pdCSM-GPCR is a machine-learning platform to predict GPCR ligands, which relies
on distance/pharmacophore patterns encoded as graph-based and auxiliary signatures.
The platform is composed of 36 regression models, trained and tested on different experimental
data sets encompassing a diverse and complementary set of GPCRs as follows:
To run a prediction:
For a single molecule prediction, your results can be displayed as follows:
In case you experience any trouble using pdCSM-GPCR or have any suggestions or comments, please do not hesitate in contacting us either via e-mail or through the online form.