
16.1 Introduction......Page 432
16.2 Methods......Page 435
16.3 Results and conclusions......Page 453
References......Page 457
17.1 Introduction......Page 463
17.2 Overview of Protein Model Assessment......Page 464
17.3 Design and Method......Page 468
17.4 Implementation Using Svm......Page 470
17.5 Implementation Using IFID3......Page 475
17.6 Conclusion......Page 477
References......Page 479
Bibliography......Page 482
Part IV: Protein–Protein Analysis of Biological Networks......Page 483
18.1 Introduction......Page 484
18.2 Optimization approaches to clustering......Page 485
18.3 Hierarchical algorithms......Page 495
18.4 Features of PPI networks......Page 498
18.5 Implementation of hierarchical methods......Page 501
18.6 Conclusion......Page 506
References......Page 507
19.1 Introduction......Page 511
19.2 Density-Based and Local Search Methods......Page 512
19.3 Hierarchical Clustering Methods......Page 515
19.4 Finding Overlapping Clusters......Page 520
19.5 Identification of Protein Complexes by Integrating Multiple Biological Sources......Page 522
19.6 Identifying Protein Complexes From Dynamic PPI Network......Page 524
19.7 Challenges and Future Research......Page 526
References......Page 527
Chapter 20: Protein Functional Module Analysis With Protein–Protein Interaction (PPI) Networks......Page 533
20.1 Introduction......Page 534
20.2 Properties of PPI Networks......Page 536
20.3 Previous Module Detection Approaches......Page 540
20.4 Weighted Graph Model of Protein Interaction Networks......Page 544
20.5 Theories and Methods......Page 548
20.6 Experimental Results......Page 553
References......Page 555
21.1 Introduction......Page 559
21.2 An overview of metabolic network alignment and mining approaches......Page 561
21.3 Generalized Network Alignment Problem......Page 564
21.4 A generalized dynamic programming algorithm......Page 567
21.5 Predicting pathway holes and resolving enzyme ambiguity......Page 578
References......Page 580
22.1 Introduction......Page 584
22.2 Preliminaries......Page 591
22.3 METHODS (Point 5)......Page 595
22.4 Coarse-Grain Comparison......Page 602
References......Page 605
Part V: Application of Protein Bioinformatics......Page 610
23.1 Introduction......Page 611
23.2 Related Studies for Pyrimidines Drug Activity Comparison......Page 612
23.3 Feature Granules and Hierarchical Kernel Design......Page 615
23.4 Experimental Results for Different Machine Learning Models......Page 620
23.5 Summary......Page 621
References......Page 622
24.1 Introduction......Page 623
24.2 The Biological Networks Domain......Page 625
24.3 Problem Formulation......Page 630
24.4 Methods......Page 636
24.5 Concluding Remarks......Page 643
References......Page 644
25.1 Introduction......Page 650
25.2 Resource Content......Page 653
25.3 Summary and Conclusion......Page 663
References......Page 666
26.1 Introduction......Page 670
26.2 Gene expression signatures......Page 672
26.3 Biological Network–based identification of gene expression signatures......Page 676
26.4 Biological Network–based integration of gene expression signatures......Page 679
26.5 Discussion and Conclusion......Page 681
References......Page 682
Index......Page 686
Series......Page 707