Cytochromes P450 (CYP) are the main actors in the oxidation of xenobiotics and play a crucial role in drug safety, persistence, bioactivation, and drug-drug/food-drug interaction. This work aims to develop Quantitative Structure-Activity Relationship (QSAR) models to predict the drug interaction with two of the most important CYP isoforms, namely 2C9 and 3A4. The presented models are calibrated on 9122 drug-like compounds, using three different modelling approaches and two types of molecular description (classical molecular descriptors and binary fingerprints). For each isoform, three classification models are presented, based on a different approach and with different advantages: (1) a very simple and interpretable classification tree; (2) a local (k-Nearest Neighbor) model based classical descriptors and; (3) a model based on a recently proposed local classifier (N-Nearest Neighbor) on binary fingerprints. The salient features of the work are (1) the thorough model validation and the applicability domain assessment; (2) the descriptor interpretation, which highlighted the crucial aspects of P450-drug interaction; and (3) the consensus aggregation of models, which largely increased the prediction accuracy.

No abstract

This work presents a modified version of Hasse diagram technique, the weighted Regularized Hasse (wR-Hasse), which aims to reduce the number of incomparabilities and derive weighted rankings of the objects. These objectives are accomplished by (a) introducing a mathematical threshold on the definition of incomparability and (b) weighting criteria according to their relevance. In order to test the new approach, we used eight data sets from literature, aiming at extensively investigating the effect of thresholds and weighting schemes on the outcome. Results showed how (a) wR-Hasse effectively reduces the number of incomparabilities with respect to the original Hasse and (b) weighting schemes tune the contribution of relevant criteria to the final outcome. Moreover, this approach allows to obtain statistics useful to further investigate data structure and relationships between object ranks.