Case Study
MetaP – Metabolism Prediction


Metabolites may well play an important role in adverse effects of parent drug (or other xenobiotic) compounds. In this case study we use and integrate ligand-based metabolite predictors (e.g. MetPred, MetaPrint2D) and we will implement protein-structure and -dynamics based approaches to predict the site of metabolism (SOM) by Cytochrome P450 enzymes, which metabolize ~75% of the currently marketed drugs and their active-site shape and plasticity often play an important role in determining the substrate’s SOM. During method development, model calibration and validation we will use data from XMetDB and other open-access databases for drugs, xenobiotics and their respective metabolites.


For metabolite prediction we will develop, integrate and combine tools for:

  • Protein-structure and -dynamics based prediction of CYP450 metabolite formation;
  • Inclusion of reactivity descriptors in the structure-based predictions;
  • Affinity and selectivity models for CYP450 binding;
  • Site-Of-Metabolism prediction using circular fingerprints;
  • Predicting probabilities for specific reaction type events.

Risk assessment framework

Prediction outcomes can serve as input for other molecular structure-based adverse outcome (AO) predictors, which relates to Tier 0 (Step 1: identification of molecular structure) and Tier 1 (Step 6: mechanism of action) in the selected framework.

Use Cases Associated

MetaP is associated with UC2 - Building and using a prediction model. For improved metabolite prediction (and thereby improved input for other predictors) we will explore the potential of combining different approaches.

Databases and tools

XMetDB, SMARTcyp, ZINC, ChEMBL, MetPred, MetaPrint2D, ParaDocks, PLANTS, GROMACS.

Service integration

To facilitate combining metabolite prediction approaches and using MetaP outcomes as input for other predictors, we will take advantage of ongoing development in workflow management systems (Nextflow, Squonk, MDStudio) and we will explore integration into/with and use of these platforms.

Currently available services:

  • Service type: Service
  • Service type: Model generation tool, Trained model, Service
  • Interactive computing and workflows sharing
    Service type: Helper tool, Visualisation tool, Processing tool, Analysis tool, Software, Workflow
  • Service type: Trained model, Service
  • Computation research made simple and reproducible
    Service type: Database / data source, Service, Workflow