Quantitative structure-activity relationships model building

Rogers, D. (1995) Genetic function approximation a genetic approach to building quantitative structure-activity relationship models, in QSAR and Molecular Modelling Concepts, Computational Tools and Biological Applications (eds F. Sanz, J. Giraldo and F. Manaut), Prous Science, Barcelona (Spain), pp. 420-426. 

The abbreviation QSAR stands for quantitative structure-activity relationships. QSPR means quantitative structure-property relationships. As the properties of an organic compound usually cannot be predicted directly from its molecular structure, an indirect approach Is used to overcome this problem. In the first step numerical descriptors encoding information about the molecular structure are calculated for a set of compounds. Secondly, statistical methods and artificial neural network models are used to predict the property or activity of interest, based on these descriptors or a suitable subset. A typical QSAR/QSPR study comprises the following steps structure entry or start from an existing structure database), descriptor calculation, descriptor selection, model building, model validation. 

While ejqierimental methods always require sufficient amount of chemicals for the estimation of drag absorption, computational in silico) methods can lead to the prediction of intestinal absorption based on chemical structure, and can thus be used before synthesis of compoimds. In silico predictions could be based both on relatively simple quantitative structure-activity relationships (QSAR) analysis and more complex physiologically based pharmacokinetic and/or pharmacodynamic models. Whichever the approach used for model building, computational methods should be based on experimental data that were obtained for a wide range of structurally diverse compoimds (training set). It should be noted, however, that current in silico methods, are not as reliable as experimental models. 

Vectors A series of scalars can be arranged in a column or in a row. Then, they are called a column or a row vector. If the elements of a column vector can be attributed to special characteristics, e.g., to compounds, then data analysis can be completed. The chemical structures of compounds can be characterized with different numbers called descriptors, variables, predictors, or factors. For example, toxicity data were measured for a series of aromatic phenols. Their toxicity can be arranged in a column arbitrarily Each row corresponds to a phenolic compound. A lot of descriptors can be calculated for each compound (e.g., molecular mass, van der Waals volume, polarity parameters, quantum chemical descriptors, etc.). After building a multivariate model (generally one variable cannot encode the toxicity properly) we will be able to predict toxicity values for phenolic compounds for which no toxicity has been measured yet. The above approach is generally called searching quantitative structure - activity relationships or simply QSAR approach. 

It is necessary here to consider the type of research which these methods may be used for. Historically, techniques for building models, both physical and mathematical, to relate biologicsd properties to chemical structure have been developed in pharmaceutical and agrochemical research. Many of the examples used in this text are derived from these fields of work. There is no reason, however, why any sort of property which depends on chemical structure should not be modelled in this way. This might be termed quantitative structure-property relationships (QSPR) rather than QSAR where A stands for activity. Such models are beginning to be reported recent examples include applications in the design of dyestuffs, cosmetics, egg-white substitutes, artificial sweeteners, cheese-making, and prepared food products. I have tried to incorporate some of these applications to illustrate the methods, as well as the more traditional examples of QSAR. 

---