Genetic Algorithm s in Molecular Modeling This Page Intentionally Left Blank (cid:9)(cid:9)(cid:9)(cid:9)(cid:9) Principles of QSAR and Drug Design GENETIC ALGORITHM S I N MOLECULAR MODELIN G Edited by James Devillers CTIS, Lyon, France ACADEMIC PRESS Harcourt Brace & Company, Publishers London San Diego New York Boston Sydney Tokyo Toronto ACADEMIC PRESS LIMITED 24—28 Oval Road London NW1 7DX United States Edition published by ACADEMIC PRESS INC. San Diego, CA 92101 Copyright © 1996 by ACADEMIC PRESS LIMITED All Rights Reserved No part of this book may be reproduced in any form by photostat, microfilm, or by any other means, without written permission from the publishers This book is printed on acid free paper A catalogue record of this book is available from the British Library ISBN 0—12—213810—4 Typeset by Florencetype Ltd, Stoodleigh, Devon Printed and bound in Great Britain by Hartnolls Ltd, Bodmin, Cornwall (cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9) Contents Contributors ix Preface xi 1 Genetic Algorithms in Computer-Aided Molecular Design 1 J. Devillers Abstract 1 Introduction 1 Classes of Search Techniques 2 Mechanics of Simple Genetic Algorithms 4 Applications of Genetic Algorithms in QSAR and Drug Design 11 Software Availability 14 Advantages and Limitations of Genetic Algorithms 20 References 21 2 An Overview of Genetic Methods 35 B.T. Luke Abstract 35 Introduction 35 Genetic Alphabet and Genes 38 Focusing and Similarity 42 Creating an Initial Population 44 Building a Mating Population 45 Choosing a Parent 46 Mating 46 Mutation Operator 50 Maturation Operator 52 Process Offspring 53 Updating the Population 55 Summary 56 Review of Various Published Algorithms 58 Conclusion 64 References 64 3 Genetic Algorithms in Feature Selection 67 R. Leardi Abstract 67 (cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9) vi Contents About Feature Selection 67 Application of Genetic Algorithms to Feature Selection 68 Classical Methods of Feature Selection vs Genetic Algorithms 69 Configuration of a Genetic Algorithm for Feature Selection 70 The Hybridization with Stepwise Selection 74 The Problem of Full-Validation 77 Two QSAR Examples 78 Acknowledgements 85 References 86 4 Some Theory and Examples of Genetic Function Approximation with Comparison to Evolutionary Techniques 87 D. Rogers Abstract 87 Introduction 87 Genetic Function Approximation 88 Comments on the Lack-Of-Fit Measure 89 Nonlinear Modeling 92 GFA versus PLS Modeling 98 Comparison of GFA with other Genetic and Evolutionary Methods 100 Conclusions 104 Acknowledgments 106 References 106 5 Genetic Partial Least Squares in QSAR 109 W.J. Dunn and D. Rogers Abstract 109 Introduction 109 Background 110 PLS 111 Genetic Algorithms 112 Genetic Partial Least Squares 115 Outlier Limiting 116 Case Study 118 Conclusion 128 References 129 6 Application of Genetic Algorithms to the General QSAR Problem and to Guiding Molecular Diversity Experiments 131 A.J. Hopfinger and H.C. Patel Abstract 131 Introduction and Background 132 Methods 132 Results 139 Concluding Remarks 154 (cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9) Contents vii Acknowledgments 155 References 156 7 Prediction of the Progesterone Receptor Binding of Steroids Using a Combination of Genetic Algorithms and Neural Networks 159 S.P. van Helden, H. Hamersma, and V.J. van Geerestein Abstract 159 Introduction 160 Experimental 162 Results 177 Concluding Remarks 189 References 190 8 Genetically Evolved Receptor Models (GERM): A Procedure for Construction of Atomic-Level Receptor Site Models in the Absence of a Receptor Crystal Structure 193 D.E. Walters