HNSC LUSC Classifier

Head and neck cancer (HNSC) patients are at risk of suffering from both pulmonary metastases or a second squamous cell carcinoma of the lung (LUSC). Differentiating pulmonary metastases from primary lung cancers is of high clinical importance, but not possible in most cases with current diagnostics. To address this, we used DNA methylation profiling of primary tumors in combination with three different machine learning methods.

The code provided can be used to generate all figure tiles shown in the manuscript that were generated using R based on the preprocessed data. Furthermore, it can be used to apply the three classifiers (neural network, support vector machine, random forest) to new IDAT files or to four example cases from the TCGA LUSC cohort that have also been diagnosed with head and neck cancer.

Please note that the code has been generated and tested using R version 3.5.1.