Pred-Skin app is based on statistically significant and externally predictive QSAR models of skin sensitization. The models were built using largest database containing human and LLNA data. So far, it is the only tool available for predicting skin sensitization based on human data!

Machine learning Technology

Developed as tool for indentify putative skin sensitizers. The Consensus models were generated averaging the predictions of individual models, achieving balanced accuracy, sensitivity, and specificity up to 0.70-0.84 with the coverage of 0.65-1.

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 easilly propose structural modifications.

Predict a single molecule



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.


Click on the “Predict Skin Sensitization” button.

Draw molecule or load a file

Bulk Predictions

Bulk prediction is useful when you want to generate predictions for a large set of compounds all at once, and then a link containing the results report will be available for download. Also, a copy of this report will be sent by email. Our system allows the evaluation of up to 10,000 compounds at once with low latency.

*To a better quality of predictions, please verify if the structures on your file are correct. For more information, please read: J. Chem. Inf. Model. 2010, 50, 1189–1204


The Pred-Skin app is a fast, reliable, and user-friendly tool and an alternative method for assessing skin sensitization potential of chemical substances. Chemically-induced skin sensitization is a complex immunological disease with a high impact on the quality of life and working ability. Despite some progress in developing alternative methods for assessing skin sensitization potential of chemical substances, there is no single in vitro test that correlates well with human data. Machine Learning (ML) models provide a rapid screening approach and contribute valuable information for the assessment of chemical toxicity. The app provides secure means for end users to make predictions using externally validated QSAR models for skin sensitization based on murine (LLNA) and human 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.



Pred-Skin employs machine learning models based on human and local lymph node assay (LLNA) skin sensitization information to help end users to "make right decisions faster."

Intuitive design

A user-friendly interface that integrates smoothly executing functions within the application.


A user-friendly interface that integrates smoothly executing functions within the application.

Download Pred-Skin

It’s the easiest make predictions on the go in the palm of your hand.

App Store Play Store