STopTox 1.0

a machine learning app to assess the battery of acute
toxicity tests classically known as the “6-pack"

Powerful

STopTox app is based on statistically significant and externally predictive QSAR models of acute toxicity endpoints. The models were built using the largest properly curated database containing experimental data for each of the “6-pack” endpoints. So far, it is the only tool available for predicting all six acute toxicity tests that was developed using a highly curated dataset and following the best practices of development and validation of QSAR models.

Machine learning Technology

Developed as a tool for identify putative acute systemic and topical toxicants. The models showed high predictive power with vigorous validation metrics, achieving balanced accuracy, sensitivity, and specificity ranging from 71 to 94%.

Probability Maps

The probability maps allow the visualization of predicted fragment contribution. This method provides an easy interpretation of the predicted activity, allowing the user to easily propose structural modifications.

Predict a single molecule

Instructions


Insert SMILES

Directly paste the SMILES representation of the desired chemical structure.

or Draw

Draw the structure using the "Molecular Editor".

or Load a file

Click the right button on the whiteboard of the "Molecular Editor" and select "Paste MOL or SDF or SMILES"." SDF and MOL files are accepted.

Predict

Click on the “Predict STopTox” button.

Draw molecule or load a file

APP CHARACTERISTICS

The STopTox app is a fast, reliable, and user-friendly tool available as an alternative method for assessing the potential of chemicals to cause acute toxicity.The acute toxicity tests are used to identify hazard potentials resulting from short exposure times. The battery of in vivo assayscommonlyknown as “6 pack” assays are required by many regulatory agencies to evaluate several aspectsof acute toxicity in humans, including acute oral toxicity, acute dermal toxicity, acute inhalation toxicity, skin irritation and corrosion, eye irritation and corrosion, and skin sensitization. The indiscriminate use of animals in laboratory tests have been a public and political concern. Despite some progress in developing alternative methods for assessing the toxicity potential of chemical substances, there are few in vitro testsdeveloped to address all “6-pack” endpoints. Machine Learning (ML) models provide a rapid screening approach and contribute valuable information for the assessment of chemical toxicity. The app provides easy and reliablemeans for end users to make predictions using externally validated QSAR models for each of the “6-pack” tests based on experimental animal data. The predictions for a single compound run in a few seconds and the app does not require computational of programming skills from the user.