Peng Jianming, Zhang Qing, Zhu Xiaofeng, Yan Zhu, Zhu Meng
School of Medicine, Yangzhou Polytechnic College, Yangzhou, China.
Department of Hepatology, Huai'an No.4 People's Hospital, Huai'an, China.
Discov Oncol. 2024 Sep 14;15(1):445. doi: 10.1007/s12672-024-01302-8.
Lower-grade gliomas (LGGs), despite their generally indolent clinical course, are characterized by invasive growth patterns and genetic heterogeneity, which can lead to malignant transformation, underscoring the need for improved prognostic markers and therapeutic strategies. This study utilized single-cell RNA sequencing (scRNA-seq) and bulk RNA-seq to identify a novel cell type, referred to as "Prol," characterized by increased proliferation and linked to a poor prognosis in patients with LGG, particularly under the context of immunotherapy interventions. A signature, termed the Prol signature, was constructed based on marker genes specific to the Prol cell type, utilizing an artificial intelligence (AI) network that integrates traditional regression, machine learning, and deep learning algorithms. This signature demonstrated enhanced predictive accuracy for LGG prognosis compared to existing models and showed pan-cancer prognostic potential. The mRNA expression of the key gene PTTG1 from the Prol signature was further validated through quantitative reverse transcription polymerase chain reaction (qRT-PCR). Our findings not only provide novel insights into the molecular and cellular mechanisms of LGG but also offer a promising avenue for the development of targeted biomarkers and therapeutic interventions.
低级别胶质瘤（LGGs）尽管其临床病程通常较为惰性，但其特点是具有侵袭性生长模式和基因异质性，这可能导致恶性转化，凸显了对改进预后标志物和治疗策略的需求。本研究利用单细胞RNA测序（scRNA-seq）和批量RNA测序来鉴定一种新型细胞类型，称为“Prol”，其特征是增殖增加，并与LGG患者的不良预后相关，特别是在免疫治疗干预的背景下。基于Prol细胞类型特有的标记基因构建了一个名为Prol特征的标志物，利用了一个整合传统回归、机器学习和深度学习算法的人工智能（AI）网络。与现有模型相比，该标志物对LGG预后的预测准确性更高，并显示出泛癌预后潜力。通过定量逆转录聚合酶链反应（qRT-PCR）进一步验证了来自Prol特征的关键基因PTTG1的mRNA表达。我们的研究结果不仅为LGG的分子和细胞机制提供了新的见解，也为开发靶向生物标志物和治疗干预措施提供了一条有前景的途径。
