High-throughput transcriptomic (HTTr) technologies are increasingly being used to screen environmental chemicals in vitro to identify molecular targets and provide mechanistic context for regulatory testing. The androgen receptor (AR, NR3C4) regulates male sexual development, is involved in the pathogenesis of a number of cancers, and is often the target of endocrine disruptors. Here, we describe the development and validation of a novel gene expression biomarker to identify AR-modulating chemicals using a pattern matching method. AR biomarker genes were identified by their consistent expression after exposure to 4 AR agonists and opposite expression after exposure to 4 AR antagonists. A genetic filter was used to include only those genes that were regulated by AR. Most of the resulting 51 biomarker genes were shown to be directly regulated by AR as determined by ChIP-Seq analysis of AR-DNA interactions. The biomarker was evaluated as a predictive tool using the fold-change rank-based Running Fisher algorithm which compares the expression of AR biomarker genes under various treatment conditions. Using 163 comparisons from cells treated with 98 chemicals, the biomarker gave balanced accuracies for prediction of AR activation or AR suppression of 97% or 98%, respectively. The biomarker was able to correctly classify 16 out of 17 AR reference antagonists including those that are weak and very weak. Predictions based on comparisons from AR-positive LAPC-4 cells treated with 28 chemicals in antagonist mode were compared to those from an AR pathway model based on 11 in vitro high-throughput screening assays that queried different steps in AR signaling. The balanced accuracy was 93% for suppression. Using our approach, we identified conditions in which AR was modulated in a large collection of microarray profiles from prostate cancer cell lines including 1) AR constitutively active mutants or knockdown of AR, 2) depletion of androgens by castration or removal from media, and 3) modulators that work through indirect mechanisms including suppression of AR expression. These results demonstrate that the AR gene expression biomarker could be a useful tool in HTTr to identify AR modulators in large collections of microarray data derived from AR-positive prostate cancer cell lines.