EPA Science Inventory

Toxicity challenges in environmental chemicals: Prediction of human plasma protein binding through quantitative structure-activity relationship (QSAR) models

Citation:

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. IVIE Workshop RTP, NC, RTP, NC, February 17, 2016.

Description:

The present study explores the merit of utilizing available pharmaceutical data to construct a quantitative structure-activity relationship (QSAR) for prediction of the fraction of a chemical unbound to plasma protein (Fub) in environmentally relevant compounds. Independent models were created with k nearest neighbor (kNN), support vector machines (SVM), and random forest (RF) algorithms, with the relevant regions of chemical space for predictions delineated. The optimal balance between accuracy and simplicity led to the creation of a “universal” QSAR model for Fub that can be applied to both pharmaceuticals and environmentally relevant chemicals.

Purpose/Objective:

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.

Record Details:

Record Type: DOCUMENT (PRESENTATION/POSTER)
Completion Date: 02/17/2016
Record Last Revised: 06/03/2016
Record Created: 06/03/2016
Record Released: 06/03/2016
OMB Category: Other
Record ID: 317810

Organization:

U.S. ENVIRONMENTAL PROTECTION AGENCY

OFFICE OF RESEARCH AND DEVELOPMENT

NATIONAL EXPOSURE RESEARCH LAB

COMPUTATIONAL EXPOSURE DIVISION