FAME 3
Prediction of phase 1 and phase 2 sites of metabolism (SoMs)

Mode

Provide input molecules:

Enter SMILES

Example: CN1CCN(Cc2ccc(cc2)C(=O)Nc3ccc(C)c(Nc4nccc(n4)c5cccnc5)c3)CC1 (imatinib)

or upload a file with a list of SMILES
or upload an sdf file
or draw your own molecule

FAME3

FAME 3 is a collection of machine learning models for prediction of both phase 1 and phase 2 sites of metabolism (SoMs). SoMs are atoms where a metabolic reaction gets initiated and, thus, are a good starting point for determining the metabolic fate of xenobiotic compounds.

FAME 3 was developed in collaboration with Dr. Angelica Mazzolari, Prof. Alessandro Pedretti and Prof. Giulio Vistoli from the Drug Design Laboratory of the University of Milan and em. Prof. Bernard Testa from the University of Lausanne.

FAME 3 is free for non-commercial and academic research. For-profit institutions may use FAME 3 for testing purposes and contact us for a commercial licence.

For more information, see the About page.

How to cite

If you are using FAME 3 for your research, please cite:

Šícho, M.; Stork, C.; Mazzolari, A.; de Bruyn Kops, C.; Pedretti, A.; Testa, B.; Vistoli, G.; Svozil, D.; Kirchmair, J. FAME 3: Predicting the Sites of Metabolism in Synthetic Compounds and Natural Products for Phase 1 and Phase 2 Metabolic Enzymes. J. Chem. Inf. Model. 2019.
doi: 10.1021/acs.jcim.9b00376

Choosing a mode

Phase 1 and Phase 2 metabolism
Phase 1 metabolism
Phase 2 metabolism
  • Default recom­mended mode.
  • Recom­mended if only phase 1 reactions are of interest.
  • Recom­mended if only phase 2 reactions are of interest.
  • Utilizes the global metabolism model to predict phase 1 and phase 2 reactions at the same time. This model covers a large variety of phase 1 and phase 2 reactions as described in the FAME 3 publication and should be suitable in most use cases.
  • Since this a slightly simpler model, it might have a greater gener­alization ability in the case of phase 1 reactions than the global model.
  • Since this utilizes a simpler model, it might have a greater gener­alization ability in the case of phase 2 reactions than the global model.