Genetic algorithms selection

Figure 8. Thrombin inhibitors identified by a genetic algorithm selection O method.

Mitchell, M. An Introduction to Genetic Algorithms, MIT Press Cambridge, MA, 1996. Gilman, A Ross, I. Genetic-algorithm selection of a regulatory structure that directs flux in a simple metabolic model. Biophys. J. 1995, 69, 1321-1333. 

Variable and pattern selection in a dataset can be done by genetic algorithm, simulated annealing or PCA... 

To become familiar with genetic algorithms and their application to descriptor selection... 

The evolutionary process of a genetic algorithm is accomplished by genetic operators which translate the evolutionary concepts of selection, recombination or crossover, and mutation into data processing to solve an optimization problem dynamically. Possible solutions to the problem are coded as so-called artificial chromosomes, which are changed and adapted throughout the optimization process until an optimrun solution is obtained. 

The descriptor set can then be reduced by eliminating candidates that show such bad characteristics. Optimization techniques such as genetic algorithms (see Section 9.7) are powerful means of automating this selection process. 

Models developed with selected subsets of descriptors, instead of all possible descriptors, can be more accurate and robust. In order to select adequate descriptors for each of the four classes of protons, genetic algorithms (GA) were used, and the results were compared with those obtained when all the descriptors were used. 

Genetic algorithms can also be used to perform molecular docking [Judson et d. 1994 Jont et d. 1995b Oshiro et d. 1995]. Each chromosome codes not only for the internal conform tion of the ligand as described in Section 9.9.1 but also for the orientation of the ligand withi the receptor site. Both the orientation and the internal conformation will thus vary as th populations evolve. The score of each docked structure within the site acts as the fitnes function used to select the individuals for the next iteration. 

As might be expected, established optimisation techniques such as simulated annealing and genetic algorithms have been used to tackle the subset selection problem. These methods... 

P Willett, J Bradshaw and D V S Green 1999. Selecting Combinatorial Libraries to Optimize rsity and Physical Properties. Journal of Chemical Information and Computer Science 39 169-177. 1 and A W R Payne 1995. A Genetic Algorithm for the Automated Generation of Molecules in Constraints. Journal of Computer-Aided Molecular Design 9 181-202. 

Provide clues about how near-real-time tactical decision aids may eventually be developed using natural selection (via genetic algorithms). 

D. Jouan-Rimbaud, D.L. Massart, R. Leardi, et al.. Genetic algorithms as a tool for wavelength selection in multivariate calibration. Anal. Chem., 67 (1995) 4295 301. 

Integer programming has been applied by De Vries [3] (a short English-language description can be found in [2]) for the determination of the optimal configuration of equipment in a clinical laboratory and by De Clercq et al. [4] for the selection of optimal probes for GLC. From a data set with retention indices for 68 substances on 25 columns, sets ofp probes (substances) (p= i,2,..., 20) were selected, such that the probes allow to obtain the best characterization of the columns. This type of application would nowadays probably be carried out with genetic algorithms (see Chapter 27). 

Evolutionary computation which is learned by watching population dynamics the most important programming are genetic algorithms which are inspired by the evolutionary processes of mutation, recombination, and natural selection in biology. 

Fig. 5.9. Wavelength selection by Genetic Algorithm a 15 optimum wavelength selected from 86 of the full spectrum b relative fitness (rf/104) of the rim in dependence of the number of generations, above fitness of the best solution, middle mean, below fitness of the worst solution (Fischbacher et al. [1994/96 1995])... 

There are three steps in the evolution of the classifier list (1) the identification of useful classifiers, (2) the creation of new classifiers that may be of value, and (3) the removal of classifiers that serve no useful purpose. This is just the sort of task for which the genetic algorithm is designed. It assesses individuals on the basis of their quality, selects the better individuals, and from them creates new, potentially better, individuals. 

---