Neural Networks in QSAR and Drug Design (eBook)

James Devillers (Autor)

eBook Download: PDF

1996 | 1. Auflage
284 Seiten
Elsevier Science (Verlag)
978-0-08-053738-2 (ISBN)

Infos

Comprehensive and impeccably edited, Neural Networks in QSAR and Drug Design is the first book to present an all-inclusive coverage of the topic. The book provides a practice-oriented introduction to the different neural network paradigms, allowing the reader to easily understand and reproduce the results demonstrated. Numerous examples are detailed, demonstrating a variety of applications to QSAR and drug design.
The contributors include some of the most distinguished names in the field, and the book provides an exhaustive bibliography, guiding readers to all the literature related to a particular type of application or neural network paradigm. The extensive index acts as a guide to the book, and makes retrieving information from chapters an easy task. A further research aid is a list of software with indications of availablility and price, as well as the editors scale rating the ease of use and interest/price ratio of each software package. The presentation of new, powerful tools for modeling molecular properties and the inclusion of many important neural network paradigms, coupled with extensive reference aids, makes Neural Networks in QSAR and Drug Design an essential reference source for those on the frontiers of this field.

Key Features
* Presents the first coverage of neural networks in QSAR and Drug Design
* Allows easy understanding and reproduction of the results described within
* Includes an exhaustive bibliography with more than 200 references
* Provides a list of applicable software packages with availability and price

---

Comprehensive and impeccably edited, Neural Networks in QSAR and Drug Design is the first book to present an all-inclusive coverage of the topic. The book provides a practice-oriented introduction to the different neural network paradigms, allowing the reader to easily understand and reproduce the results demonstrated. Numerous examples are detailed, demonstrating a variety of applications to QSAR and drug design.The contributors include some of the most distinguished names in the field, and the book provides an exhaustive bibliography, guiding readers to all the literature related to a particular type of application or neural network paradigm. The extensive index acts as a guide to the book, and makes retrieving information from chapters an easy task. A further research aid is a list of software with indications of availablility and price, as well as the editors scale rating the ease of use and interest/price ratio of each software package. The presentation of new, powerful tools for modeling molecular properties and the inclusion of many important neural network paradigms, coupled with extensive reference aids, makes Neural Networks in QSAR and Drug Design an essential reference source for those on the frontiers of this field. - Presents the first coverage of neural networks in QSAR and Drug Design- Allows easy understanding and reproduction of the results described within- Includes an exhaustive bibliography with more than 200 references- Provides a list of applicable software packages with availability and price

Inhalt

Front Cover 1
Neural Networks in QSAR and Drug Design 4
Copyright Page 5
Contents 6
Contributors 10
Preface 12
Chapter 1. Strengths and Weaknesses of the Backpropagation Neural Network in QSAR and QSPR Studies 14
Abstract 14
Introduction 14
Standard BNN Algorithm 16
Designing the Model 19
Selection of the Best BNN Model 28
Comparison of the Performances of a BNN Model with those Obtained with other Approaches 31
Software Availability 33
Hybrid Systems with BNN 33
Conclusion 36
Annex: Artificial Neural Networks (ANNs) on Internet 37
References 37
Chapter 2. AUTOLOGP Versus Neural Network Estimation of n-Octanol/Water Partition Coefficients 60
Abstract 60
Introduction 60
Materials and Methods 62
Results and Discussion 66
Concluding Remarks 70
References 71
Chapter 3. Use of a Backpropagation Neural Network and Autocorrelation Descriptors for Predicting the Biodegradation of Organic Chemicals 78
Abstract 78
Introduction 78
Biodegradation Data 79
Molecular Descriptors 89
Statistics 91
Modeling Results 92
References 94
Chapter 4. Structure–Bell-Pepper Odor Relationships for Pyrazines and Pyridines Using Neural Networks 96
Abstract 96
Introduction 97
Materials and Methods 98
Results and Discussion 103
Conclusion 105
References 106
Chapter 5. A Neural Structure–Odor Threshold Model for Chemicals of Environmental and Industrial Concern 110
Abstract 110
Introduction 111
Materials and Methods 112
Results and Discussion 122
Concluding Remarks 127
References 128
Chapter 6. Adaptive Resonance Theory Based Neural Networks Explored for Pattern Recognition Analysis of QSAR Data 132
Abstract 132
Introduction 133
Neuro-Physiological Basis of ART 134
Taxonomy and State-of-the-Art 135
Theory of ART-2a and FuzzyART 137
Data Preprocessing by Complement Coding 141
Quantification or Qualification? 142
Case Study I: Classification of Rose Varieties from their Headspace Analysis 143
Case Study II: Optimal Selection of Aliphatic Substituents 151
Conclusions 160
References 160
Chapter 7. Multivariate Data Display Using Neural Networks 170
Abstract 170
Introduction 170
Methods 172
Results and Discussion 180
Conclusions 186
References 187
Chapter 8. Quantitative Structure–Activity Relationships of Nicotinic Agonists 190
Abstract 190
Introduction 191
Methods 194
Results 201
Discussion 209
References 217
Chapter 9. Evaluation of Molecular Surface Properties Using a Kohonen Neural Network 222
Abstract 222
Introduction 222
Materials and Methods 223
Kohonen Network 224
Template Approach 225
From a 3D-Space to a 2D-Map 226
Clustering of the Structures by an Investigation of their Maps 228
In Search of the Bioactive Conformation, the Best Superposition, SAR 230
Conclusions 233
References 234
Chapter 10. A New Nonlinear Neural Mapping Technique for Visual Exploration of QSAR Data 236
Abstract 236
Introduction 236
Background 238
Case Study I: Analysis of Sensor Data 244
Case Study II: Optimal Test Series Design 250
Concluding Remarks 259
References 259
Chapter 11. Combining Fuzzy Clustering and Neural Networks to Predict Protein Structural Classes 268
Abstract 268
Introduction 269
Methodology 270
Results and Discussion 279
Caveats and Conclusions 288
References 290
Index 294
Color Plate Section 298

Produkt-Details

• Erscheint lt. Verlag: 9.8.1996
• Sprache: englisch
• Themenwelt: Geisteswissenschaften ► Psychologie ► Klinische Psychologie
• Themenwelt: Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
• Themenwelt: Medizin / Pharmazie ► Gesundheitsfachberufe
• Themenwelt: Medizin / Pharmazie ► Medizinische Fachgebiete ► Neurologie
• Themenwelt: Medizin / Pharmazie ► Medizinische Fachgebiete ► Pharmakologie / Pharmakotherapie
• Themenwelt: Medizin / Pharmazie ► Medizinische Fachgebiete ► Psychiatrie / Psychotherapie
• Themenwelt: Studium ► 2. Studienabschnitt (Klinik) ► Pharmakologie / Toxikologie
• Themenwelt: Naturwissenschaften ► Biologie ► Biochemie
• Themenwelt: Naturwissenschaften ► Chemie ► Anorganische Chemie
• Themenwelt: Naturwissenschaften ► Chemie ► Organische Chemie
• Themenwelt: Naturwissenschaften ► Chemie ► Physikalische Chemie
• Themenwelt: Naturwissenschaften ► Chemie ► Technische Chemie
• Themenwelt: Technik
• Themenwelt: Weitere Fachgebiete ► Land- / Forstwirtschaft / Fischerei
• ISBN-10: 0-08-053738-3 / 0080537383
• ISBN-13: 978-0-08-053738-2 / 9780080537382