Department of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, 410078, P. R. China.
Shenzhen Center for Chronic Disease Control, Shenzhen, 518020, P. R. China.
BMC Cancer. 2024 Nov 21;24(1):1435. doi: 10.1186/s12885-024-13173-x.
Exosome small RNAs are believed to be involved in the pathogenesis of cancer, but their role in breast cancer is still unclear. This study utilized machine learning models to screen for key exosome small RNAs and analyzed and validated them.
Peripheral blood samples from breast cancer screening positive and negative people were used for small RNA sequencing of plasma exosomes. The differences in the expression of small RNAs between the two groups were compared. We used machine learning algorithms to analyze small RNAs with significant differences between the two groups, fit the model through training sets, and optimize the model through testing sets. We recruited new research subjects as validation samples and used PCR-based quantitative detection to validate the key small RNAs screened by the machine learning model. Finally, target gene prediction and functional enrichment analysis were performed on these key RNAs.
The machine learning model incorporates six small RNAs: piR-36,340, piR-33,161, miR-484, miR-548ah-5p, miR-4282, and miR-6853-3p. The area under the ROC curve (AUC) of the machine learning model in the training set was 0.985 (95% CI = 0.948-1), while the AUC in the test set was 0.972 (95% CI = 0.882-0.995). RT-qPCR was used to detect the expression levels of these key small RNAs in the validation samples, and the results revealed that their expression levels were significantly different between the two groups (P < 0.05). Through target gene prediction and functional enrichment analysis, it was found that the functions of the target genes were enriched mainly in the chemokine signaling pathway.
The combination of six plasma exosome small RNAs has good prognostic value for women with positive breast cancer by imaging screening. The chemokine signaling pathway may be involved in the early stage of breast cancer. It is worth further exploring whether small RNAs mediate chemokine signaling pathways in the pathogenesis of breast cancer through the delivery of exosomes.
外泌体小分子 RNA 被认为参与了癌症的发病机制，但它们在乳腺癌中的作用仍不清楚。本研究利用机器学习模型筛选关键外泌体小分子 RNA，并对其进行分析和验证。
使用乳腺癌筛查阳性和阴性人群的外周血样本进行血浆外泌体小 RNA 测序。比较两组间小分子 RNA 的表达差异。我们使用机器学习算法分析两组间差异有统计学意义的小分子 RNA，通过训练集拟合模型，通过测试集优化模型。我们招募新的研究对象作为验证样本，并用基于 PCR 的定量检测对机器学习模型筛选出的关键小分子 RNA 进行验证。最后，对这些关键 RNA 进行靶基因预测和功能富集分析。
机器学习模型纳入了 6 个小分子 RNA：piR-36,340、piR-33,161、miR-484、miR-548ah-5p、miR-4282 和 miR-6853-3p。训练集机器学习模型的 ROC 曲线下面积（AUC）为 0.985（95%CI=0.948-1），测试集 AUC 为 0.972（95%CI=0.882-0.995）。用 RT-qPCR 检测验证样本中这些关键小分子 RNA 的表达水平，结果显示两组间表达水平差异有统计学意义（P<0.05）。通过靶基因预测和功能富集分析，发现靶基因的功能主要富集在趋化因子信号通路。
通过影像学筛查，六种血浆外泌体小分子 RNA 的组合对乳腺癌阳性女性具有良好的预后价值。趋化因子信号通路可能参与乳腺癌的早期阶段。值得进一步探索小分子 RNA 是否通过外泌体传递来调节乳腺癌发病机制中的趋化因子信号通路。
