GLORYx
Predicting Phase I and Phase II Metabolites

About GLORYx

GLORYx was designed to predict metabolites of xenobiotics that can be formed in humans in phase I and phase II meabolism. GLORYx is based on a two-pronged approach consisting of the following aspects: the incorporation of sites of metabolism (SoMs) predicted by FAME 3 and the transformation of molecules into their potential metabolites using reaction rule sets. Users can choose to predict metabolites for phase I, phase II, or both phase I and phase II.

Incorporating Site of Metabolism Prediction

SoM prediction is the prediction of metabolically labile atom positions in a molecule. FAME 3, which was developed previously in our research group, is a machine learning-based tool that was developed to predict SoMs for phase I and phase II metabolism in humans. The models were developed using the extremely randomized trees algorithm and 2D circular descriptors of atoms and their environments. FAME 3 was shown to have a high level of accuracy, achieving Matthews correlation coefficients (MCC) of 0.53 and 0.71, and AUCs of 0.88 and 0.97, on independent test sets for phase I and phase II metabolism, respectively. For more details on FAME 3, see the FAME 3 publication.

GLORYx uses SoM prediction with FAME 3 as a key step in the prediction of the metabolite structures. The reaction rules are applied at all positions in the molecule regardless of the SoM probabilities that FAME 3 predicted for the atoms involved in the reaction. The predicted SoM probabilities are used to score the predicted metabolites, as part of a new scoring approach that was previously found to be effective for CYP metabolism (see GLORY) and continues to be effective for both phase I and phase II metabolism.

Reaction Rules

The full list of reaction rules, including reaction type and SMIRKS, can be found in the publication on GLORYx. The phase I reaction rules include the reaction rule set developed for GLORY, as well as additional rules.

Scoring and Ranking of Predictions

The predictions made by GLORYx are scored and ranked (per input molecule) based on the predicted SoM probabilities of the atoms involved in the reaction and a simple binary weighting of the corresponding reaction type.

Further Information

For more details on the method development and evaluation of GLORYx, including the reaction rules and the datasets, please refer to the publication.

Usage

Enter SMILES, draw a molecule, or upload a file (.smi or .sdf). The input file may contain up to 1,000 molecules if it is a SMILES file or be up to 40 MB in size (approximately 15,000 molecules) if it is an SDF file. Please note that files larger than a few MB may take some time to upload. Click submit to start the calculation. You will then be forwarded to the result page.

Note that GLORYx only makes predictions for input molecules containing at least 3 heavy atoms and does not predict any metabolites containing fewer than 3 heavy atoms. Note also that GLORYx can not make predictions for molecules containing any atoms other than the following: C, N, S, O, H, F, Cl, Br, I, and P. This is the case because FAME 3 can not make predictions for molecules containing atoms that are not included in this list.

Preferred Format of Input Molecules for Best Results

Each SMILES and/or SDF entry should represent a single-component molecule. No predictions are made for multi-component molecules.

All molecules should be neutral and already have explicit hydrogens added. If there are missing hydrogens, the software will attempt to automatically add correct hydrogens before making predictions.

Output

On the result page, you will be able to download the predicted metabolites. For inputs of up to 1000 molecules, the predicted metabolites are available for download as a single SDF file. If the number of input molecules is larger than 1000, the output is split into multiple SDF files corresponding to batches of 1000 input molecules. These SDF files are available for download as a ZIP file.

Each .sdf file provides each input molecule followed by all of its predicted metabolites. If the input was in SDF format, each input molecule is included in the output SDF file with its original coordinates and properties, as well as an additional property called "ID_GLORYx" which contains the ID for that molecule, to enable further clarity in terms of recognizing which predicted metabolites correspond to which input molecule. If the input was in SMILES format, the SDF entry for each input molecule contains a property containing the original input SMILES for that molecule.

The structures of the predicted metabolites are provided along with the following information for each predicted metabolite:

• Rank (among predicted metabolites for the particular parent molecule)
• Score
• Reaction name
• Identifying information for the parent molecule (i.e. the input molecule for which the metabolite was predicted):
  • InChI
  • SMILES
  • ID
  If there were multiple input molecules, the ID of the parent molecule corresponds to the molecule’s position in the ordered list of input molecules (i.e. its position in the input file).

If the same metabolite was predicted via multiple reaction rules, the information corresponding to the version with the highest score is reported.

Viewing the Predicted Metabolites

If the input contains fewer than 25 molecules, the individual predictions for each input molecule can be viewed on the result page. If no predictions could be made for a particular input molecule, a corresponding error message is displayed.