Glide WS - Model Generation Panel (Deprecated)

Build a trained scoring model for docking to a particular protein target. The model uses an ensemble of protein structures (conformations) for the target, data from assessment of water thermodynamics from MD simulations (WaterMap), experimental binding affinities for known ligands (which form a training set), a test set of actives and a set of decoys to determine the enrichment of the training set and the test set. The scoring function includes penalties and interactions that are specific to the target.

To open this panel, click the Tasks button and browse to Receptor-Based Virtual Screening → Glide WS Model Generation.

  • Using
  • Features
  • Additional Resources

Using the Glide WS - Model Generation Panel

Prior to opening the panel, you should perform the following tasks:

  1. Select a set of complexes for the target of interest to use as a training set for the model. These complexes must have known binding affinities, and should represent conformations of a single protein.

  2. Prepare the complexes with the Protein Preparation Workflow Panel. You should do a full preparation, including fixing structural defects, prediction of het states for the ligand, Epik penalties, H-bond assignment, and minimization.

  3. Align the complexes with the Align Binding Sites tool. You should perform the alignment before you generate WaterMap data. If you want to use a pregenerated WaterMap for one of your complexes, you must align the remaining complexes to the receptor used for the WaterMap. If you want to pregenerate WaterMap data for your complexes, you must align them first. If you have more than one WaterMap that you want to use and they are not aligned, you can use the script rotate_all.py to align them. For instructions run it with the -h option,

    $SCHRODINGER/run rotate_all.py -h

  4. (Optional) Select a test set of known actives, and prepare them with LigPrep. Include the Epik state penalties. Ensure that these actives all have titles and that the titles are different for each active. The test set should be stored in a file, as it is read from file rather than taken from the project.

  5. (Optional) If you want to use your own decoy set for the enrichment assessment, you should prepare them as you did for the test set.

To set up and run the model generation job:

  1. Add the prepared and aligned complexes to the table. If the complexes are already in the project, select them in the Project Table and click From Project; otherwise click From File, and load the files. You can choose files with more than one complex; all complexes are read from each file. If the complexes have associated WaterMap data, it is read and added to the table; if not you can specify the location of the data or choose to have it generated automatically.

  2. Change the titles of the complexes if necessary. The title must be unique. If the complexes do not have titles, a unique title is supplied.

  3. Check that the ligand is correct for each complex. To do this, click the In column for the complex. The complex is displayed in the Workspace, and markers are placed on the ligand. To change the ligand, click the ligand cell in the table, then pick the ligand in the Workspace, and click OK in the dialog box that opens when you click the cell. You might have to change the ligand if the complex has more than one ligand-sized molecule (e.g. cofactors), as the first of these is the one that is chosen automatically.

  4. Check that the binding free energies are correct for each complex. If not, you can edit the cell to provide the correct value. You must have a value for each complex to run the model generation.

  5. If you want to include Epik state penalties, select Add Epik state penalties to docking score.

  6. Specify the test set of ligands. You need not provide a test set; if you do, click Browse to navigate to the file you created in the preparation stage.

  7. Choose the source of the decoy ligands. If you choose to use your own decoys, click Browse to navigate to the file you created in the preparation stage.

  8. Start the job.

    If this is the first time you have run a model generation job, click the Settings button (gear icon) and choose Run Settings, then choose a GPU host for the job. The WaterMap jobs take about 1.5 hours on a GPU. When you have finished making settings, click Save and Start to save the settings and start the job.

    If you have already made appropriate job settings, click the Run button.

The results of the enrichment and the assessment of the quality of the model are available in the log file, which you can view in the Monitor panel.

Glide WS - Model Generation Panel Features

 

Use structures from option menu

Specify the source of the structures to use for the model.

  • Project Table (selected entries)—Use the entries that are selected in the Project Table as the source of the structures.

  • File—Use the specified file as the source of the structures. All structures in the file are used. The supported file types are Maestro (.mae, .mae.gz, .maegz), SD (.sdf, .sdf.gz, .sdfgz).

