Skip to Main Navigation
Skip to Page Content
Share This:

Computer Models of Chemical Activity

Using structural data to generate activity predictions for new or poorly characterized chemicals can help researchers and regulators make decisions about further testing needs.

List of projects for chemical activity computer models
Project Description Publication
Open-source quantitative structure-property relationship tools NICEATM and collaborators at EPA developed tools that use molecular structures to predict the physicochemical features for a wide range of substances.
Quantitative structure–activity relationship (QSAR) models to screen for potential skin sensitizers NICEATM and collaborators at the University of North Carolina-Chapel Hill (UNC-CH) developed QSAR models of human data that can either be combined with or used instead of animal data to screen for potential skin sensitizers.
Open-source tools for predicting estrogen and androgen receptor pathway activity NICEATM is creating open-source versions of published computational models to predict activity relevant to endocrine disruption. Predictions from these models are available through NICEATM's Integrated Chemical Environment (ICE) resource.
QSAR models to predict critical parameters for in vitro to in vivo extrapolation (IVIVE) NICEATM—as part of an open-source workflow for IVIVE—is developing QSAR models to predict properties, such as human plasma fraction unbound and hepatic intrinsic clearance, that affect how substances behave in biological systems. In progress
International collaborations to predict estrogenic, anti-androgenic, and acute systemic toxicity NICEATM and EPA ran three global collaborations to leverage the expertise of the world-wide modeling community to predict estrogenic activity (CERAPP), anti-androgenic activity (CoMPARA) and acute oral systemic toxicity (CATMoS). Predictions from these models will be available through the EPA Chemistry Dashboard.
QSAR models to predict physicochemical properties, environmental fate and toxicological endpoints The existing OPERA (Open-source Structure activity Relationship App) resource was updated to include QSAR models to predict physicochemical properties such as lipid-aqueous partition coefficient and acid dissociation constant. The consensus models from CERAPP, CoMPARA and CATMoS were also added to the standalone application.
  • Cariello N, et al. Open-source QSPR models for pKa prediction using multiple machine learning approaches. (in preparation).
  • OPERA on NIEHS GitHub site
Development of QSAR models to predict additional toxicity endpoints

NICEATM is planning to develop QSAR models to predict the following additional toxicity endpoints:

  • Substrate selectivity for glucuronidation
  • Intestinal cell permeability
  • Acute toxicity endpoints: skin sensitization potency, ocular irritation, dermal irritation, acute systemic inhalation toxicity
  • Fish acute toxicity (LC50)
  • Cancer hallmarks and key characteristics of carcinogens
  • Mechanisms of developmental toxicity
In progress