Application of Predictive QSAR Models to Database Mining

Application of Predictive QSAR Models to Database Mining 

Quantitative Structure-Activity Relationship models are used increasingly in chemical data mining and combinatorial library design [5, 6]. For example, three-dimensional (3-D) stereoelectronic pharmacophore based on QSAR modeling was used recently to search the National Cancer Institute Repository of Small Molecules [7] to find new leads for inhibiting HIV type 1 reverse transcriptase at the nonnucleoside binding site [8]. A descriptor pharmacophore concept was introduced by us recently [9] on the basis of variable selection QSAR the descriptor pharmacophore is defined as a subset of 

Building Predictive QSAR Models The Importance ofValidation 

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. 

Typically, the final part of QSAR model development is the model validation [17, 18], when the predictive power of the model is tested on an independent set of compounds. In essence, predictive power is one of the most important characteristics of QSAR models. It can be defined as the ability of a model to predict accurately the target property (e.g., biological activity) of compounds that were not used for model development. The typical problem of QSAR modeling is that at the time of the model development a researcher only has, essentially, training set molecules, so predictive ability can only be characterized by statistical characteristics of the training set model and not by true external validation. 

---

Shen M, Beguin C, Golbraikh A, Stables JP, Kohn H, Tropsha A. Application of predictive QSAR models to database mining identification and experimental validation of novel anticonvulsant compounds. J Med Chem 2004 47(9) 2356-64. 

Tropsha, a. Application of predictive QSAR models to database mining. 

I 76 Application of Predictive QSAR Models to Database Mining... 

A. Tropsha, Application of predictive QSAR models to database mining. In Cheminformatics in Drug Discovery., T. Oprea Ed., Wiley-VCH, Wein-heim, 2005, pp. 437-455. 

The advantage of using QSAR models for database mining is that it affords not only the compounds selection but also quantitative prediction of their activity. For illustration, we shall discuss our recent success in developing validated predictive models of anticonvulsants [51] and their application to the discovery of novel potent compounds by the means of database mining [10]. 

Figure 10.2 Application of the QSAR modeling workflow to the discovery of novel anticonvulsants. The workflow emphasizes the importance of model validation and applicability domain in ensuring high hit rates as a result of database mining with predictive QSAR models.

---