QSPR models development

As far as tissue characterization is concerned, the fraction of lipid and water tends to be the dominating factor that influences partitioning into or out of the tissue. Some QSPR studies have included proteins which account for an electrostatic interaction with the amino or carboxyl terminal ends of an ionized chemical at physiological pH as well as some nonspecific binding for neutral compounds. However, a recent QSPR model developed by Schmitt (2008)... 

In a typical QSPR model development, a set of chemicals is used to build up the model. These chemicals have their property values known, and the modeler calculates the chemical descriptors associated with the structure. Then relationships between the descriptors and the property are calculated, with a series of programs. Some programs are currently used to screen chemicals proposed by industry as products to be introduced into the market. Thus the US EPA yearly evaluates about 1500 to 2000 chemicals, and quite often this evaluation is done without appropriate environmental and toxicological properties. 

These and other properties of benzodiazepine drags make it critical to establish the quantitative relationship between their structure and pharmacokinetic properties in order to optimize their action and predict the properties of innovative drags using QSPR models developed by us. 

In order to develop a proper QSPR model for solubility prediction, the first task is to select appropriate input deseriptors that are highly correlated with solubility. Clearly, many factors influence solubility - to name but a few, the si2e of a molecule, the polarity of the molecule, and the ability of molecules to participate in hydrogen honding. For a large diverse data set, some indicators for describing the differences in the molecules are also important. 

Shen M, Xiao Y, Golbraikh A, Gombar VK, Tropsha A. Development and validation of k-nearest-neighbor QSPR models of metabolic stability of drug candidates. J Med Chem 2003 46 3013-20. 

Basak, S. C., Mills, D. Use of mathematical structural invariants in the development of QSPR models. MATCH (Commun. Math. Comput. Chem.) 2001, 44, 15-30. 

A from the center of a positive ionizable group was identified. However, its predictive performance on a test set consisted of eight structurally similar compounds was relatively poor. To achieve a computational model with greater predictability, a descriptor-based QSPR model was also developed. Descriptors related to molecular hydrophobicity as well as hydrogen bond donor, shape and charge features contributed to explain hOCTl inhibitor properties of the analyzed compounds. 

QSPR models have been developed by six multivariate calibration methods as described in the previous sections. We focus on demonstration of the use of these methods but not on GC aspects. Since the number of variables is much larger than the number of observations, OLS and robust regression cannot be applied directly to the original data set. These methods could only be applied to selected variables or to linear combinations of the variables. 

The following shows the development of the predictive QSPR model. The descriptors considered for the model include geometric and topological descriptors, electronic properties, charge-dependent properties, physico-chemical properties, and accumulation factors. The solid phases studied include three soil types (mollisol, ultisol, and aridisol) and two aquatic sediments. 

For some compounds in the Wilschut database more than one permeability coefficient was gathered from literature. In some cases, the differences in kp were greater than one log unit underlining the interlaboratory variations of such measurements. For the development of a new QSPR model one may now either choose one representative data point for each molecule or combine the multiple data points in a reasonable way. In some cases authors even employed all the available data for a single compound. Apart from the permeability data, the data on the partition coefficient and even on the molecular weight may vary from one report to another. Differences in the partition coefficient are easily explained Some collections list experimentally determined values which depend on the experimental procedure employed... 

Moody RP, MacPherson H (2003) Determination of dermal absorption QSAR/QSPRs by brute force regression multiparameter model development with Molsuite 2000. J Toxicol Env Healt A 66 1927-1942. 

Narayanan and Gunturi [33] developed QSPR models based on in vivo blood-brain permeation data of 88 diverse compounds, 324 descriptors, and a systematic variable selection method called Variable Selection and Modeling method based on the Prediction (VSMP). VSMP efficiently explored all... 

Chiu, T.-L. and So, S.-S. Development of neural network QSPR models for Hansch substituent constants. 

