In silico modeling to predict drug-induced phospholipidosis.

Drug-induced phospholipidosis (DIPL) is a preclinical finding during pharmaceutical drug development that has implications on the course of drug development and regulatory safety review. A principal characteristic of drugs inducing DIPL is known to be a cationic amphiphilic structure. This provides evidence for a structure-based explanation and opportunity to analyze properties and structures of drugs with the histopathologic findings for DIPL. In previous work from the FDA, in silico quantitative structure-activity relationship (QSAR) modeling using machine learning approaches has shown promise with a large dataset of drugs but included unconfirmed data as well. In this study, we report the construction and validation of a battery of complementary in silico QSAR models using the FDA's updated database on phospholipidosis, new algorithms and predictive technologies, and in particular, we address high performance with a high-confidence dataset. The results of our modeling for DIPL include rigorous external validation tests showing 80-81% concordance. Furthermore, the predictive performance characteristics include models with high sensitivity and specificity, in most cases above ≥80% leading to desired high negative and positive predictivity. These models are intended to be utilized for regulatory toxicology applied science needs in screening new drugs for DIPL.

Construction and Consensus Performance of (Q)SAR Models for Predicting Phospholipidosis Using a Dataset of 743 Compounds.

Drug-induced phospholipidosis (PLD) continues to be a safety concern for pharmaceutical companies and regulatory agencies, prompting the FDA/CDER Phospholipidosis Working Group to develop a database of PLD findings that was recently expanded to contain a total of 743 compounds (385 positive and 358 negative). Three commercial (quantitative) structure-activity relationship [(Q)SAR)] software platforms [MC4PC, Leadscope Predictive Data Miner (LPDM), and Derek for Windows (DfW)] were used to build and/or test models with the database and evaluated individually and together for their ability to predict PLD induction. Models constructed with MC4PC showed improved sensitivity over previous models constructed with an earlier version of the database and software (61.2 % vs. 50.0 %), but lower specificity in cross-validation experiments (58.2 % vs. 91.9 %) due in part to the more balanced ratio of positives to negatives in the training set. A new model created with LPDM gave good cross-validation statistics (79.0 % sensitivity, 78.0 % specificity) and the single DfW structural alert for PLD was found to have high positive predictivity (83.3 %) but low sensitivity (10.4 %) when tested with the entire PLD database. Combining the predictions of MC4PC, LPDM and/or DfW resulted in increased sensitivity and coverage over using one software platform alone, although it did not enhance the overall prediction accuracy beyond that of the best performing individual software platform. The comparison across software platforms, however, facilitated the identification and analysis of chemicals that were consistently predicted incorrectly by all platforms. The prevalence of cationic amphiphilic drug (CAD) structural motifs in the database contributed heavily to many of the structural alerts and discriminating features in the models, but the subset of incorrectly predicted structures across all models underscores the need to account for mitigating features and/or additional filtering criteria to assess PLD, in particular for PLD-inducing non-CADs and non-PLD-inducing CADs. (Q)SAR tools may be used as part of an early screening battery or regulatory risk assessment approach to identify those compounds with the greatest chance of inducing PLD and potentially toxicity.

Development of a phospholipidosis database and predictive quantitative structure-activity relationship (QSAR) models.

ABSTRACT Drug-induced phospholipidosis (PL) is a condition characterized by the accumulation of phospholipids and drug in lysosomes, and is found in a variety of tissue types. PL is frequently manifested in preclinical studies and may delay or prevent the development of pharmaceuticals. This report describes the construction of a database of PL findings in a variety of animal species and its use as a training data set for computational toxicology software. PL data and chemical structures were compiled from the published literature, existing pharmaceutical databases, and Food and Drug Administration (FDA) internal reports yielding a total of 583 compounds suitable for modeling. The database contained 190 (33%) positive drugs and 393 (77%) negative drugs, of which 39 were electron microscopy-confirmed negative compounds and 354 were classified as negatives due to the absence of positive reported data. Of the 190 positive findings, 76 were electron microscopy confirmed and 114 were considered positive based on other evidence. Quantitative structure-activity relationship (QSAR) models were constructed using two commercially available software programs, MC4PC and MDL-QSAR, and internal cross-validation (10 x 10%) experiments were performed to assess their predictive performance. Performance parameters for the MC4PC model were specificity 92%, sensitivity 50%, concordance 78%, positive predictivity 76%, and negative predictivity 78%. For MDL-QSAR, predictive performance was similar: specificity 80%, sensitivity 76%, concordance 79%, positive predictivity 65%, and negative predictivity 87%. By combining the output of the two QSAR programs, the overall predictive performance was vastly improved and sensitivity could be optimized to 81% without significant loss of specificity (79%). Many of the structural alerts and significant molecular descriptors obtained from the QSAR software were found to be associated with parts of active molecules known for their cationic amphiphilic drug (CAD) properties supporting the hypothesis that the endpoint of PL is statistically correlated with chemical structure. QSAR models can be useful tools for screening drug candidate molecules for potential PL.