News & Publications


Learn more about Prous Institute and our progress in drug discovery, technology, industry partnerships, collaborations and scientific articles.

Publication of Drug-Induced Phospholipidosis SYMMETRY® Models

A new paper published by US FDA scientists (In silico modeling to predict drug-induced phospholipidosis; Sydney S. Choi, Jae S. Kim, Luis G. Valerio Jr., Nakissa Sadrieh;  Toxicol Appl Pharmacol. 269 (2013) 195–204) explores the use of Prous Institute’s SYMMETRY® in the construction and validation of QSAR models for the identification of drug-induced phospholipidosis (DIPL). This lysosomal storage disorder, characterized by an excess accumulation of phospholipids in tissues, poses a challenge for regulators and the pharmaceutical industry because the clinical consequences are unknown.  

Using SYMMETRY®’s advanced model building capabilities, a study was carried out on an FDA-compiled database containing over 700 DIPL positive and negative compounds (inducers or non-inducers of phospholipidosis).  To model build the model with SYMMETRY®, a novel algorithmic approach was employed combining logistic regression and molecular descriptor similarity.

The model’s prediction performance was evaluated with automatic cross validation and yielded positive and negative prediction values of over 80%.  rigorous external validations also gave high prediction values. The authors indicate that the models are intended to be used for regulatory toxicology applied science needs in the screening of new drugs for DIPL.  

Prous Institute's computational discovery and toxicology platform, SYMMETRY®, has been made available to FDA/CDER via an agency-approved Research Collaboration Agreement and is used to develop in silico predictive models for drug safety.