You are here:
Comparison of Global and Mode of Action-Based Models for Aquatic Toxicity
Martin, T., D. Young, CrystalR Jackson, AND M. Barron. Comparison of Global and Mode of Action-Based Models for Aquatic Toxicity. Journal of Chemical Information and Modeling. American Chemical Society, Washington, DC, 26(3):245-262, (2015).
The purpose of this paper is to compare the predictive ability of global and mode of action based acute aquatic toxicity models.
The ability to estimate aquatic toxicity for a wide variety of chemicals is a critical need for ecological risk assessment and chemical regulation. The consensus in the literature is that mode of action (MOA) based QSAR (Quantitative Structure Activity Relationship) models yield the most toxicologically meaningful and theoretically, the most accurate results. In this study, a two-step prediction methodology was developed to estimate acute aquatic toxicity from molecular structure. In the first step, one against the rest linear discriminant analysis (LDA) models were used to predict the MOA. In the second step, a multiple linear regression (MLR) model corresponding to the predicted MOA was used to predict the acute aquatic toxicity value. The MOA-based approach yielded comparable results to a global MLR model, and similar prediction accuracy to a single MLR model fit to the entire training set. Overall, the global hierarchical clustering approach yielded higher accuracy and prediction coverage than the MOA based approach. Utilizing multiple two dimensional chemical descriptors in MLR models yielded comparable results to using only the octanol water partition coefficient (LogKow). These results show the development of MOA-based QSARs is limited by higher dataset requirements and the commonly used aquatic toxicity QSAR parameter of LogKow can provide reasonable prediction accuracy for many chemical classes.
Record Details:Record Type: DOCUMENT (JOURNAL/PEER REVIEWED JOURNAL)
Organization:U.S. ENVIRONMENTAL PROTECTION AGENCY
OFFICE OF RESEARCH AND DEVELOPMENT
NATIONAL RISK MANAGEMENT RESEARCH LABORATORY
SUSTAINABLE TECHNOLOGY DIVISION
CLEAN PROCESSES BRANCH