Chapter 5: Genetic algorithms based CAMD

This chapter discusses the genetic algorithms (GAs) based computer-aided molecular design (CAMD). GA performs a guided stochastic search, where improved solutions are achieved by sampling the areas of the search space that have a higher probability for good solutions. GAs allow for the direct incorporation of higher-level chemical knowledge and reasoning strategies to make the search more efficient. A background of GAs and the implementation of GA-based search are presented followed by a discussion on the theory behind genetic search. Two polymer design case studies are discussed and an evolutionary design framework based on GAs is presented for the problems. The chapter discusses the five main aspects of the procedure of implementation of a genetic algorithm or a genetic program—namely, (1) genetic encoding, (2) assignment of fitness, (3) selection of parents for reproduction, (4) genetic operations, and (5) replacement of existing chromosomes with newly evolved ones. There are broadly two schools of thought as to the reason genetic algorithms really work: schema theory and building block hypothesis. Recently, a generalization of the schema theory called “forma analysis” has been proposed. Genetic encoding is the process of devising a one-to-one, invertible map, φ that represents every point in the original state space, Ω of the problem in a corresponding point in the genetic space, Ψ. The process of creation of offspring chromosomes from parents is achieved by means of genetic operators. For the studies, three target polymers were selected that offered different levels of difficulty in design: polyethylene terephthalate (PET), poly(vinylidene propylene) copolymer (PVP), and polycarbonate of bisphenol-A (PC). Polyethylene terephthalate is the simplest and the polycarbonate is the most difficult of the three.

[1]  Kyle V. Camarda,et al.  Design of novel pharmaceutical products via combinatorial optimization , 2000 .

[2]  L. Darrell Whitley,et al.  An Executable Model of a Simple Genetic Algorithm , 1992, FOGA.

[3]  Lemont B. Kier,et al.  Design of molecules from quantitative structure-activity relationship models. 1. Information transfer between path and vertex degree counts , 1993, J. Chem. Inf. Comput. Sci..

[4]  John J. Grefenstette,et al.  Optimization of Control Parameters for Genetic Algorithms , 1986, IEEE Transactions on Systems, Man, and Cybernetics.

[5]  H. Wiener.  Structural determination of paraffin boiling points. , 1947, Journal of the American Chemical Society.

[6]  R. Gani,et al.  A group contribution approach to computer‐aided molecular design , 1991 .

[7]  Nikolai S. Zefirov,et al.  General methodology and computer program for the exhaustive restoring of chemical structures by molecular connectivity indexes. Solution of the inverse problem in QSAR/QSPR , 1990 .

[8]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[9]  Mahmoud M. El-Halwagi,et al.  Computer-aided synthesis of polymers and blends with target properties , 1996 .

[10]  Igor I. Baskin,et al.  Inverse problem in QSAR/QSPR studies for the case of topological indexes characterizing molecular shape (Kier indices) , 1993, J. Chem. Inf. Comput. Sci..

[11]  Venkat Venkatasubramanian,et al.  Computer-aided molecular design using genetic algorithms , 1994 .

[12]  Venkat Venkatasubramanian,et al.  Integrated product engineering: a hybrid evolutionary framework , 2000 .

[13]  Sam Kwong,et al.  Genetic Algorithms : Concepts and Designs , 1998 .

[14]  Lemont B. Kier,et al.  A Shape Index from Molecular Graphs , 1985 .

[15]  Iain D. Craig.  Genetic Algorithms and Simulated Annealing edited by Lawrence Davis Pitman, London, 1987 (£19.95) , 1988, Robotica.

[16]  J. Devillers.  Genetic algorithms in molecular modeling , 1996 .

[17]  Luke E. K. Achenie,et al.  Designing environmentally safe refrigerants using mathematical programming , 1996 .

[18]  Robert C. Glen,et al.  A genetic algorithm for the automated generation of molecules within constraints , 1995, J. Comput. Aided Mol. Des..

[19]  Luke E. K. Achenie,et al.  Novel Mathematical Programming Model for Computer Aided Molecular Design , 1996 .

[20]  John J. Grefenstette,et al.  Genetic algorithms in noisy environments , 1988, Machine Learning.

[21]  M. Randic.  Characterization of molecular branching , 1975 .

[22]  C. Maranas.  Optimal Computer-Aided Molecular Design: A Polymer Design Case Study , 1996 .

[23]  Luigi Di Pace,et al.  A machine learning approach to computer-aided molecular design , 1991, J. Comput. Aided Mol. Des..

[24]  K. Joback,et al.  ESTIMATION OF PURE-COMPONENT PROPERTIES FROM GROUP-CONTRIBUTIONS , 1987 .

[25]  P. Schleyer.  Encyclopedia of computational chemistry , 1998 .

[26]  Costas D. Maranas,et al.  Optimal molecular design under property prediction uncertainty , 1997 .

[27]  Rafiqul Gani,et al.  Prediction of gas solubility and vapor-liquid equilibria by group contribution , 1989 .

[28]  Sandro Macchietto,et al.  Computer aided molecular design: a novel method for optimal solvent selection , 1993 .

[29]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[30]  George C. Derringer,et al.  A computer-based methodology for matching polymer structures with required properties , 1985 .

[31]  Rafiqul Gani,et al.  Computer-aided molecular design with combined molecular modeling and group contribution , 1999 .

[32]  L. Booker.  Foundations of genetic algorithms. 2: L. Darrell Whitley (Ed.), Morgan Kaufmann, San Mateo, CA, 1993, ISBN 1-55860-263-1, 322 pp., US$45.95 , 1994 .

[33]  Lawrence Davis,et al.  Genetic Algorithms and Simulated Annealing , 1987 .

[34]  Lawrence. Davis,et al.  Handbook Of Genetic Algorithms , 1990 .

[35]  Nicholas J. Radcliffe,et al.  The algebra of genetic algorithms , 1994, Annals of Mathematics and Artificial Intelligence.

[36]  James Devillers,et al.  Designing Molecules with Specific Properties from Intercommunicating Hybrid Systems , 1996, J. Chem. Inf. Comput. Sci..

[37]  Kyle V. Camarda,et al.  Optimization in polymer design using connectivity indices , 1999 .

[38]  S. Macchietto,et al.  Design on optimal solvents for liquid-liquid extraction and gas absorption processes , 1990 .

[39]  R. Gani,et al.  New group contribution method for estimating properties of pure compounds , 1994 .

[40]  Larry J. Eshelman,et al.  Biases in the Crossover Landscape , 1989, ICGA.

[41]  Ragavan Vaidyanathan,et al.  Computer-Aided Design of High Performance Polymers , 1994 .