Zhang Shihua, Zhang Cheng, Du Jinke, Zhang Rui, Yang Shixiong, Li Bo, Wang Pingping, Deng Wensheng
College of Life Science and Health, Wuhan University of Science and Technology, Wuhan, China.
State Key Laboratory of Tea Plant Biology and Utilization, Anhui Agricultural University, Hefei, China.
Front Cell Dev Biol. 2021 Feb 11;9:605977. doi: 10.3389/fcell.2021.605977. eCollection 2021.
Accurate prediction of lymph-node metastasis in cancers is pivotal for the next targeted clinical interventions that allow favorable prognosis for patients. Different molecular profiles (mRNA and non-coding RNAs) have been widely used to establish classifiers for cancer prediction (e.g., tumor origin, cancerous or non-cancerous state, cancer subtype). However, few studies focus on lymphatic metastasis evaluation using these profiles, and the performance of classifiers based on different profiles has also not been compared. Here, differentially expressed mRNAs, miRNAs, and lncRNAs between lymph-node metastatic and non-metastatic groups were identified as molecular signatures to construct classifiers for lymphatic metastasis prediction in different cancers. With this similar feature selection strategy, support vector machine (SVM) classifiers based on different profiles were systematically compared in their prediction performance. For representative cancers (a total of nine types), these classifiers achieved comparative overall accuracies of 81.00% (67.96-92.19%), 81.97% (70.83-95.24%), and 80.78% (69.61-90.00%) on independent mRNA, miRNA, and lncRNA datasets, with a small set of biomarkers (6, 12, and 4 on average). Therefore, our proposed feature selection strategies are economical and efficient to identify biomarkers that aid in developing competitive classifiers for predicting lymph-node metastasis in cancers. A user-friendly webserver was also deployed to help researchers in metastasis risk determination by submitting their expression profiles of different origins.
准确预测癌症中的淋巴结转移对于接下来能为患者带来良好预后的靶向临床干预至关重要。不同的分子谱（mRNA和非编码RNA）已被广泛用于建立癌症预测的分类器（例如，肿瘤起源、癌性或非癌性状态、癌症亚型）。然而，很少有研究关注使用这些谱来评估淋巴转移，并且基于不同谱的分类器的性能也尚未进行比较。在此，将淋巴结转移组和非转移组之间差异表达的mRNA、miRNA和lncRNA鉴定为分子特征，以构建不同癌症中淋巴转移预测的分类器。采用这种相似的特征选择策略，系统地比较了基于不同谱的支持向量机（SVM）分类器的预测性能。对于代表性癌症（共九种类型），这些分类器在独立的mRNA、miRNA和lncRNA数据集上分别实现了81.00%（67.96 - 92.19%）、81.97%（70.83 - 95.24%）和80.78%（69.61 - 90.00%）的相对总体准确率，且生物标志物数量较少（平均分别为6个、12个和4个）。因此，我们提出的特征选择策略经济高效，能够识别有助于开发用于预测癌症淋巴结转移的竞争性分类器的生物标志物。还部署了一个用户友好的网络服务器，通过提交不同来源的表达谱来帮助研究人员确定转移风险。
