You are here:
CoMPARA: Collaborative Modeling Project for Androgen Receptor Activity
Citation:
Mansouri, K., N. Kleinstreuer, R. Judson, A. Williams, I. Shah, AND A. Richard. CoMPARA: Collaborative Modeling Project for Androgen Receptor Activity. ENVIRONMENTAL HEALTH PERSPECTIVES. National Institute of Environmental Health Sciences (NIEHS), Research Triangle Park, NC, 128(2):27002, (2020). https://doi.org/10.1289/EHP5580
Impact/Purpose:
This paper presents the development of a set of QSAR models to androgen receptor activity. These models were independently developed and validated by a large number of groups form the US, Europe, Japan and China. The COMPARA project provided a single set of development (training) chemicals and a set of external validation chemicals. The end result is a consensus model that is weighted by the relative accuracies of the individual models. The consensus values for agonist and antagonist activity are being made public through the CompTox Chemicals Dashboard. This model was developed to support chemical prioritization efforts for the EDSP program. We have run ~1800 chemicals through an in vitro model (reviewed by a FIFRA SAP), but the CoMPARA models provides estimates of AR activity for all chemicals subject to EDSP.
Description:
Background: Endocrine disrupting chemicals (EDCs) are xenobiotics that mimic the interaction of natural hormones and alter synthesis, transport or metabolic pathways. The prospect of EDCs causing adverse health effects in humans and wildlife has led to the development of scientific and regulatory approaches for evaluating bioactivity. This need is being partially addressed by the use of high-throughput screening (HTS) in vitro approaches and computational modeling. Objective: In support of the Endocrine Disruptor Screening Program (EDSP), the U.S. EPA (Environmental Protection Agency) led two worldwide consortiums to “virtually” (i.e., in silico) screen chemicals for their potential estrogenic and androgenic activities. Here, we describe the Collaborative Modeling Project for Androgen Receptor (AR) Activity (CoMPARA) efforts which follows the steps of the Collaborative Estrogen Receptor (ER) Activity Prediction Project (CERAPP). Results: The CoMPARA list of screened chemicals built upon CERAPP’s list of 32,464 chemicals to include additional lists of interest, as well as simulated ToxCast metabolites, totaling 55,450 chemical structures. Modelers and computational toxicology scientists from 25 international groups contributed 91predictive QSAR models for binding, agonist, and antagonist activity predictions to CoMPARA. Models were underpinned by a common training set of 1,746 chemicals compiled from 11 ToxCast/Tox21 HTS in vitro assays. The models were then evaluated using literature data extracted from different sources and curated for quality. To overcome the limitations of single model approaches, CoMPARA predictions were combined into consensus models which provided ~80% averaged predictive accuracy for the evaluation set. These consensus models have been implemented into the free and open-source OPERA application to enable new chemicals of interest to be screened. The entire EPA DSSTox (Distributed Structure-Searchable Toxicity) database of ~750,000 chemicals were virtually screened, and their predicted AR activity have been made available on the EPA CompTox Chemicals dashboard (https://comptox.epa.gov/).
URLs/Downloads:
DOI: CoMPARA: Collaborative Modeling Project for Androgen Receptor Activity
https://pubmed.ncbi.nlm.nih.gov/32074470/