Target-Prediction

Here you can run a target prediction for your input compound:
There are different ways to start the prediction.
  • Search a compound by its name via pubchem
  • Create structure by smiles
  • Draw your structure
  • Load a molecule by clicking on

Pubchem-Name: e.g. Aspirin
Smiles: e.g. CC(=O)OC1=CC=CC=C1C(=O)O

The target prediction is based on the similarity distribution among the targets’ ligands. The distributions are utilized for estimating individual thresholds and probabilities for a specific target.

Your input compound will be screened against a database containing 1,800 mammal proteins, 341,000 compounds and 665,000 compound-target interactions.


As an example molecule Ulipristal was chosen. It is a new classified drug and isn't included in the dataset. By clicking on insert example Ulipristal is loaded into ChemDoodle. To classify it, please click on Start Target-Prediction.