In Silico Modelling of Phospholipidosis: Improving Predictive Performance Through the Use of Structural Fragments

Katarzyna Przybylak and Mark Cronin, Liverpool John Moores University, UK

Drug-induced phospholipidosis (PLD) is a side effect of the administration of cationic amphiphilic drugs (CADs). It is desirable to identify and screen compounds with the potential to induce PLD as early as possible in drug development. Recently, a number of in silico methods have been developed to predict PLD based on the simple physicochemical properties such as log P and pKa. These models are low-cost and high-throughput strategies; however, they produce a high number of false positive predictions. The aim of this study was to assess the predictive performance of existing in silico approaches e.g., the Ploemen and Pelletier models, and to develop new strategies for the rapid identification of the potential PLD-inducers. Studies of 450 chemicals (93 positive in vivo and 357 negative in vivo phospholipidosis-inducers) confirmed the high false positive rate of prediction of models based only on log P and pKa values. Modification of the methods by incorporating structural information, as well as linear discriminant analysis based on five descriptors associated with the general properties of cationic amphiphilic compounds, gave moderate improvements in the prediction performance. Therefore, a new strategy, based on molecular fragments and captured by SMARTS strings was developed. These structural fragments, derived from the structural characteristics of cationic amphiphilic drugs, were grouped into five substructural categories: primary amines, secondary amines, tertiary amines, cyclic amines and aromatic systems. They were able to identify potential PLD-inducers and achieved a high sensitivity of 87%. The results showed that the phospholipidosis is linked directly to the molecular structure of chemical; therefore the SMARTS pattern methodology could be used as a first line of screening of PLD potential during the drug discovery process. The funding of the European Union 6th Framework OSIRIS Integrated Project (GOCE-037017-OSIRIS) is gratefully acknowledged.

(presenting author: Mark Cronin)