A New Epigenetic Model to Stratify Glioma Patients According to Their Immunosuppressive State

• Main Authors: Maurizio Polano, Emanuele Fabbiani, Eva Adreuzzi, Federica Di Cintio, Luca Bedon, Davide Gentilini, Maurizio Mongiat, Tamara Ius, Mauro Arcicasa, Miran Skrap, Michele Dal Bo, Giuseppe Toffoli
• Format: Article
• Language: English
• Published: MDPI AG 2021-03-01
• Series: Cells
• Subjects: immunosuppression; tumor microenviroment; neural network; genome-wide methylation model; glioma; extracellular matrix
• Online Access: https://www.mdpi.com/2073-4409/10/3/576

Gliomas are the most common primary neoplasm of the central nervous system. A promising frontier in the definition of glioma prognosis and treatment is represented by epigenetics. Furthermore, in this study, we developed a machine learning classification model based on epigenetic data (CpG probes) to separate patients according to their state of immunosuppression. We considered 573 cases of low-grade glioma (LGG) and glioblastoma (GBM) from The Cancer Genome Atlas (TCGA). First, from gene expression data, we derived a novel binary indicator to flag patients with a favorable immune state. Then, based on previous studies, we selected the genes related to the immune state of tumor microenvironment. After, we improved the selection with a data-driven procedure, based on Boruta. Finally, we tuned, trained, and evaluated both random forest and neural network classifiers on the resulting dataset. We found that a multi-layer perceptron network fed by the 338 probes selected by applying both expert choice and Boruta results in the best performance, achieving an out-of-sample accuracy of 82.8%, a Matthews correlation coefficient of 0.657, and an area under the ROC curve of 0.9. Based on the proposed model, we provided a method to stratify glioma patients according to their epigenomic state.