The increasing number of publicly available databases with large amounts of data is facilitating computational modeling efforts in different fields. However, for QSAR/QSPR modeling, the quality of experimental data and chemical structure information remains a big challenge. In order to build a suite of robust predictive QSAR/QSPR models to support regulatory purposes, all collected datasets for the open structure-activity relationship application (OPERA) project have undergone extensive curation procedures. Automated workflows were designed and applied to select only high-quality data, and associated chemical structures were standardized to generate QSAR-ready forms prior to modeling. The five OECD principles for QSAR modeling were followed to provide scientifically valid, high accuracy models with minimum complexity that yield mechanistic interpretation, when possible. Current OPERA models cover a wide variety of physicochemical properties, environmental fate and toxicity endpoints including logP, water solubility, pKa, plasma-protein binding, endocrine disrupting activity, and acute oral toxicity. Technical and performance details are described in OECD-compliant QSAR model reporting format reports (QMRF reports). OPERA is constantly updated with new data and models and can be used via the open source standalone application on GitHub (https://github.com/kmansouri/OPERA) and its predictions can be accessed through the EPA’s CompTox Chemicals Dashboard (https://comptox.epa.gov/dashboard) and NICEATM’s Integrated Chemical Environment (https://ice.ntp.niehs.nih.gov/). <i>This abstract does not necessarily represent the views or policies of any federal agency.</i><br/>

OPERA models for physicochemical properties, environmental fate and toxicological endpoints to support regulatory purposes

2019 Spring National Meeting

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.