Prediction

The aim of the Prediction tool is to take advantage of the module activities to distinguish between phenotypes.

Metabolizer Prediction uses the module activity values to compute a RF or SVM prediction model with cross-validation. Moreover, previously obtained models can be used to predict the phenotype of new samples.

RF: Random Forest, SVM: Support Vector Machines

The tool can be accessed from the main menu bar, by clicking on the Prediction button, see Workflow for further information.

The main page of a the tool is its filling in form. This form includes all the information and parameters that the tool needs to process a job. The form is divided in different panels:

• Type
• Input data
• Design data
• Train Method
• Species
• Job information

Once the form has been filled in, press the Launch job button to launch a job. Your job will be listed in the My jobs panel, see Workflow for further information.

The results page of the Prediction tool includes different output results. You can download any table or image showed in the results page by clicking on the name right before it. You can also download calculated module activity values and CV statistics of trained model by clicking on Module activity values and Statistics respectively. CV results also represented by area under the Receiver Operating characteristic (ROC) curve.

CV: Cross Validation

The results are divided in different panels:

• Input Parameters
• Path values
• Prediction Model

• Input Parameters
• Path values
• Prediction Results