and T.D. Muhammad Abstract 193 Introduction 194 Methods 195 Results and Discussion 202 Conclusion 209 Acknowledgments 209 References 209 9 Genetic Algorithms for Chemical Structure Handling and Molecular Recognition 211 G. Jones, P. Willett, and R.C. Glen Abstract 211 Introduction 212 3-D Conformational Search 212 Flexible Ligand Docking 219 Flexible Molecular Overlay and Pharmacophore Elucidation 226 Conclusions 238 Acknowledgements 239 References 239 10 Genetic Selection of Aromatic Substituents for Designing Test Series 243 C. Putavy, J. Devillers, and D. Domine Abstract 243 Introduction 243 Materials and Methods 244 (cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9)(cid:9) viii Contents Results and Discussion 251 Conclusion 267 References 267 11 Computer-Aided Molecular Design Using Neural Networks and Genetic Algorithms 271 V. Venkatasubramanian, A. Sundaram, K. Chan, and J.M. Caruthers Abstract 271 Introduction 272 The Forward Problem Using Neural Networks 275 Genetic Algorithms for the Inverse Problem 286 Characterization of the Search Space 292 An Interactive Framework for Evolutionary Design 297 Conclusions 298 References 300 12 Designing Biodegradable Molecules from the Combined Us e of a Backpropagation Neural Network and a Genetic Algorithm 30 3 J. Devillers and C. Putavy Abstract 303 Introduction 303 Background 304 Results and Discussion 309 Conclusion 312 References 312 Annexe 315 Index 325 A colour plate section appears between pages 212-213. Contributors J.M. Caruthers, Laboratory for Intelligent Process Systems, School of Chemical Engineering, Purdue University, West Lafayette, IN 47907, USA. K. Chan, Laboratory for Intelligent Process Systems, School of Chemical Engineering, Purdue University, West Lafayette, IN 47907, USA . J. Devillers, CTIS, 21 rue de la Banniere, 69003 Lyon, France. D. Domine, CTIS, 21 rue de la Banniere, 69003 Lyon, France . W.J. Dunn, College of Pharmacy, University of Illinois at Chicago, 833 S. Wood Street, Chicago, IL 60612, USA. R.C. Glen, Tripos Inc., St Louis, MO 63144, USA. H. Hamersma, Department of Computational Medicinal Chemistry, NV Organon, P.O. Box 20, 5340 BH Oss, The Netherlands. A.J. Hopfinger, Laboratory of Molecular Modeling and Design, M/C 781 , The University of Illinois at Chicago, College of Pharmacy, 833 S. Wood Street, Chicago, IL 60612-7231, USA. G. Jones, Krebs Institute for Biomolecular Research and Department o f Information Studies, University of Sheffield, Western Bank, Sheffield S10 2TN, UK. R. Leardi, Istituto di Analisi e Tecnologie Farmaceutiche ed Alimentari, University di Genova, via Brigata Salerno (ponte), I—16147 Genova, Italy. B.T. Luke, International Business Machines Corporation, 522 South Road , Poughkeepsie, NY 12601, USA. T.D. Muhammad, Department of Biological Chemistry, Finch University of Health Sciences/The Chicago Medical School, 3333 Green Bay Road, North Chicago, IL 60064, USA. H.C. Patel, Laboratory of Molecular Modeling and Design, M/C 781, The University of Illinois at Chicago, College of Pharmacy, 833 S. Wood Street, Chicago, IL 60612-7231, USA. C. Putavy, CTIS, 21 rue de la Banniere, 69003 Lyon, France. D. Rogers, Molecular Simulations Incorporated, 9685 Scranton Road, San Diego, CA 92121, USA. A. Sundaram, Laboratory for Intelligent Process Systems, School of Chemical Engineering, Purdue University, West Lafayette, IN 47907, USA. V.J. van Geerestein, Department of Computational Medicinal Chemistry, NV Organon, P.O. Box 20, 5340 BH Oss, The Netherlands. S.P. van Helden, Department of Computational Medicinal Chemistry, N V Organon, P.O. Box 20, 5340 BH Oss, The Netherlands.
Description: