Molecular descriptors selection

Each of these two QSAR model searches led to pools of several thousands of statistically valid linear equations, expressing the estimate of the Cox2 pICso value as linear combinations of molecular descriptors selected by a Genetic Algorithm (GA) [57,... 

The chemical space is defined as the p-dimensional space constituted by a set of p molecular descriptors selected to represent the studied compounds chemical space design is generally recognized as a crucial step for the successful application of QSPR/QSAR methods [Oprea, Zamora et al, 2002 Dutta, Guha et al, 2006 Eckert, Vogt et al, 2006 Landon and Schaus, 2006]. 

Hancock,T, Put, R., Coomans, D., Vander Heyden, Y. and Everingham, Y. (2005) A performance comparison of modern statistical techniques for molecular descriptor selection and retention prediction in chromatographic QSRR studies. Chemom. InteU. Lab. Syst., 76, 185—196. 

Ros, F., Pintore, M. and Chretien, J.R. (2002) Molecular descriptor selection combining genetic... 

TABLE 14.3. Important molecular descriptors selected by CART... 

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. 

Li H, Yap CW, Ung CY, Xue Y, Cao ZW and Chen YZ Effect of selection of molecular descriptors on the prediction of blood-brain barrier penetrating and nonpenetrating agents by statistical learning methods. J Chem Inf Model 2005 45 1376-1384. 

Our basic methods have been detailed In previous reports (11, 12). In summary, however, our approach Is basically the same as that used by Hansch and co-workers (20-22) A set of compounds, which can reasonably be expected to elicit their carcinogenic response via the same general mechanism. Is chosen, and their relative biological activities, along with a set of molecular descriptors. Is entered Into a computer. The computer, using the relative biological response as the dependent variable, then performs stepwise multiple regression anayses (23) to select... 

More typically the process of building up the QSAR models requires more complex chemical information. For a set of compounds, with known property value, the descriptors are calculated. The process of model building proceeds through a reduction of the molecular descriptors, in order to indentify the most important ones. Then, using these selected chemical descriptors and a suitable algorithm, the model is developed. Finally, the model so obtained has to be validated. 

The VolSurf approach was used to correlate the 3D molecular descriptors by utilizing the water solubilities for as many compounds as could be found. Although over 2000 solubility values were identified, many showed contradictory results (both low and high values published). Moreover, some of the estimations had not been made by the authors and the original reference was not reported, while others were simply wrong, having not been measured under the standard conditions required. From the 2000 compounds, about 850 were carefully selected in addi-... 

The quantitative comparison of the optimized 3D structure of a selected set of ligands allows the development of their minimal 3D structural requirements for the recognition and activation of the biological target, that is, the pharmacophore hypothesis, and gives a sound 3D rationale to the available SARs [21]. A more complete and mechanistically relevant approach to the development of the 3D pharmacophore consists in its translation into a numerical molecular descriptor that quantifies the molecular-pharmacophore similarity-diversity for computational QSAR modeling [21,41]. 

The Aspen NRTL-SAC solvent database was identified from the list of solvents presented in the pharmaceutical based International Committee on Harmonization s guidelines for residual solvents in API [28], Hexane, Acetonitrile and Water were selected as the basis for the X, Y and Z segments respectively, the binary interaction parameters for the segments together with molecular descriptors in terms of X,Y and Z segments were then regressed from experimental vapour-liquid and liquid-liquid equilibrium data from the Dechema database. The list of solvent parameters that were used in the case study are given in Table 13. 

A set of n = 209 polycyclic aromatic compounds (PAC) was used in this example. The chemical structures have been drawn manually by a structure editor software approximate 3D-structures including all H-atoms have been made by software Corina (Corina 2004), and software Dragon, version 5.3 (Dragon 2004), has been applied to compute 1630 molecular descriptors. These descriptors cover a great diversity of chemical structures and therefore many descriptors are irrelevant for a selected class of compounds as the PACs in this example. By a simple variable selection, descriptors which are constant or almost constant (all but a maximum of five values constant), and descriptors with a correlation coefficient >0.95 to another descriptor have been eliminated. The resulting m = 467 descriptors have been used as x-variables. The y-variable to be modeled is the Lee retention index (Lee et al. 1979) which is based on the reference values 200, 300, 400, and 500 for the compounds naphthalene, phenanthrene, chrysene, and picene, respectively. 

Since the value of H depends on the choice of , modifications of this procedure have been proposed (Fernandez Piema and Massart 2000). Another modification of the Hopkins statistic—published in the chemometrics literature—concern the distributions of the values of the used variables (Hodes 1992 Jurs and Lawson 1991 Lawson and Jurs 1990). The Hopkins statistic has been suggested for an evaluation of variable selection methods with the aim to find a variable set (for instance, molecular descriptors) that gives distinct clustering of the objects (for instance, chemical structures)—hoping that the clusters reflect, for instance, different biological activities (Lawson and Jurs 1990). 

FIGURE 5.2 Molecular descriptors (a) length-to-breadth LIB) ratio (b) minimum area, Amin, (c) dihedral angle of distortion. (Adapted from Sander, L.C. and Wise, S.A., in Smith, R.M. (Ed.), Retention and Selectivity Studies in HPLC, Elsevier, Amsterdam, 1995, p. 337. With permission.)... 

J.A., and Wilson, T.M. Selection, application, and validation of a set of molecular descriptors for nuclear receptor ligands. Book of Abstracts,... 

The first stage includes the selection of a dataset for QSAR studies and the calculation of molecular descriptors. The second stage deals with the selection of a statistical data analysis and correlation technique, either linear or nonlinear such as PLS or ANN. Many different algorithms and computer software are available for this purpose in all approaches, descriptors serve as independent variables and biological activities serve as dependent variables. 

---