QSAR tool

Numerous QSAR tools have been developed [152, 154] and used in modeling physicochemical data. These vary from simple linear to more complex nonlinear models, as well as classification models. A popular approach more recently became the construction of consensus or ensemble models ( combinatorial QSAR ) combining the predictions of several individual approaches [155]. Or, alternatively, models can be built by rurming the same approach, such as a neural network of a decision tree, many times and combining the output into a single prediction. 

In this chapter we have only addressed a selected number of topics and for lack of space we have left out many others. Cluster analysis has played a larger role in QSAR than appears from our overview. This technique is an established QSAR tool in recognition or classification of known patterns [38,60] as well as for cognition or detection of novel patterns [61]. 

Table 4 Most relevant QSAR tools to estimate physicochemical and toxicological properties Tool Description Ref...

Similarly, quantitative structure-metabolism relationships (QSMR) have been studied [42]. QSAR tools, such as pattern recognition analysis, have been used to e. g. predict phase II conjugation of substituted benzoic acids in the rat [53]. 

A software application designed to help companies evaluate new chemical alternatives for concern characteristics. The P2 Framework organizes and integrates the SAR/QSAR tools and methodologies OPPT uses to evaluate new chemicals... 

Description SYBYL module for the calculation of EVA descriptors, CoMFA and CoMSIA fields, also including several QSAR tools. Last release 6.1... 

McFarland, J.W. and Gans, D.J. (1990a). Cluster Significance Analysis A New QSAR Tool for Asymmeric Data Sets. Drug InfJ., 24,705-711. 

Walters, D.E. (1998). Genetically Evolved Receptor Models (GERM) as a 3D QSAR Tool. In 3D QSAR in Drug Design - Vol. 3 (Kubinyi, H., Folkers, G. and Martin, Y.C., eds.), Kluwer/ ESCOM, Dordrecht (The Netherlands), pp. 159-166. 

To facilitate easy and quick generation of local QSARs, an in-house QSAR tool has been developed within Hoffman-La Roche. This tool allows all project teams to build a local model. Local SARs have been developed for several projects using hERG assay data and the in vitro screen for chromosomal damage in mammalian cells. These local SARs can also be applied in a more general sense. 

There is a choice of building in-house predictive models starting from literature and in-house bioavailability data. A wide range of QSAR tools are commercially or freely available. Alternatively, commercial packages can be used as discussed in this chapter. 

The Ti-x diagram is a scatter plot of absolute values of the hardness T] against absolute values of the molecular electronegativity % [Kobayashi, Shinohara et al., 2006]. It was proposed as a QSAR tool to highlight groups of molecules with different electronic structures and, accordingly, different reactivities. 

ToxTree is the newest cancer hazard estimation tool downloadable at the European Chemical Bureau website (http //ecb.jrc.it/qsar/qsar-tools/index.php c=TOXTREE). It is a structural alert-based program with a decision tree approach. 

QSAR tools such as these are currently being used to rationalize SAR and to predict the potency of newly designed analogs currently undergoing evaluation before initiation of synthesis. 

An OECD (Q)SAR application toolbox for REACH has been developed and implemented to categorize chemicals by different tools (for example Toxtree, Toxmatch, in Joint Research Center (JRC)-QSAR tools ) and to predict toxicity mainly by read-across techniques. This is suggested for regulatory use. 

Limited Set of Hazards Approach. A third approach would be to benchmark chemicals based on a few hazards for which experimental and QSAR data are readily available. For example, persistence, bioaccumulation potential, and ecotoxicity are three hazards for which experimental and QSAR data, as well as a QSAR tool (the PBT profiler) are readily available for many chemicals. This type of... 

Tsar includes methods to handle data of many types, and statistical techniques to manipulate the various types of data. We have briefly described the use of some of these methods in the context of a published dataset, and have presented our results here. Many other algorithms are integrated within the program, making Tsar an essential QSAR tool. 

---