CATMoS: Collaborative Acute Toxicity Modeling Suite

Abstract

Background: Humans are exposed to tens of thousands of chemical substances that need to be assessed for their potential toxicity. Acute systemic toxicity testing serves as the basis for regulatory hazard classification, labeling, and risk management. However, it is cost- and time-prohibitive to evaluate all new and existing chemicals using traditional rodent acute toxicity tests. In silico models built using existing data facilitate rapid acute toxicity predictions without using animals.

Objectives: The U.S. Interagency Coordinating Committee on the Validation of Alternative Methods (ICCVAM) Acute Toxicity Workgroup organized an international collaboration to develop in silico models for predicting acute oral toxicity based on five different end points: Lethal Dose 50 (${\text{LD}}_{50}$ value, U.S. Environmental Protection Agency hazard (four) categories, Globally Harmonized System for Classification and Labeling hazard (five) categories, very toxic chemicals [${\text{LD}}_{50}$ (${\text{LD}}_{50}\le 50\mathrm{mg}/\mathrm{kg}$)], and nontoxic chemicals ($L{D}_{50}>\mathrm{2,000}\mathrm{mg}/\mathrm{kg}$).

Methods: An acute oral toxicity data inventory for 11,992 chemicals was compiled, split into training and evaluation sets, and made available to 35 participating international research groups that submitted a total of 139 predictive models. Predictions that fell within the applicability domains of the submitted models were evaluated using external validation sets. These were then combined into consensus models to leverage strengths of individual approaches.

Results: The resulting consensus predictions, which leverage the collective strengths of each individual model, form the Collaborative Acute Toxicity Modeling Suite (CATMoS). CATMoS demonstrated high performance in terms of accuracy and robustness when compared with in vivo results.

Discussion: CATMoS is being evaluated by regulatory agencies for its utility and applicability as a potential replacement for in vivo rat acute oral toxicity studies. CATMoS predictions for more than 800,000 chemicals have been made available via the National Toxicology Program's Integrated Chemical Environment tools and data sets (ice.ntp.niehs.nih.gov). The models are also implemented in a free, standalone, open-source tool, OPERA, which allows predictions of new and untested chemicals to be made. https://doi.org/10.1289/EHP8495.

Figure 1.

Characteristics of training (Supplemental Material 1) and evaluation sets (Supplemental Material 2). (A) Distribution of $\mathrm{L}{\mathrm{D}}_{50}$ values. (B) Sources of the chemical structures.

Figure 2.

Evaluation scores (A) and coverage of the prediction set (B) by the submitted models. See Supplemental Material 5 and 6 for Figure 2A and B, respectively. Modeling groups along the x-axis are defined in Table 4.

Figure 3.

Distributions of the coverage of the prediction set chemicals (A) and concordance among the single models (B) across the five end points. See Supplemental Material 7.

Figure 4.

Example of identifying the winning bin and reconciling the consensus predictions across five end points using the WoE (weight of evidence) approach. The columns represent the different bins from the EPA and GHS categories combined. The rows represent the five different end points and the WoE prediction. The arrows in each row represent the range of the prediction for each end point which were attributed a value of 1 and outside of it a value of 0. For the $\mathrm{L}{\mathrm{D}}_{50}$ end point, the range limits are calculated by adding and subtracting the confidence interval of 0.3 in log value to the original $\mathrm{L}{\mathrm{D}}_{50}$ prediction of $316\mathrm{m}\mathrm{g}/\mathrm{k}\mathrm{g}$ resulting in a range of 160 to $613\mathrm{m}\mathrm{g}/\mathrm{k}\mathrm{g}$. The winning bin is determined by the maximum of the sum of each column in the WoE row. Note: EPA, U.S. Environmental Protection Agency; GHS, U.N. Globally Harmonized System of Classification and Labeling of Chemicals; $\mathrm{L}{\mathrm{D}}_{50}$, dose of a substance that would be expected to kill half the animals in a test group; NT, nontoxic/toxic; VT, very toxic/not very toxic; WoE, weight of evidence.