Dataset Information

Incorporating ToxCast and Tox21 datasets to rank biological activity of chemicals at Superfund sites in North Carolina.

ABSTRACT: BACKGROUND:The Superfund program of the Environmental Protection Agency (EPA) was established in 1980 to address public health concerns posed by toxic substances released into the environment in the United States. Forty-two of the 1328 hazardous waste sites that remain on the Superfund National Priority List are located in the state of North Carolina. METHODS:We set out to develop a database that contained information on both the prevalence and biological activity of chemicals present at Superfund sites in North Carolina. A chemical characterization tool, the Toxicological Priority Index (ToxPi), was used to rank the biological activity of these chemicals based on their predicted bioavailability, documented associations with biological pathways, and activity in in vitro assays of the ToxCast and Tox21 programs. RESULTS:The ten most prevalent chemicals found at North Carolina Superfund sites were chromium, trichloroethene, lead, tetrachloroethene, arsenic, benzene, manganese, 1,2-dichloroethane, nickel, and barium. For all chemicals found at North Carolina Superfund sites, ToxPi analysis was used to rank their biological activity. Through this data integration, residual pesticides and organic solvents were identified to be some of the most highly-ranking predicted bioactive chemicals. This study provides a novel methodology for creating state or regional databases of biological activity of contaminants at Superfund sites. CONCLUSIONS:These data represent a novel integrated profile of the most prevalent chemicals at North Carolina Superfund sites. This information, and the associated methodology, is useful to toxicologists, risk assessors, and the communities living in close proximity to these sites.

SUBMITTER: Tilley SK

PROVIDER: S-EPMC5351294 | biostudies-literature | 2017 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Incorporating ToxCast and Tox21 datasets to rank biological activity of chemicals at Superfund sites in North Carolina.

Tilley Sloane K SK Reif David M DM Fry Rebecca C RC

Environment international 20170131

<h4>Background</h4>The Superfund program of the Environmental Protection Agency (EPA) was established in 1980 to address public health concerns posed by toxic substances released into the environment in the United States. Forty-two of the 1328 hazardous waste sites that remain on the Superfund National Priority List are located in the state of North Carolina.<h4>Methods</h4>We set out to develop a database that contained information on both the prevalence and biological activity of chemicals pre ...[more]

PMID: 28153528

Similar Datasets

Project description:The specificity of toxicant-target biomolecule interactions lends to the very imbalanced nature of many toxicity datasets, causing poor performance in Structure-Activity Relationship (SAR)-based chemical classification. Undersampling and oversampling are representative techniques for handling such an imbalance challenge. However, removing inactive chemical compound instances from the majority class using an undersampling technique can result in information loss, whereas increasing active toxicant instances in the minority class by interpolation tends to introduce artificial minority instances that often cross into the majority class space, giving rise to class overlapping and a higher false prediction rate. In this study, in order to improve the prediction accuracy of imbalanced learning, we employed SMOTEENN, a combination of Synthetic Minority Over-sampling Technique (SMOTE) and Edited Nearest Neighbor (ENN) algorithms, to oversample the minority class by creating synthetic samples, followed by cleaning the mislabeled instances. We chose the highly imbalanced Tox21 dataset, which consisted of 12 in vitro bioassays for?>?10,000 chemicals that were distributed unevenly between binary classes. With Random Forest (RF) as the base classifier and bagging as the ensemble strategy, we applied four hybrid learning methods, i.e., RF without imbalance handling (RF), RF with Random Undersampling (RUS), RF with SMOTE (SMO), and RF with SMOTEENN (SMN). The performance of the four learning methods was compared using nine evaluation metrics, among which F1 score, Matthews correlation coefficient and Brier score provided a more consistent assessment of the overall performance across the 12 datasets. The Friedman's aligned ranks test and the subsequent Bergmann-Hommel post hoc test showed that SMN significantly outperformed the other three methods. We also found that a strong negative correlation existed between the prediction accuracy and the imbalance ratio (IR), which is defined as the number of inactive compounds divided by the number of active compounds. SMN became less effective when IR exceeded a certain threshold (e.g.,?>?28). The ability to separate the few active compounds from the vast amounts of inactive ones is of great importance in computational toxicology. This work demonstrates that the performance of SAR-based, imbalanced chemical toxicity classification can be significantly improved through the use of data rebalancing.

Dataset Information

Incorporating ToxCast and Tox21 datasets to rank biological activity of chemicals at Superfund sites in North Carolina.

Publications

Incorporating ToxCast and Tox21 datasets to rank biological activity of chemicals at Superfund sites in North Carolina.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets