Li Huilin, Li Musu, Sun Yue, Yu Er, Pan Jiahe, Wu Yiwen, Lu Zixuan, Wo Hongmei, Shao Fang, You Dongfang, Tang Shaowen, Zhao Yang, Dai Juncheng, Yi Honggang
Department of Biostatistics, National Vaccine Innovation Platform, School of Public Health, Nanjing Medical University, Nanjing, 211166, China.
Department of Social Security, School of Health Police and Management, Nanjing Medical University, Nanjing, 211166, China.
J Mol Neurosci. 2025 Aug 27;75(3):110. doi: 10.1007/s12031-025-02393-w.
Low-grade gliomas (LGGs) represent a complex and aggressive category of brain tumors. Despite recent advancements in molecular subtyping and characterization, the necessity to identify additional molecular subtypes and biomarkers remains. To delineate survival subtypes in LGG, we propose a deep learning (DL)-based multi-omics SurvivalNet (MOST) model. By integrating histological RNA-seq, miRNA-seq, and DNA methylation data obtained from The Cancer Genome Atlas (TCGA), we applied the MOST model to analyze data from 497 LGG patients. We employed consensus clustering to reveal heterogeneous subtypes, validated our findings using an internal validation set through a supervised classification algorithm, and further evaluated the robustness of our model in an independent external cohort. The DL-based MOST model identified two optimal patient subtypes with significant differences in survival (P = 3.07E - 16) and demonstrated a robust model fit (C = 0.92 ± 0.02). This multi-omics model was validated using external Chinese Glioma Genome Atlas (CCGA) datasets, including RNA-Seq (N = 497, C = 0.85), miRNA array (N = 89, C = 0.80), and DNA methylation (N = 89, C = 0.61). High-risk subcategories exhibited increased expression of the homeobox (HOX) family genes, regulation of cholesterol homeostasis, glycolysis, epithelial-mesenchymal transition pathway enrichment, and a high density of M2 macrophages. Our study utilized deep learning to identify multi-omics features associated with differential survival outcomes in patients with LGG. This work is anticipated to significantly enhance prognosis prediction for LGG due to its robustness within the cohorts.
低级别胶质瘤（LGGs）是一类复杂且侵袭性的脑肿瘤。尽管在分子亚型分类和特征描述方面取得了最新进展，但仍有必要识别更多的分子亚型和生物标志物。为了描绘LGG中的生存亚型，我们提出了一种基于深度学习（DL）的多组学生存网络（MOST）模型。通过整合从癌症基因组图谱（TCGA）获得的组织学RNA测序、miRNA测序和DNA甲基化数据我们将MOST模型应用于分析497例LGG患者的数据。我们采用一致性聚类来揭示异质性亚型，通过监督分类算法使用内部验证集验证我们的发现，并在独立的外部队列中进一步评估我们模型的稳健性。基于DL的MOST模型识别出两种生存情况有显著差异的最佳患者亚型（P = 3.07E - 16），并显示出稳健的模型拟合度（C = 0.92 ± 0.02）。这个多组学模型使用外部中国胶质瘤基因组图谱（CCGA）数据集进行了验证，包括RNA测序（N = 497，C = 0.85）、miRNA阵列（N = 89，C = 0.80）和DNA甲基化（N = 89，C = 0.61）。高风险亚类表现出同源框（HOX）家族基因表达增加、胆固醇稳态调节、糖酵解、上皮-间质转化途径富集以及M2巨噬细胞高密度。我们的研究利用深度学习来识别与LGG患者不同生存结果相关的多组学特征。由于该模型在各队列中的稳健性，预计这项工作将显著提高LGG的预后预测。
