QSAR models evaluation

QSAR modeling. Therefore considerably larger and more consistent data sets for each enzyme will be required in future to increase the predictive scope of such models. The evaluation of any rule-based metabolite software with a diverse array of molecules will indicate that it is possible to generate many more metabolites than have been identified in the literature for the respective molecules to date, which could also reflect the sensitivity of analytical methods at the time of publishing the data. In such cases, efficient machine learning algorithms will be necessary to indicate which of the metabolites are relevant and will be likely to be observed under the given experimental conditions. 

In a study by Andersson et al. [30], the possibilities to use quantitative structure-activity relationship (QSAR) models to predict physical chemical and ecotoxico-logical properties of approximately 200 different plastic additives have been assessed. Physical chemical properties were predicted with the U.S. Environmental Protection Agency Estimation Program Interface (EPI) Suite, Version 3.20. Aquatic ecotoxicity data were calculated by QSAR models in the Toxicity Estimation Software Tool (T.E.S.T.), version 3.3, from U.S. Environmental Protection Agency, as described by Rahmberg et al. [31]. To evaluate the applicability of the QSAR-based characterization factors, they were compared to experiment-based characterization factors for the same substances taken from the USEtox organics database [32], This was done for 39 plastic additives for which experiment-based characterization factors were already available. 

Criteria for Evaluation of QSAR Models for Regulatory Purposes... 

Another recent tool has been developed within the ORCHESTRA project. The tool keeps into account both the chemometric information and the toxicity predictions done by the model, and in particular what kind of errors have been done by the model. It applies to the CAESAR QSAR models. Furthermore, this tool is based not only on the a priori data and information, as the other approaches, but also on the a posteriori result of the model. The user knows if the model can or cannot be used for a certain compound. In some cases a warning is given, recommending expert opinion. In all cases the reasons for the reliability is given, and it can be evaluated in a transparent way. 

OECD also provides a check list for the application of its principles in the context of QSAR validation. This checklist can be useful to help scientists and regulators during the selection of a QSAR model and to evaluate its robustness/ validity [9]. 

The second example focuses on qualitative evaluation of cancerogenic potential of some perfluorinated compounds using both QSARs models and an in vitro cell transformation assay. 

Among the possible alternative methods, in vitro assay (for ATMs) and quantitative structure-activity relationships (QSARs) models (for ANTMs) are the most applied approaches in the toxicological and ecotoxicological evaluation of chemicals profiles, even in the field of environmental research and risk assessment. 

In this chapter we will introduce and discuss the use of alternative methods to evaluate the carcinogenic potential of some PFCs. In detail, in silico (QSAR) models and BALB/c 3T3 CTA will be used to investigate the issue. 

Among possible alternative, QSARs models and the BALB/c 3T3 in vitro CTA represent a possible solution. An example of the application of these methodologies is reported in this chapter focusing on the evaluation of PFCs. 

Within the project we also evaluated alternative methods as tools to obtain information on the toxicological and physicochemical profile of the pollutants. In this paragraph, an example of the application of QSARs models is reported a comparison is done between predicted values from different models or between QSARs evaluation and experimental values from internationally recognized databases. 

Finally, results reported in the third part from evaluation of Riskcycle compounds of concern suggest that the use of different QSARs models for the same endpoint is a good practice to reduce the variability of the response. 

To produce QSAR models, a data set containing chemicals within a specified well-defined end-point is necessary. Since our knowledge about the properties of the natural compounds that surround us is very poor, especially for allelochemicals and toxicological evaluation of synthetic pesticides is well documented (regulators oblige the chemical industry to produce experimental data for synthetic chemicals, before they can be marketed), when allelochemicals toxicity values are not available, pesticides with similar structure can be used in the analysis. Therefore suitable data sets can be defined with pesticides and their activities, to predict the toxicity (activity) of the allelochemicals. 

There are two possible application strategies for the use of 4D-QSAR models as a VHTS. The first is to take a collection of (manifold) 4D-QSAR models and create a consensus 4D-QSAR model. The consensus model is evaluated for each molecule using all of the individual 4D-QSAR models ... 

QSAR modeling has been traditionally viewed as an evaluative approach, i.e., with the focus on developing retrospective and explanatory models of existing data. Model extrapolation has been considered only in hypothetical sense in terms of potential modifications of known biologically active chemicals that could improve compounds activity. Nevertheless recent studies suggest that current QSAR methodologies may afford robust and validated models capable of accurate prediction of compound properties for molecules not included in the training sets. 

A preliminary and essential step in a QSAR study is to evaluate the database to identify any outliers and hidden patterns, trends, and major groupings. Outliers refer to certain members of the database exhibiting mechanistic behaviors so different that the outlier cannot belong to the bulk of the data. Selecting suitable molecular descriptors, whether they are theoretical or empirical or are derived from readily available experimental characteristics of the structures, is an important step in the development of sound QSAR models. Many descriptors reflect simple molecular properties and thus can provide insight into the physicochemical nature of the activity or property under consideration. 

Brusseau, M.L. 1993. Using QSAR to evaluate phenomenological models for sorption of organic compound by soil. Environ. Toxicol. Chem. 12 1835-1846. 

Hansch analysis and other classical QSAR approaches evaluate the QSAR model based on the correlation of rows of compounds with known activities (dependent variables) to columns of parameters (independent variables). For this reason, classical QSAR is sometimes called 2D QSAR. CoMFA is an example of 3D QSAR because lead analogues are modeled and analyzed in a virtual three-dimensional space. The value of both methods ultimately hinges on how well experimental and calculated activities correlate (Figure 12.2) and how well the model predicts the activity of compounds not included in the training set. 

The quantitative structure-activity relationship (QSAR) model is by definition a model. Any model, such as animal model (also called in vivo) or in vitro model, is a system that applies to a specific situation, and thus, it is useful to study, evaluate, or assess a more complex system, which cannot be used experimentally for investigation. Thus, any model is a simplification of the target object of the study, and the model is useful for this or not depending on its purpose. It is also possible to imagine a series of models, each addressing one or more features of the more complex system. 

Quite often the model is adopted empirically, on the basis of the available resources or tools. QSAR models that aim to address a certain legislative scope should refer to the legislation itself, both for the development of the model, and for the evaluation of the suitability of the purpose. 

The basic assumption of the QSAR model is that the activity under evaluation can be studied, and/or predicted using the chemical information of a certain compound. For the relationship between the activity and the chemical information, a mathematical function can be used. 

---