Drop file with SIMILES (line separated or as this example file) here.

The TSV (tab separated) file must contain a header indicating which column is the identifier (id) and which column is the SMILE descriptor. For example in the provided example file, the first column corresponds to the compound identifier (free text) and the second to the SMILE descriptor.

Max SMILEs per request: 100

CoMpOund enZyme interAction pRedicTor

The main aim of MOZART (coMpOund enZyme interAction pRedicTor) is to identify the interaction between a compound and enzyme subclasses targets. The model implanted in the platform was developed using a multi-target machine learning model based on an artificial neural network multi-layer perceptron algorithm.

The presented model was able to predict enzymatic reactions of a query molecule with a high accuracy. The input data is codified in the SMILE specification and the model is be able to predict the Enzyme Commission number (EC number) that the reactions can catalyze.

If you are interested in making a large number of requests or in the possibility of calling the application via an API rest, please contact us

MOZART could be downloaded as free open-source software at https://github.com/mpperez3/MOZART or in their java-compiled version at https://zenodo.org/record/4453296.