Activity 2

Objectives: Supervised Classification for two experimental groups

Data:

• TCGA_265_mod_gene_LUSC_train.txt: RNA-Seq data of Lung squamous cell carcinoma (LUSC) samples taken from The Cancer Genome Atlas (TCGA) data portal. Contains 11 Normal and 150 Tumor samples. NOTE: It is always recommended to use balanced sample size to avoid biased training.
• TCGA_265_mod_gene_LUSC_test.txt: RNA-Seq data of Lung squamous cell carcinoma (LUSC) samples taken from The Cancer Genome Atlas (TCGA) data portal. Contains 6 Normal and 75 Tumor samples.

Workflow + questions:

1. Explore both files from a text editor:
   • How many genes and samples are there for each file?
   • Any specific detail about headers?
2. Upload your files to Babelomics 5.0. Go to section Expression > Class Prediction
3. Select these parameters:
   • SVM, KNN and Random Forest
   • Leave-one-out for error estimation
   • Correlation-based Feature Selection (CFS)
4. Download test_result.txt and answer these questions:
   • Which supervised classification method(s) works better?
   • How many genes were used for the prediction?
   • Are the selected genes same for all methods?