Mining Applications in Drug Discovery

Each attempt to cover data mining and its applications in drug discovery is bound to be incomplete. Therefore we restrict our discussion to those areas of drug discovery that are relevant to the field of medicinal chemistry. The chapter is divided in... 

Banville, D.L. 2008. Mining chemical structural information from the literature, in Pharmaceutical Data Mining Approaches and Applications for Drug Discovery, K.V. Balakin (Ed.), Wiley Inc., chap. 20. 

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. 

It is convenient to categorize data mining into types of tasks corresponding to the different objectives. The categorization below is not unique and underlines only the most dominant tasks encountered in drug discovery applications. 

The are several clearance and toxicological aspects that have to be considered in the drug discovery process such as metabolic stability, enzyme selectivity, CYP inhibition and type of inhibition. Among these factors, the prediction of the site of metabolism has become one of the most successful parameters for prediction. The knowledge of the site of metabolism enhances the opportunity to chemically modify the molecule to improve the metabolic stability. There are several approaches based on database mining, chemical reactivity, protein interaction or both that have been developed for the prediction of this property, with different degree of success and applicability. 

Fig. 16.5 Computer-aided drug discovery workflow based on combination of QSAR modeling and consensus database mining as applied to the discovery of novel anticonvulsants [10]. 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.

---