Related Experiment Video
Updated: Mar 3, 2026
In Silico Modeling Method for Computational Aquatic Toxicology of Endocrine Disruptors: A Software-Based Approach Using QSAR Toolbox
Published on: August 28, 2019
A Semi-automated Approach to Create Purposeful Mechanistic Datasets from Heterogeneous Data: Data Mining Towards the
M Bashir Surfraz1, Adrian Fowkes1, Jeffrey P Plante1
1Granary Wharf House, 2 Canal Wharf, Holbeck, Leeds, LS11 5PS, United Kingdom.
Abstract:
The need to find an alternative to costly animal studies for developmental and reproductive toxicity testing has shifted the focus considerably to the assessment of in vitro developmental toxicology models and the exploitation of pharmacological data for relevant molecular initiating events. We hereby demonstrate how automation can be applied successfully to handle heterogeneous oestrogen receptor data from ChEMBL. Applying expert-derived thresholds to specific bioactivities allowed an activity call to be attributed to each data entry. Human intervention further improved this mechanistic dataset which was mined to develop structure-activity relationship alerts and an expert model covering 45 chemical classes for the prediction of oestrogen receptor modulation. The evaluation of the model using FDA EDKB and Tox21 data was quite encouraging. This model can also provide a teratogenicity prediction along with the additional information it provides relevant to the query compound, all of which will require careful assessment of potential risk by experts.
Insights
This study developed an automated model for predicting estrogen receptor modulation using chemical data, offering an alternative to animal testing for toxicity assessments and aiding in teratogenicity prediction.
Area of Science:
- Toxicology
- Computational Chemistry
- Pharmacology
Background:
- Rising costs and ethical concerns necessitate alternatives to animal studies for developmental and reproductive toxicity testing.
- In vitro models and pharmacological data are increasingly used for molecular initiating events assessment.
- Oestrogen receptor (OR) modulation is a key endpoint in toxicity testing.
Purpose of the Study:
- To develop an automated approach for handling heterogeneous oestrogen receptor data.
- To build a predictive model for oestrogen receptor modulation and teratogenicity.
- To reduce reliance on animal testing in toxicity assessments.
Main Methods:
- Automated handling of oestrogen receptor data from ChEMBL using expert-derived thresholds.
- Development of structure-activity relationship (SAR) alerts and an expert model for 45 chemical classes.
- Model evaluation using FDA EDKB and Tox21 datasets.
Main Results:
- Successfully applied automation to heterogeneous oestrogen receptor data.
- Developed a predictive model for oestrogen receptor modulation with encouraging evaluation results.
- The model provides teratogenicity prediction and relevant compound information.
Conclusions:
- The developed automated model offers a viable alternative to animal testing for oestrogen receptor modulation and toxicity prediction.
- Expert intervention enhanced the mechanistic dataset and model performance.
- The model aids in assessing potential risks of chemical compounds.
