1. Log in into Metabolizer. For further information on this step visit Logging in.

2. We will work with a Breast Cancer dataset from the repository The Cancer Genome Atlas. You can download the expression matrix and the experimental design from these links:

• Expression matrix: brca_genes_vals_bn.txt
• Experimental design: brca_normal-basal_ed.txt

3. Upload the data to Metabolizer in the data panel by clicking on My data. For further information on this step visit Upload your data.

4. Press the Prediction button.

5. In the Type panel select Train new model.

6. In the Input data panel select Expression matrix. Press the File browser of the Expression matrix file, and select the desired file.

7. In the Design data panel select Two group comparison. Press the File browser of the Experimental design file, and select the desired file. Automatically Condition 1 and Condition 2 files are selected. Change Condition 1 to “Tumor” and Condition 2 to “Normal”.

8. Select Human as species (by default).

9. In the Function level analysis, check both checkboxes, Gene ontology and Uniprot keywords.

10. In the Pathways panel select all the pathways (by default).

11. In the Job information panel, press the File browser button and select the desired output folder. In this case we will use analysis. Give a name to the job, for example “BRCA train model”.

12. Press the Launch job button. A job will be created and listed in the jobs panel. You can access this panel by clicking on the My jobs button.