A gene expression biomarker accurately predicts estrogen receptor α modulation in a human gene expression compendium
Citation:
Vanduyn, N., B. Chorley, R. Tice, R. Judson, AND C. Corton. A gene expression biomarker accurately predicts estrogen receptor α modulation in a human gene expression compendium. SOT, New Orleans, LA, March 13 - 17, 2016.
Impact/Purpose:
Our work demonstrates that the gene expression-based ERα biomarker can accurately identify ERα modulators in MCF-7 cells and could be applied as a potential “Tier 0” screening model prior to ToxCast/Tox21 EDC high-throughput screens.
Description:
The EPA’s vision for the Endocrine Disruptor Screening Program (EDSP) in the 21st Century (EDSP21) includes utilization of high-throughput screening (HTS) assays coupled with computational modeling to prioritize chemicals with the goal of eventually replacing current Tier 1 screening tests. The ToxCast program currently includes 18 HTS in vitro assays that evaluate the ability of chemicals to modulate estrogen receptor α (ERα), an important endocrine target. We propose microarray-based gene expression profiling as a complementary approach to predict ERα modulation and have developed computational methods to identify ERα modulators in an existing database of whole-genome microarray data. The ERα biomarker consisted of 46 ERα-regulated genes with consistent expression patterns across 7 known ER agonists and 3 known ER antagonists. The biomarker was evaluated as a predictive tool using the fold-change rank-based Running Fisher algorithm by comparison to annotated gene expression data sets from experiments in MCF-7 cells. Using 141 comparisons from chemical- and hormone-treated cells, the biomarker gave a balanced accuracy for prediction of ERα activation or suppression of 94% or 93%, respectively. The biomarker was able to correctly classify 18 out of 21 (86%) OECD ER reference chemicals including “very weak” agonists and replicated predictions based on 18 in vitro ER-associated HTS assays. For 114 chemicals present in both the HTS data and the MCF-7 compendium, the balanced accuracies (BA) were 95% and 98% for activation or suppression, respectively. In a comparison to in vivo data for ER activity, the biomarker accurately predicted 48 out of 56 chemicals (BA = 86%) evaluated in rat and mouse uterotrophic assays. These results demonstrate that this gene expression-based ERα biomarker can accurately identify ERα modulators in MCF-7 cells and could be applied as a potential “Tier 0” screening model prior to ToxCast/Tox21 EDC high-throughput screens. This abstract does not represent EPA policy.