Sold Out
Book Categories |
Forewords xi
The DEMETRA Project: An Innovative Contribution to Regulatory QSAR xi
Reference xiv
Preface Emilio Benfenati Mose Casalegno xv
The Pesticides and their Ecotoxicological Properties xv
Moving Forwards the use of QSAR to Predict Toxicological Properties xvi
The DEMETRA Project xvii
The Book Chapters xix
Acknowledgement xx
Disclaimer xx
References xxi
QSARs for regulatory purposes: the case for pesticide authorization Emilio Benfenati Mark Clook Steven Fryday Andy Hart 1
Overview of the Current Pesticide Authorization Procedure 1
Description of the current pesticide legislation (EU Directive 91/414/EEC) 1
Outline of the ecotoxicology tests required for pesticide authorization under 91/414/EEC 3
How frequently are certain studies submitted and how many studies are submitted to address an Annex point? 3
What changes are likely to occur that could alter the frequency and number of toxicity studies submitted? 17
Introduction on QSARS for Pesticides 19
Regulatory Perspectives in the use of QSARs 22
Current use of QSARs in regulation 22
Potential barriers for using QSARs in the pesticide authorization procedure 27
End-user criteria for the use of QSARs in regulatory assessment 29
Quality Criteria for Modelling Ecotoxicity Data 30
Data quality and precision required 30
Quality criteria to be applied to ecotoxicity data used in a QSAR 30
Degree of precision required of QSARs for pesticide assessments 39
Toxicity End-Points with a High Potential to be Replaced with a QSAR Approach 47
Data availability 47
Number of animals tested 48
Study costs 50
End-points with high potential for replacement with a QSAR 51
Priority end-points 54
References 54
Databases for pesticide ecotoxicity Emilio Benfenati Elena Boriani Marian Craciun Ladan Malazizi Daniel Neagu Alessandra Roncaglioni 59
Introduction 59
Data Availability 60
The EPA-OPP database 61
The SEEM database 62
The BBA database 64
Other databases 64
Selection of the Data 65
Key features in the choice of the database 66
Comparison of the data internally to the database 67
Data Representation for Predictive Toxicology 70
A public database example: DSSTox 72
Current toxicity database limitations 72
XML-based standards in chemistry and toxicology 73
PToxML - a simple XML-based description in predictive toxicology 73
The Characteristics of the Final Data Sets 78
Conclusions 78
Acknowledgments 80
References 80
Characterization of chemical structures Emilio Benfenati Mose Casalegno Jane Cotterill Nick Price Morena Spreafico Andrey Toropov 83
Introduction 83
Characterization of Bi-dimensional Structures 85
Preprocessing of compounds in the data set 86
Geometrical isomers 88
Tautomers 88
Characterization of Tri-dimensional Structures 89
Crystallographic data 89
Conformational searching and energy minimization 90
Stereoisomers 93
Procedure for the quality control of the chemicals and chemical structures 94
Chemical Structure File Formats 94
Bi-dimensional descriptors 95
Tri-dimensional descriptors 99
Fragments and Residues in DEMETRA 102
References 107
Algorithms for (Q)SAR model building Qasim Chaudhry Jacques Chretien Marian Craciun Gongde Guo Frank Lemke Johann-Adolf Muller Daniel Neagu Nadege Piclin Marco Pintore Paul Trundle 111
Introduction 111
Methods for Data Pre-Processing and Selecting Descriptors 112
Models with Classifiers 114
FISs 114
Adaptive fuzzy partition 116
k-NN methods 120
Models with Regression Systems 125
Traditional linear regression QSAR models 125
ANNs and fuzzy neural networks 128
Self-organizing statistical-learning networks 134
Conclusions 143
References 144
Hybrid systems Nicolas Amaury Emilio Benfenati Severin Bumbaru Antonio Chana Marian Craciun Jacques R. Chretien Giuseppina Gini Gongde Guo Frank Lemke Viorel Minzu Johann-Adolf Muller Daniel Neagu Marco Pintore Silviu Augustin Stroia Paul Trundle 149
Introduction: Goals of the Hybrid Systems 149
Our Hybrid Approach for Quantitative Structure-Activity Relationship 151
Gating Networks 152
Introduction 152
Gating networks for predictive toxicology - a new approach based on descriptors clustering 154
Hybrid neural fuzzy systems 157
Gating networks as HISs - a data-driven approach 159
Multi-Classifier Systems 160
Approaches for multi-classifier systems 161
An architecture of MCS 162
Classifiers 163
Combination Methods 163
Distributed multi-classifier systems 165
Neural Ik- and Ek-Based Systems - Introduction of the Prototype NIKE 167
Experiment 1 173
