You are here:
Toxicity challenges in environmental chemicals: Prediction of human plasma protein binding through quantitative structure-activity relationship (QSAR) models (2016 IVIVE Workshop Proceedings)
Ingle, B., B. Veber, J. Nichols, AND R. Tornero-Velez. Toxicity challenges in environmental chemicals: Prediction of human plasma protein binding through quantitative structure-activity relationship (QSAR) models (2016 IVIVE Workshop Proceedings). In Proceedings, IVIVE Workshop, RTP, NC, February 17, 2016. U.S. Department of Health & Human Services, NIEHS, Research Triangle Park, NC, 4, (2016).
The National Exposure Research Laboratory (NERL) Computational Exposure Division (CED) develops and evaluates data, decision-support tools, and models to be applied to media-specific or receptor-specific problem areas. CED uses modeling-based approaches to characterize exposures, evaluate fate and transport, and support environmental diagnostics/forensics with input from multiple data sources. It also develops media- and receptor-specific models, process models, and decision support tools for use both within and outside of EPA.
Physiologically based pharmacokinetic (PBPK) models bridge the gap between in vitro assays and in vivo effects by accounting for the adsorption, distribution, metabolism, and excretion of xenobiotics, which is especially useful in the assessment of human toxicity. Quantitative structure-activity relationships (QSAR) serve as a vital tool for the high-throughput prediction of chemical-specific PBPK parameters, such as the fraction of a chemical unbound by plasma protein (Fub). The presented work explores the merit of utilizing experimental pharmaceutical Fub data for the construction of a universal QSAR model, in order to compensate for the limited range of high-quality experimental Fub data for environmentally relevant chemicals, such as pollutants, pesticides, and consumer products. Independent QSAR models were constructed with three machine-learning algorithms, k nearest neighbors (kNN), random forest (RF), and support vector machine (SVM) regression, from a large pharmaceutical training set (~1000) and assessed with independent test sets of pharmaceuticals (~200) and environmentally relevant chemicals in the ToxCast program (~400). Small descriptor sets yielded the optimal balance of model complexity and performance, providing insight into the biochemical factors of plasma protein binding, while preventing over fitting to the training set. Overlaps in chemical space between pharmaceutical and environmental compounds were considered through applicability of domain (AD) assessment and quantified through reliability estimates. The pharmaceutical and environmental test sets exhibited similar variance and predictability, indicating the combination of a large pharmaceutical training set with a small feature space yields a generalized model for Fub with adequate coverage of environmentally relevant chemical space. Thus, the presented work provides a reliable model for the high-throughput predictions of Fub in environmentally relevant chemicals, a critical component in of in silico toxicity screening.