Knowledge-based prediction applications

Anari MR, Sanchez RI, Bakhtiar R, Franklin RB, Baillie TA. Integration of knowledge-based metabolic predictions with liquid chromatography data-dependent tandem mass spectrometry for drug metabolism studies application to studies on the biotransformation of indinavir. Anal Chem 2004 76 823-32. 

Knowledge-based methods are those based on the application of certain rules to describe the metabolism. These rules could be defined as chemical reactions relating structure and biotransformations to predict the metabolic fate of a query chemical structure, as in the Meteor approach [26], or alternatively they could be obtained by fragment analysis of a metabolic database as performed in the SPORCalc (Substrate Product Occurrence Ratio Calculator) system [27]. 

The most successful application of structure-based predictive modeling in the future may be to specific endpoints. As described in Chapter 8 the prediction of something as broad as carcinogenicity is very difficult. If one isolates individual effects and endpoints within this category, then more success will ensue. Such an approach is likely to require the development of tiered strategies for toxicity prediction. It will also allow for the integration of test data from other assays, and where possible, human knowledge. 

DEREK for Windows is a computer-based application that uses a knowledge base approach to predict toxic hazards (including carcinogenicity) of chemicals. It is developed by Lhasa Limited (http //www.lhasalimited.org/index.php cat=221 owner=220 sub cat=221), with SAR contribution from members. The cancer module contains alerts describing structural features associated with carcinogenicity. Each alert is supported by comment, references, and examples describing the evidence on which it has been based. 

---