Experiment 2 174
Rule-Based Systems 175
Self-Organizing Statistical Learning Networks 177
Conclusions 180
References 180
Validation of the models Emilio Benfenati Jacques R. Chretien Giuseppina Gini Nadege Piclin Marco Pintore Alessandra Roncaglioni 185
Introduction 185
Selection of the Training and Test Sets 186
Internal Validation and Robustness 187
External Validation 189
Validation Parameters for Classifiers: Matrix of Confusion 191
Graphical Evaluation of the Models: The Receiver Operating Characteristic and Regression Error Characteristic Curves 192
How to Deal with False Negatives/False Positives 196
The Applicability Domain 197
References 198
Results of DEMETRA models Nicolas Amaury Emilio Benfenati Elena Boriani Mose Casalegno Antonio Chana Qasim Chaudhry Jacques R. Chretien Jane Cotterill Frank Lemke Nadege Piclin Marco Pintore Chiara Porcelli Nicholas Price Alessandra Roncaglioni Andrey Toropov 201
Overview of Results with the Regression Approach 201
Overview of the Prediction Results Obtained by Classification Methods 208
Data sets and toxicity intervals 208
Descriptors selection and classification results 208
Conclusions about classification results 214
Overview of Results of Local Models 215
Chemical classes 215
Overview of Results Obtained with the Hybrid Models 221
Hybrid model for rainbow trout 222
Outliers and the applicability domain 226
Hybrid model for water flea (Daphnia magna) 249
Hybrid model for quail: oral exposure 266
Hybrid model for quail: dietary exposure 269
Hybrid model for acute contact toxicity of honey bee 274
Conclusions 279
Acknowledgments 280
References 281
The quality criteria of the DEMETRA models for regulatory purposes Emilio Benfenati 283
The OECD Guidelines for QSAR Models 283
Introduction 283
The identification of the regulation 284
The criteria for the endpoint selection 284
The model utility 285
The endpoint selection: identification of the guidelines 285
The accordance of the toxicity data to the guidelines 286
The check of quality data 286
The definition of the model components. OECD principle number 2: an unambiguous algorithm 286
The selection of the toxicity values of the data set 287
The characterization of the uncertainty of the experimental data 287
The chemical structures 288
The chemical descriptors 289
The algorithms 289
The performances of the model 289
The reproducibility of the models 290
The false-negative issue 290
The applicability domain 291
The quality control 292
The use of the model 292
The Specificity of the QSAR Models for Regulatory Purposes 292
The Probabilistic Meaning of the Model, the Prediction of the Effect, and the Prediction of the Mechanism 295
The probabilistic nature of the models 295
The mechanistic basis of the models 296
The final model and the ways to obtain it 297
The Benefits of the DEMETRA Models 297
Future Perspectives 298
References 301
The use of the DEMETRA models Emilio Benfenati Marian Craciun Daniel Neagu 303
Introduction 303
The Users of the DEMETRA Models 303
Ownership of the Software 304
Using DEMETRA Models 306
Chemical Restrictions of the DEMETRA Models 307
The Format for Model Presentation for DEMETRA: HISML 308
References 312
Appendices 315
Summary of responses to DEMETRA survey 317
Toxicity values for five ECOTOX data sets for pesticide 323
Example procedures in molecular modelling 463
The descriptors selected for each data set 469
List of abbreviations 487
Software tool for toxicity prediction of pesticides, candidate pesticides, and their derivatives (user guide) 493
Index 505
Login|Complaints|Blog|Games|Digital Media|Souls|Obituary|Contact Us|FAQ
CAN'T FIND WHAT YOU'RE LOOKING FOR? CLICK HERE!!! X
You must be logged in to add to WishlistX
This item is in your Wish ListX
This item is in your CollectionQuantitative Structure-Activity Relationships (QSAR) for Pesticide Regulatory Purposes
X
This Item is in Your InventoryQuantitative Structure-Activity Relationships (QSAR) for Pesticide Regulatory Purposes
X
You must be logged in to review the productsX
X
X
Add Quantitative Structure-Activity Relationships (QSAR) for Pesticide Regulatory Purposes, , Quantitative Structure-Activity Relationships (QSAR) for Pesticide Regulatory Purposes to the inventory that you are selling on WonderClubX
X
Add Quantitative Structure-Activity Relationships (QSAR) for Pesticide Regulatory Purposes, , Quantitative Structure-Activity Relationships (QSAR) for Pesticide Regulatory Purposes to your collection on WonderClub |