海德堡大学Felix Sahm小组取得一项新突破。他们开发出微环境决定的风险连续体细化了脑膜瘤的亚型，揭示了基于机器学习的肿瘤分类的决定因素。相关论文于2026年2月9日发表于国际顶尖学术期刊《自然—遗传学》杂志上。

通过在多个独立数据集中应用多组学分析和多条正交计算评估线，研究团队发现肿瘤细胞特征和肿瘤微环境（TME）的增量变化对表观遗传脑膜瘤的分类和临床结果有影响。

除了揭示非肿瘤细胞在中枢神经系统甲基化分类中的决定性作用外，这还挑战了不同脑膜瘤亚群的模型，使其朝着TME决定的风险连续体发展。这细化了目前分子脑膜瘤亚型分型的争议。此外，该课题组将这些知识应用于设计和验证一种简单的诊断方法，以提高基于免疫组织化学的临床预测准确性，这也适用于耐药限制的环境。

据悉，目前神经肿瘤学中肿瘤的分类依赖于分子模式（主要是DNA甲基化）及其机器学习支持的解释。了解算法解释的过程对于安全应用于临床常规至关重要。这对于成人最常见的原发性颅内肿瘤脑膜瘤来说是典型的。

附：英文原文

Title: A microenvironment-determined risk continuum refines subtyping in meningioma and reveals determinants of machine learning-based tumor classification

Author: Maas, Sybren L. N., Tang, Yiheng, Stutheit-Zhao, Eric, Rahmanzade, Ramin, Blume, Christina, Hielscher, Thomas, Zettl, Ferdinand, Benfatto, Salvatore, Calafato, Domenico, Sill, Martin, Benotmane, Jasim Kada, Yabo, Yahaya A., Behling, Felix, Suwala, Abigail, Kardo, Helin, Ritter, Michael, Peyre, Matthieu, Sankowski, Roman, Okonechnikov, Konstantin, Sievers, Philipp, Patel, Areeba, Reuss, David, Friedrich, Mirco J., Stichel, Damian, Schrimpf, Daniel, Van den Bosch, Thierry P. P., Beck, Katja, Wirsching, Hans-Georg, Jungwirth, Gerhard, Hanemann, C. Oliver, Lamszus, Katrin, Etminan, Nima, Unterberg, Andreas, Mawrin, Christian, Remke, Marc, Ayrault, Olivier, Lichter, Peter, Reifenberger, Guido, Platten, Michael, Kacprowski, Tim, List, Markus, Pauling, Josch K., Baumbach, Jan, Milde, Till, Grossmann, Rachel, Ram, Zvi, Ratliff, Miriam, Mallm, Jan-Philipp, Neidert, Marian C., Bos, Eelke M., Prinz, Marco, Weller, Michael, Acker, Till, Hartmann, Felix J.

Issue&Volume: 2026-02-09

Abstract: Classification of tumors in neuro-oncology today relies on molecular patterns (mostly DNA methylation) and their machine learning-supported interpretation. Understanding the process of algorithmic interpretation is essential for safe application in clinical routine. This is paradigmatically true for the most common primary intracranial tumor in adults, meningioma. Here, by applying multiomic profiling and multiple lines of orthogonal computational evaluation in multiple independent datasets, we found that not only tumor cell characteristics but also incremental changes in the tumor microenvironment (TME) have impact on epigenetic meningioma classification and clinical outcome. Besides revealing the decisive role of non-neoplastic cells in the CNS methylation classifier, this challenges the model of distinct meningioma subgroups toward a TME-determined risk continuum. This refines current controversies in molecular meningioma subtyping. In addition, we apply these learnings to devise and validate a simple diagnostic approach for increased clinical prediction accuracy based on immunohistochemistry, which is also applicable in resource-limited settings.

DOI: 10.1038/s41588-025-02475-w

Source: https://www.nature.com/articles/s41588-025-02475-w