You are here:
Essential Set of Molecular Descriptors for ADME Prediction in Drug and Environmental Chemical Space
Citation:
Yin, Y., D. Chang, C. Grulke, C. Tan, M. Goldsmith, AND R. Tornero-Velez. Essential Set of Molecular Descriptors for ADME Prediction in Drug and Environmental Chemical Space. Research. Synatom Research, Lambertville, NJ, (1):996, (2014).
Impact/Purpose:
The National Exposure Research Laboratory’s (NERL’s) Human Exposure and Atmospheric Sciences Division (HEASD) conducts research in support of EPA’s mission to protect human health and the environment. HEASD’s research program supports Goal 1 (Clean Air) and Goal 4 (Healthy People) of EPA’s strategic plan. More specifically, our division conducts research to characterize the movement of pollutants from the source to contact with humans. Our multidisciplinary research program produces Methods, Measurements, and Models to identify relationships between and characterize processes that link source emissions, environmental concentrations, human exposures, and target-tissue dose. The impact of these tools is improved regulatory programs and policies for EPA.
Description:
Historically, the disciplines of pharmacology and toxicology have embraced quantitative structure-activity relationships (QSAR) and quantitative structure-property relationships (QSPR) to predict ADME properties or biological activities of untested chemicals. The question arises as to whether drug and environmental chemical domains have sufficient overlap in chemical space such that pharmaceutical datasets may help inform the development of predictive models of chemical toxicants, or vice versa. Herein, we provide a curated set of simplified molecular input line entry system (SMILES) notations and associated set of molecular descriptors for a combined dataset of 670 drugs [1] and 239 ToxCast Phase I chemicals [2]. This combined dataset serves the purpose of examining their shared chemical space, and establishes a default set of descriptors which may be scrutinized for predictive power for properties of interest. A workflow model in the Konstanz Information Miner (KNIME) platform is provided to assist the uninitiated with their first time foray into QSAR/QSPR modeling. The workflow is fully extensible for chemicals and molecular descriptors, is designed to relate a query sample to the training data via the k-Nearest Neighbors (k-NN) algorithm, and is amenable to multivariate descriptor space applicability domain (AD) inquiry.
URLs/Downloads:
http://www.labome.org/research/Essential-Set-of-Molecular-Descriptors-for-ADME-Prediction-in-Drug-and-Environmental-Chemical-Space.html