The purpose of this study was to explore the use of detailed biological data in combination with a statistical learning method for predicting the CYP1A2 and CYP2D6 inhibition. Data were extracted from the Aureus-Pharma highly structured databases which contain precise measures and detailed experimental protocol concerning the inhibition of the two cytochromes. The methodology used was Recursive Partitioning, an easy and quick method to implement. The building of models was preceded by the evaluation of the chemical space covered by the datasets. The descriptors used are available in the MOE software suite. The models reached at least 80% of Accuracy and often exceeded this percentage for the Sensitivity (Recall), Specificity, and Precision parameters. CYP2D6 datasets provided 11 models with Accuracy over 80%, while CYP1A2 datasets counted 5 high-accuracy models. Our models can be useful to predict the ADME properties during the drug discovery process and are indicated for high-throughput screening.

Prediction of in vivo drug-drug interactions (DDIs) from in vitro and in vivo data, also named in vitro in vivo extrapolation (IVIVE), is of interest to scientists involved in the discovery and development of drugs. To avoid detrimental DDIs in humans, new drug candidates should be evaluated for their possible interaction with other drugs as soon as possible, not only as an inhibitor or inducer (perpetrator) but also as a substrate (victim). DDI risk assessment is addressed along the drug development program through an iterative process as the features of the new compound entity are revealed. Both in vitro and preclinical/clinical outcomes are taken into account to better understand the behavior of the developed compound and to refine DDI predictions. During the last decades, several equations have been proposed in the literature to predict DDIs, from a quantitative point of view, showing a substantial improvement in the ability to predict metabolism-based in vivo DDIs. Mechanistic and dynamic approaches have been proposed to predict the magnitude of metabolic-based DDIs. The purpose of this article is to provide an overview of the current equations and methods, the pros and cons of each method, the required input data for each of them, as well as the mechanisms (i.e., reversible inhibition, mechanism-based inhibition, induction) underlying metabolic-based DDIs. In particular, this review outlines how the methods (static and dynamic) can be used in a complementary manner during drug development. The discussion of the limitations and advantages associated with the various approaches, as well as regulatory requirements in that field, can give the reader a helpful overview of this growing area.

No abstract