Machine Learning–based New Classification for Immune Infiltration of Gliomas
Feng Yuan, Yingshuai Wang, Lei Yuan, Lei Ye, Yangchun Hu, Hongwei Cheng, Yan Li.
Abstract
Glioma is a highly heterogeneous and poorly immunogenic malignant tumor, with limited efficacy of immunotherapy. The characteristics of the immunosuppressive tumor microenvironment (TME) are one of the important factors hindering the effectiveness of immunotherapy. Therefore, this study aims to reveal the immune microenvironment (IME) characteristics of glioma and predict different immune subtypes using machine learning methods, providing guidance for immune therapy in glioma.
Introduction
Malignant primary brain tumors are still one of the refractory tumors in humans, its 5-year overall survival rate does not exceed 35%. Glioma is the most common primary central nervous system (CNS) tumor, accounting for about 27% of all CNS tumors and about 80% of intracranial malignant tumors. Among them, Glioblastoma (GBM) has the highest degree of malignancy and the worst prognosis. Although the patient received the standard treatment, that is, the maximum safe removal of the tumor, postoperative radiotherapy, concomitant chemotherapy with temozolomide (TMZ) and Tumor-treating fields (TTFields), the median overall survival is 20.9 months.
Materials and Methods:
Single sample gene set enrichment analysis (ssGSEA) normalizes the gene expression profile within a sample and then calculates the ssGSEA score for each gene set. In this way, ssGSEA transforms the gene expression profile of a single sample into a gene set enrichment score matrix.
Morpheus is a multifunctional matrix visualization and analysis software used for screening DEGs across different subtypes of glioma. A P-value of <0.01 and a False Discovery Rate (FDR) of <0.01 are considered critical thresholds.
Discussion
Glioma is the most common primary CNS malignancy, which is a fatal and poorly prognostic tumor. Immunotherapy has achieved unprecedented success in certain advanced cancer patients and has prolonged the lives of cancer patients. Malignant glioma is a malignant tumor with poor immunogenicity. So far, the latest immunotherapy has not made breakthrough progress in patients with glioma. Therefore, understanding the mechanism by which immunotherapy works or fails, and how to improve it to achieve the desired effect has become the focus of current research.
Citation: Yuan F, Wang Y, Yuan L, Ye L, Hu Y, Cheng H, et al. (2024) Machine learning–based new classification for immune infiltration of gliomas. PLoS ONE 19(10): e0312071. https://doi.org/10.1371/journal.pone.0312071
Editor: Michael C. Burger, Goethe University Hospital Frankfurt, GERMANY
Received: June 3, 2024; Accepted: September 30, 2024; Published: October 25, 2024.
Copyright: © 2024 Yuan et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: All relevant data are within the paper and its Supporting Information files.
Funding: This paper is funded by Anhui provincial key clinical specialties of the 14th Five-Year Plan (2021-25), and Natural Science Research Project of Colleges and Universities in Anhui Province (No. KJ2021A0293), and Research Funding for Doctoral Talent in 2024 – Feng Yuan (1931). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Competing interests: The authors have declared that no competing interests exist.
