You are here:
OPERA: Open-Source QSAR Models for Regulatory Support
Citation:
Mansouri, K., T. Martin, X. Chang, D. Allen, A. Williams, AND N. Kleinstreuer. OPERA: Open-Source QSAR Models for Regulatory Support. SETAC, Louisville, KY, November 12 - 16, 2023. https://doi.org/10.23645/epacomptox.24526729
Impact/Purpose:
N/A
Description:
OPERA is a suite of over twenty QSAR models for toxicity endpoints and physicochemical, environmental fate, and ADME properties that follows the five OECD principles for QSAR modeling. It is a freely accessible standalone application that is based on the open-source/open-data concept. OPERA provides scientifically valid, high accuracy models with minimal complexity that support mechanistic interpretation, when possible. The models are built on thoroughly curated experimental data and standardized QSAR-ready chemical structures. OPERA has recently added models for ADME related parameters such as fraction unbound to plasma protein (Fu), hepatocyte intrinsic clearance (Clint), and Caco2 permeability (logPapp). The suite also includes three consensus models developed through international collaborative projects to support regulatory assessment processes involving estrogen and androgen pathway activity (CERAPP and CoMPARA), as well as acute oral systemic toxicity (CATMoS). In the latest version, most OPERA models including physicochemical properties (logKow, water solubility, Henry’s law constant, vapor pressure, melting point, and boiling point) and ADME parameters (Fu, Clint and Caco2) were updated with the latest publicly available datasets to improve their predictivity and applicability domain coverage, as well as to account for highly investigated groups of chemicals such as polyfluorinated substances (PFAS). The suite can generate predictions for single chemicals or in batch mode, and the chemical structure inputs can be processed using its internal QSAR-ready standardization workflow or provided via structure identifiers (CASRN, DTXSID, InChI Key) that are used to query its internal database of over 1M curated chemical structures from EPA’s DSSTox. OPERA provide detailed prediction reports with accuracy estimates, applicability domain assessments, confidence ranges, and experimental values when available. Technical and performance details are described in OECD-compliant QSAR model reporting format (QMRF) reports. OPERA predictions are available through EPA’s CompTox Chemicals Dashboard, the National Toxicology Program’s Integrated Chemical Environment, and recently through FDA’s Precision Platform. OPERA can be downloaded as a standalone command-line or graphical user interface for Windows and Linux operating systems from the NIEHS GitHub repository. It can also be run as a plugin within the OECD’s QSAR Toolbox, and is provided as Python, C/C++ and Java libraries that can be embedded in other applications. This project was funded with federal funds from the NIEHS, NIH under Contract No. HHSN273201500010C. The views expressed in this presentation are those of the authors and do not necessarily reflect the views or policies of any federal agency.
URLs/Downloads:
DOI: OPERA: Open-Source QSAR Models for Regulatory Support
PRESENTATION.PDF (PDF, NA pp, 5570.055 KB, about PDF)