Differentiating Pathway-Specific From Nonspecific Effects in High-Throughput Toxicity Data: A Foundation for Prioritizing Adverse Outcome Pathway Development

Abstract

The U.S. Environmental Protection Agency's ToxCast program has screened thousands of chemicals for biological activity, primarily using high-throughput in vitro bioassays. Adverse outcome pathways (AOPs) offer a means to link pathway-specific biological activities with potential apical effects relevant to risk assessors. Thus, efforts are underway to develop AOPs relevant to pathway-specific perturbations detected in ToxCast assays. Previous work identified a "cytotoxic burst" (CTB) phenomenon wherein large numbers of the ToxCast assays begin to respond at or near test chemical concentrations that elicit cytotoxicity, and a statistical approach to defining the bounds of the CTB was developed. To focus AOP development on the molecular targets corresponding to ToxCast assays indicating pathway-specific effects, we conducted a meta-analysis to identify which assays most frequently respond at concentrations below the CTB. A preliminary list of potentially important, target-specific assays was determined by ranking assays by the fraction of chemical hits below the CTB compared with the number of chemicals tested. Additional priority assays were identified using a diagnostic-odds-ratio approach which gives greater ranking to assays with high specificity but low responsivity. Combined, the two prioritization methods identified several novel targets (e.g., peripheral benzodiazepine and progesterone receptors) to prioritize for AOP development, and affirmed the importance of a number of existing AOPs aligned with ToxCast targets (e.g., thyroperoxidase, estrogen receptor, aromatase). The prioritization approaches did not appear to be influenced by inter-assay differences in chemical bioavailability. Furthermore, the outcomes were robust based on a variety of different parameters used to define the CTB.

Figure 1.

Illustration of a chemical-assay dose-response curve annotated with the ToxCast pipeline metrics: maximal activity or top value (T), concentration at ½ maximal activity (AC50), and concentration at cut-off (ACC).

Figure 2.

Distribution of ToxCast assays with biomolecular targets according to assay responsivity (hits/chemicals tested) versus sensitivity (hits < CTBlb/hits). Assays were ranked according to hits < CTBlb/chemicals tested (A) or diagnostic odds ratio (B): top 95th percentile (diamond), 95th > percentile > 90th (square), 90th > percentile >80th (triangle), and < 80th percentile (circle). The two approaches prioritized the assays similarly, although the diagnostic odds ratio favored highly specific, less sensitive assays (inset, B).

Figure 3.

Assay rank versus assay content in terms of % protein (filled triangles) and % lipid (open circles). Assay rank was determined according to the number of chemical-assay hits < CTBlb/chemicals tested. Percent protein and lipid (v/v) were determined by Fischer et al. (2017) for 25 Tox21 assays and are presented on a logarithmic (base 10) scale. Neither system % lipid nor % protein appeared to influence the assay rank.

Figure 4.

Regression of assay rank (determined as hits < CTBlb/chemicals tested) versus EC50_free/AC50 for 25 TOX21 assays modeled by Fischer et al. (2017). Toxicity data for ARE_BLA_agonist_viability were not provided. The slope was not significantly different from zero (95% confidence intervals: −0.01953 to 0.2712), suggesting that chemical bioavailability was not a determinant of the ranking.

Figure 5.

Regression of EC50_mem/AC50 and the nominal hit concentration relation to the burst threshold (AC50-CTBlb) for chemical assay data falling within the CTB (AC50-CTBlb > 0). No significant correlation between the factors driving chemical partitioning to the cellular membrane (EC50mem/AC50) and the relationship of the hit from the CTB threshold (CTBlb) was determined, suggesting that even in cell-based assays, the CTB effect is more complicated than simple baseline toxicity. Slope regression was 0.0016 with a 95% confidence interval of −0.0020 to 0.0051.