Pred-hERG 4.2

a machine learning app to assess the cardiac
toxicity via hERG inhibition

Pred-hERG 4.2

Support the decision making in early stages of
Drug Discovery!

what's new!

-More intuitive displayed hERG results (prediction and potency);
-Models are  retrained with Random Forest and ECFP with bond diameter 6 (ECFP6);
-Similar off-target compounds are now based on MACCS fingerprints to display more relevant similar compounds;
-Implementation of the applicability domain (AD);


Pred-hERG is based on statistically significant and externally predictive QSAR models of hERG blockage. Inferring new instructions from data is the core strength of machine learning. It also highlights the critical role of data: the more data available to train the algorithm, the more it learns.

Machine learning Technology

Developed as a tool for identifying putative hERG blockers. The consensus models were generated averaging the predictions of individual models, achieving balanced accuracy, sensitivity, and specificity as high as 89%-90%.


The largest publicly available dataset for hERG liability was retrieved from the ChEMBL 23 database containing 16,932 associated bioactivity records of hERG K+ blockage for 8,531 unique organic compounds. The curated dataset used in our publication containing 5,984 compounds is available for download here

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.

Fast prediction

Predictions are fast and predictions for one chemical appear directly on the screen. Indeed, simpler models (e.g. linear instead of non-linear, or with fewer parameters) often run faster but are not always able to take into account the same exact properties of the data as more complex ones.

OECD regulatory compliance

Our models also satisfy the guidelines of the Organisation for Economic Cooperation and Development (OECD) principles and the list of tests required by Registration, Evaluation, Authorisation and Restriction of Chemical substances (REACH) for successful toxicity assessment.

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 hERG Liability” button.

Draw molecule or load a file

Get in Touch with Us

Our Headquarter is in Brazil

LabMol, Faculdade de Farmácia, Universidade Federal de Goiás
Rua 240, Qd. 87, Setor Leste Universitário, Goiânia, Goiás 74605-170, Brazil.
Phone: (+55) 62 3209 6451
Fax: (+55) 62 33209 6037
Feature Request:
Use this form to request new features or suggest modifications to existing ones
Bug Report:
Your comments, suggestions, and ideas for improvements are very important to us.

We are social

Subscribe to our Newsletter

Stay informed on our latest news!