Endocrine System Disruption

Overview

Estrogen Receptor module provides an estimate of the risk of reproductive toxicity associated with compound binding to estrogen receptor alpha which is one of main targets for endocrine disrupting chemicals. Predictor included in Tox Boxes allows discriminating between high affinity estrogen receptor ligands, weak binders, and non-binders.

Features

• Endocrine disruption module predicts probabilities of the test compound exhibiting Log RBA > 0 and Log RBA > 3, and classifies the analyzed chemicals according to their estrogen receptor binding affinity.

• Lists all the rules applicable to the calculation of irritation potential of the analyzed molecule along with their descriptions.
• Highlights the structural fragments corresponding to the listed rules on the molecule of interest.
• Developed predictive models are also suitable for calculation of irritational properties for the salts of common organic electrolytes.
• Utilizes critically evaluated data sets of experimental rabbit eye and skin irritation results with >2000 compounds each compiled from nearly 100 references.
• Provides a list of up to five most similar structures from the training set with the experimental values of their standard Draize test result and references.

Interface

File:estrogen receptor.png

1. The highlighted structural fragment corresponds to the rule (alert) selected from the list.
2. Calculated probability for a compound to cause moderate or stronger rabbit skin irritation in a standard Draize test.
3. A list of all the rules (alerts) applicable to the particular calculation with their descriptions. A substructure associated with the selected rule is highlighted in the Structure pane.
   Click the alert to see a corresponding substructure.
4. Up to 5 records of similar compounds from the training set, including structure name, CAS number (if available), experimental values and references.

Technical information

Calculated quantitative parameters

In vitro measurement of estrogen receptor binding affinity (Log RBA) estimates the relative affinity of compound to receptor compared to reference ligand estradiol: %RBA = IC50(reference)/IC50(test compound) * 100%. Here IC50 is the concentration at which the unlabeled ligand displaces half of specifically bound radiolabeled 17β-estradiol to the ER, (reference estrogen in a typical experiment is the same 17β-estradiol). Experimental data were converted to binary representation with two cut-offs at Log RBA = -3, and Log RBA = 0. Predicted values are probabilities that tested compound will have Log RBA higher than the defined cut-offs. Based on the predictions compounds are classified as strong binders (Log RBA > 0), weak binders (Log RBA most probably falling in the range from -3 to 0), and non-binders (Log RBA < -3).

Experimental data

Experimental data that was used for the development of predictive models was collected from various reference databases (Endocrine disruption - FDA Endocrine Disruptors DB, Risk Assessment of Endocrine Disruptors (METI)), as well as original publications. After thorough verification of the obtained values the final data sets contained nearly 1500 compounds with experimentally measured ER alpha binding affinities.

Model features & prediction accuracy

The predictive models of Endocrine System Disruption were built using binomial PLS method in Algorithm Builder. The models incorporated essential physicochemical properties of chemicals such as ionization and molecular size as well as fragmental descriptors including predefined substructures representing structural features known to have a profound influence on the analyzed property.

The resulting models are highly accurate: overall accuracy of ER alpha affinity predictions exceeds 85% in both training and test sets in case of general binding model (Log RBA > -3), and exceeds 90% in case of strong binding (Log RBA > 0).