skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: In silico modeling to predict drug-induced phospholipidosis

Abstract

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. - Highlights: • New in silicomore » models for predicting drug-induced phospholipidosis (DIPL) are described. • The training set data in the models is derived from the FDA's phospholipidosis database. • We find excellent predictivity values of the models based on external validation. • The models can support drug screening and regulatory decision-making on DIPL.« less

Authors:
; ; ;
Publication Date:
OSTI Identifier:
22285311
Resource Type:
Journal Article
Resource Relation:
Journal Name: Toxicology and Applied Pharmacology; Journal Volume: 269; Journal Issue: 2; Other Information: Copyright (c) 2013 Elsevier Science B.V., Amsterdam, The Netherlands, All rights reserved.; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; ALGORITHMS; DECISION MAKING; DRUGS; PHOSPHOLIPIDS; SAFETY ANALYSIS; SCREENING; SIMULATION; STRUCTURE-ACTIVITY RELATIONSHIPS; VALIDATION

Citation Formats

Choi, Sydney S., Kim, Jae S., Valerio, Luis G., E-mail: luis.valerio@fda.hhs.gov, and Sadrieh, Nakissa. In silico modeling to predict drug-induced phospholipidosis. United States: N. p., 2013. Web. doi:10.1016/J.TAAP.2013.03.010.
Choi, Sydney S., Kim, Jae S., Valerio, Luis G., E-mail: luis.valerio@fda.hhs.gov, & Sadrieh, Nakissa. In silico modeling to predict drug-induced phospholipidosis. United States. doi:10.1016/J.TAAP.2013.03.010.
Choi, Sydney S., Kim, Jae S., Valerio, Luis G., E-mail: luis.valerio@fda.hhs.gov, and Sadrieh, Nakissa. Sat . "In silico modeling to predict drug-induced phospholipidosis". United States. doi:10.1016/J.TAAP.2013.03.010.
@article{osti_22285311,
title = {In silico modeling to predict drug-induced phospholipidosis},
author = {Choi, Sydney S. and Kim, Jae S. and Valerio, Luis G., E-mail: luis.valerio@fda.hhs.gov and Sadrieh, Nakissa},
abstractNote = {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. - Highlights: • New in silico models for predicting drug-induced phospholipidosis (DIPL) are described. • The training set data in the models is derived from the FDA's phospholipidosis database. • We find excellent predictivity values of the models based on external validation. • The models can support drug screening and regulatory decision-making on DIPL.},
doi = {10.1016/J.TAAP.2013.03.010},
journal = {Toxicology and Applied Pharmacology},
number = 2,
volume = 269,
place = {United States},
year = {Sat Jun 01 00:00:00 EDT 2013},
month = {Sat Jun 01 00:00:00 EDT 2013}
}