    When you select this option, a File name text box and Browse button are displayed, so you can enter the file name in the text box, or click Browse and navigate to the file.

Training set protein-ligand complexes table

This table lists the protein-ligand complexes that have been added to the training set for model generation.

  • To sort the rows by the values in one of the columns, click the column heading.
  • To add rows to the table, use the Add buttons.
  • To delete rows from the table, select the rows, and press the Delete key, or right-click in the table and choose Delete from the shortcut menu.
  • To export the table data in CSV or HTML format, right-click in the table and choose Export Table Data then the format.

The table columns are described below.

Row Table row number. Noneditable. You can sort the table by the row number to restore the table to the order in which the complexes were imported.
In Check box to control the inclusion of the complex in the Workspace. To include a complex in the Workspace, check its In box. All other structures are excluded (removed) from the Workspace. To include multiple complexes in the Workspace, you can use shift-click and control-click to select the complexes, just as for row selection. This behavior is the same as in the Project Table. The ligand is highlighted in each complex.
Receptor title Title of the receptor. The title is taken from the Title property in the file, if added from file, or from the Project Table. If the title is blank, a default title is added. You can edit the table cell to change the title. The title must be unique; if it is not unique on addition or editing, it is made unique by appending text.
Ligand ASL Identity of the ligand molecule in terms of an ASL expression (Atom Specification Language). You can choose a different ligand molecule by clicking the table cell, then picking an atom in the desired ligand molecule in the Workspace. When you have picked the molecule, click OK in the dialog box that is displayed when you click the table cell. If you make a mistake when picking the ligand molecule, just pick again before clicking OK. You might need to do this if the complex has cofactors as well as the ligand, for example.
The 2D structure of the ligand is displayed in a tool tip when you pause the pointer over the table cell.
Binding free energy (kcal/mol) Experimental binding free energy of the ligand to the receptor. The value is set when you add the complex, if you choose a binding property. Otherwise, you can edit the table cell to enter the value. You must enter a value in kcal/mol: the value is not automatically converted from other units, as it is when you add the complex. All complexes must have a value of this property before you can start the job to generate the model.
WaterMap Data Source of WaterMap data. If the WaterMap is being generated as part of the job, the source is "Create automatically", otherwise it is the full path of the WaterMap file to be used for the complex. You can right-click in a table row and choose Choose WaterMap Data to change the source of the WaterMap data.
Required in Ensemble Check the box in this column if you want to require a receptor to be in the ensemble, rather than allowing the receptors to be selected by the algorithm.
Details for the selected complex options

Lists the Entry ID / Title, and options for the Ligand / ASL, Binding Free Energy, and WaterMap.

Ligand Detection link
Opens the Preferences Panel to the Ligand Detection tab.

Specify additional ligands for the training set, the ligands to use in the test set and the ligands to use for the decoys. The test set is used to run a docking enrichment study with a set of decoys. The training set is also used in an enrichment study with the same set of decoys.

The ligands must be properly prepared for docking, for example by running LigPrep. They should also have titles that are unique for each ligand (though not for tautomers or ionization states).

Job toolbar

Manage job submission and settings. See Job Toolbar for a description of this toolbar.

The Job Settings button opens the Glide WS - Model Generation - Job Settings Dialog Box (deprecated), where you can make settings for running the job.

Status bar

The status bar displays information about the current job settings and status for the panel. The settings includes the job name, task name and task settings (if any), number of subjobs (if any) and the host name and job incorporation setting. The job status can include messages about job start, job completion and incorporation.

Use the Reset button to reset the panel to its default settings and clear any data from the panel. You can also reset the panel from the Job toolbar.

The status bar also contains the Help button , which opens the help topic for the panel in your browser. If the panel is used by one or more tutorials, hovering over the Help button displays a button, which you can click to display a list of tutorials (or you can right-click the Help button instead). Choosing a tutorial opens the tutorial topic.

Tutorials

Quick Reference Sheets

Related Topics