Genetic variable selection

The use of protoplasts in studies of stress physiology and biochemistry expands the advantages of cell culture systems discussed in the preceding sections. Additional applications are related to the fusion of protoplasts. Intraspecifie and interspecific protoplast fusion greatly enhance genetic variability of the fused protoplasts (Kumar Cocking, 1987). The resulting somatic hybrids provide cells which can be used for selection of specific traits (e.g. environmental stress tolerance) provided by one or both donor cells and for basic studies on cytoplasmic and nuclear inheritance of desired characteristics. 

We may suppose that not all 600 wavelengths are useful for the prediction of nitrogen contents. A variable selection method called genetic algorithm (GA, Section 4.5.6) has been applied resulting in a subset with only five variables (wavelengths). Figure 1.3c and d shows that models with these five variables are better than models... 

Variable selection is an optimization problem. An optimization method that combines randomness with a strategy that is borrowed from biology is a technique using genetic algorithms—a so-called natural computation method (Massart et al. 1997). Actually, the basic structure of GAs is ideal for the purpose of selection (Davis 1991 Hibbert 1993 Leardi 2003), and various applications of GAs for variable selection in chemometrics have been reported (Broadhurst et al. 1997 Jouan-Rimbaud et al. 1995 Leardi 1994, 2001, 2007). Only a brief introduction to GAs is given here, and only from the point of view of variable selection. 

FIGURE 4.20 Scheme of a GA applied to variable selection. The first chromosome defines a variable subset with four variables selected from m = 10 variables. Fitness is a measure for the performance of a model built from the corresponding variable subset. The population of chromosomes is modified by genetically inspired actions with the aim to increase the... 

Broadhurst, D., Goodacre, R., Jones, A., Rowland, J. J., Kell, D. B. Anal. Chim. Acta 348, 1997, 71-86. Genetic algorithms as a method for variable selection in multiple Unear regression and partial least squares regression, with applications to pyrolysis mass spectrometry. 

Genetic variability for Zn accumulation in A. halleri has been described in 17 European populations (Macnair, 2002). At high Zn concentrations, all individuals hyper-accumulate, independently of provenance, in contrast to the experience with T. caerulescens. At low Zn concentrations, considerable variation exists, once again uncorrelated with selection site. From genetic analyses of intraspecific crosses, the heritability of Zn accumulation was estimated to lie in the range 0.25-0.5, and there was a significant positive correlation between Zn concentration at the maternal parent collection site and the accumulation capacity of the progeny. 

Hoffman, B.T., Kopajtic, T., Katz, J.L., and Newman, A.H. 2D QSAR Modeling and preliminary database searching for dopamine transporter inhibitors using genetic algorithm variable selection of Molconn Z descriptors./. Med. Chem. 

Rogers, D. Hopfingee, A.J. Application of genetic function approximation to quantitative structure-activity relationships and quantitative structure-property relationships. J. Chem. Inf. Comput. Sci. 1994, 34, 854-866. Kubinyi, H. Variable selection in QSAR studies. 1. An evolutionary algorithm. Quantum Struct.-Act. Relat. 1994, 13, 285-294. 

One such algorithm, the genetic algorithm (GA) has seen considerable usage in chemometrics PAT applications for variable selection [99-101]. GA operates in the following manner. 

M. P. Gomez-Carracedo, M. Gestal, J. Dorado and J. M. Andrade, Chemically driven variable selection by focused multimodal genetic algorithms in mid-IR spectra, Anal. Bioanal. Chem., 389(7-8), 2007, 2331-2342. 

---