Random forest chemical function predictions for Tox21 chemicals in personal care products uses and "other" uses. This dataset is associated with the following publication: Isaacs , K., M. Goldsmith, P. Egeghy , K. Phillips, R. Brooks, T. Hong, and J. Wambaugh. Characterization and prediction of chemical functions and weight fractions in consumer products. Toxicology Reports. Elsevier B.V., Amsterdam, NETHERLANDS, 3: 723-732, (2016).

Importance of random forest predictors for all classification models of chemical function. This dataset is associated with the following publication: Isaacs , K., M. Goldsmith, P. Egeghy , K. Phillips, R. Brooks, T. Hong, and J. Wambaugh. Characterization and prediction of chemical functions and weight fractions in consumer products. Toxicology Reports. Elsevier B.V., Amsterdam, NETHERLANDS, 3: 723-732, (2016).

Merged product weight fraction and chemical function data. This dataset is associated with the following publication: Isaacs , K., M. Goldsmith, P. Egeghy , K. Phillips, R. Brooks, T. Hong, and J. Wambaugh. Characterization and prediction of chemical functions and weight fractions in consumer products. Toxicology Reports. Elsevier B.V., Amsterdam, NETHERLANDS, 3: 723-732, (2016).

This dataset provides a prediction for all Tox21 chemicals with available QSUR descriptors across all 41 valid QSUR models developed with FUse. This dataset is associated with the following publication: Phillips, K., J. Wambaugh, C. Grulke, K. Dionisio, and K. Isaacs. High-throughput screening of chemicals as functional substitutes using structure-based classification models. GREEN CHEMISTRY. Royal Society of Chemistry, Cambridge, UK, 19: 1063-1074, (2017).

Chemicals and harmonized functions - dataset of chemicals mapped to a harmonized chemical function category. This dataset is associated with the following publication: Isaacs , K., M. Goldsmith, P. Egeghy , K. Phillips, R. Brooks, T. Hong, and J. Wambaugh. Characterization and prediction of chemical functions and weight fractions in consumer products. Toxicology Reports. Elsevier B.V., Amsterdam, NETHERLANDS, 3: 723-732, (2016).

In an effort to address a major challenge in chemical safety assessment, alternative approaches for characterizing systemic effect levels, a predictive model was developed. Systemic effect levels were curated from ToxRefDB, HESS-DB and COSMOS-DB from numerous study types totaling 4382 in vivo studies for 1201 chemicals. Observed systemic effects in mammalian models are a complex function of chemical dynamics, kinetics, and inter- and intra-individual variability. In order to address the complexity problem, systemic effect levels were modeled at the study-level by leveraging study covariates (e.g., study type, strain, administration route) in addition to multiple descriptor sets, including chemical (ToxPrint, PaDEL, and Physchem), biological (ToxCast), and kinetic descriptors. Using Random Forest modeling with cross-validation and external validation procedures, study-level covariates alone accounted for approximately 20% of the variance reducing the root mean squared error (RMSE) from 0.96 log10 mg/kg/day to 0.85 log10 mg/kg/day, providing a baseline performance metric (lower expectation of model performance). A consensus model developed using a combination of study-level covariates, chemical, biological, and kinetic descriptors explained a total of 38% of the variance with an RMSE of 0.76 log10 mg/kg/day. A benchmark model (upper expectation of model performance) was also developed with an RMSE of 0.5 log10 mg/kg/day by incorporating study-level covariates and the mean effect level per chemical. To achieve a representative chemical-level prediction, the minimum study-level predicted and observed effect level per chemical were compared reducing the RMSE from 1.1 to 0.8 log10 mg/kg/day. Although biological descriptors did not improve model performance, the final model was enriched for biological descriptors that indicated xenobiotic metabolism gene expression, oxidative stress, and cytotoxicity, demonstrating the importance of accounting for kinetics and non-specific bioactivity in predicting systemic effect levels. Herein, we have generated an externally predictive model of systemic effect levels for use as a safety assessment tool and have generated forward predictions for thousands of chemicals. This dataset is associated with the following publication: Truong, L., G. Ouedraogo, L. Pham, J. Clouzeau, S. Loisel-Joubert, D. Blanchet, H. Noçairi, W. Setzer, R. Judson, C. Grulke, K. Mansouri, and M. Martin. (Archives of Toxicology) Predicting In Vivo Effect Levels for Repeat Dose Systemic Toxicity using Chemical, Biological, Kinetic and Study Covariates. Archives of Toxicology. Springer, New York, NY, USA, 92(2): 587-600, (2018).

An elicitation with 32 experts informed relative prioritization of risks from chemical properties and human use factors for consumer product-related chemicals. Three different versions of the model were evaluated using distinct weight profiles. This dataset is associated with the following publication: Wood, M., K. Plourde, S. Larkin, P. Egeghy, A. Williams, V. Zemba, I. Linkov, and D. Vallero. Advances on a Decision Analytic Approach to Exposure‐Based Chemical Prioritization. RISK ANALYSIS. Blackwell Publishing, Malden, MA, USA, 40(1): 83-96, (2020).

The Exposure Forecaster Database (ExpoCastDB) is EPA's database for aggregating chemical exposure information and can be used to help with chemical exposure predictions. The database currently includes biomonitoring exposure data from three studies: the American Healthy Homes Survey, the First National Environmental Health Survey of Child Care Centers and the Children's Total Exposure to Persistent Pesticides and Other Persistent Organic Pollutants study. Data include the amounts of chemicals found in food, drinking water, air, dust indoor surfaces and urine. The database will eventually include high-throughput exposure predictions for thousands of chemicals based on manufacture and use information. EPA researchers developed high-throughput exposure models to predict exposures for 1,763 chemicals using production volume, environmental fate and transport models, and a simple indicator of consumer product use.The model is being improved by adding more refined indoor and consumer use information since these are also large determinants of exposure. As these models are refined and more exposure data is collected, it will be added to ExpoCastDB.

The Chemical and Product Categories database (CPCat) catalogs the use of over 40,000 chemicals and their presence in different consumer products. The chemical use information is compiled from multiple sources while product information is gathered from publicly available Material Safety Data Sheets (MSDS). EPA researchers are evaluating the possibility of expanding the database with additional product and use information.

Data and model predictions supporting the manuscript: Isaacs K.K., Phillips K.A., Biryol D., Dionisio K.L., and Price P. Consumer product chemical weight fractions from ingredient lists. Journal of Exposure Science and Environmental Epidemiology (in press as of 8/2017). This dataset is associated with the following publication: Isaacs, K., K. Phillips, D. Biryol, K. Dionisio, and P. Price. Consumer product chemical weight fractions from ingredient lists. Journal of Exposure Science and Environmental Epidemiology. Nature Publishing Group, London, UK, 28: 216-222, (2018).