A more common use of informatics for data analysis is the development of (quantitative) structure-property relationships (QSPR) for the prediction of materials properties and thus ultimately the design of polymers. Quantitative structure-property relationships are multivariate statistical correlations between the property of a polymer and a number of variables, which are either physical properties themselves or descriptors, which hold information about a polymer in a more abstract way. The simplest QSPR models are usually linear regression-type models but complex neural networks and numerous other machine-learning techniques have also been used. 

While both the Bicerano and van Krevelen systems model a significant number of polymer properties, most QSPR studies have focused on only a small number of key properties (which is mainly correlated to the availability of data for model development). 

Liu and Zhong introduced a number of QSPR models based on molecular connectivity indices [151, 152], In a first iteration, the researchers developed polymer-dependent correlations descriptors were calculated for a set of solvents and models were developed per polymer type [151], Polymer classes under consideration were polystyrene, polyethylene, poly-1-butene, poly-l-pentene, poly(4-methyl-l-pentene), polydimethylsiloxane, and polyisobutylene. As the authors fail to provide any validation for their models, it is difficult to asses their predictive power. In a subsequent iteration and general expansion of this study, mixed and therefore more general models based on the calculated connectivity indices of both solvent and polymers were developed. While it is unclear from the paper which polymer representation was used for the calculation of the connectivity indices, the best regression model (eight parameter model) yields only acceptable predictive power (R = 0.77, = 0.77, s = 34.47 for the training set, R = 0.75... 

Toropov et al.76-79 developed QSPR models for the complexes of nine alkaline-earth and transition metals with some amino acids, phosphate derivatives of adenosine, and heterocyclic compounds based on topological indices. Although the numbers of examples in the datasets were big enough, 11076 and 150,79 they involved only a few different ligands (17 and 25 molecules, respectively). The validation calculations were performed on the test sets containing the same ligands as in the training sets, which could explain the well observed performance of the predictions.7679... 

In this work, we have demonstrated that modern QSPR modeling methods are becoming an important tool for computer-aided designs of new metal binders. Further developments depend not only on new data-mining techniques and descriptors applied, but also on the quality of the experimental data used for the training and validation of the models. Thus, both theoretical and experimental chemists should make an effort to build a basis for predictive structure-property modeling that will accelerate the development of target molecules and materials. 

Recently, Riviere and Brooks (2007) published a method to improve the prediction of dermal absorption of compounds dosed in complex chemical mixtures. The method predicts dermal absorption or penetration of topically applied compounds by developing quantitative structure-property relationship (QSPR) models based on linear free energy relations (LFERs). The QSPR equations are used to describe individual compound penetration based on the molecular descriptors for the compound, and these are modified by a mixture factor (MF), which accounts for the physical-chemical properties of the vehicle and mixture components. Principal components analysis is used to calculate the MF based on percentage composition of the vehicle and mixture components and physical-chemical properties. 

By a quantitative structure-property relationship (QSPR) analysis of a total of 45 different empirical solvent scales and 350 solvents, the direct calculation of predicted values of solvent parameters for any scale and for any previously unmeasured solvent was possible using the CODESS A program [ie. comprehensive descriptors for structural and statistical analysis) developed by Katritzky et al. [244]. The QSPR models for each of the solvent scales were constructed using only theoretical descriptors, derived solely from the molecular solvent structure. This QSPR study enabled classification of the various solvent polarity scales and ultimately allowed a unified PCA treatment of these scales. This PCA treatment, carried out with 40 solvent scales as variables (each having 40 data points for 40 solvents as objects), allowed a rational classification and grouping... 

Similar to LEER approaches, QSPR models may or may not take microspeciation into account. Microspecies are distinguished naturally if atomic descriptors take into account the protonation state of other groups. Although quite challenging to model developers, exact and complete inclusion of microspeciation rewards the programer with better pK prediction for multiprotic systems. Two commercial software... 

---