Predicting biomarkers from classifier for liver metastasis of colorectal adenocarcinomas using machine learning models
Predicting biomarkers from classifier for liver metastasis of colorectal adenocarcinomas using machine learning models
复制标题
DOI：
10.1002/cam4.3289
复制
发表时间：
2020-07-24
期刊：
影响因子：
4
通讯作者：
Wei W
中科院分区：
文献类型：
--
作者：
Shuwen H;Xi Y;Qing Z;Jing Z;Wei W
肝转移的早期诊断对于提高结直肠腺癌（CAD）患者的生存率具有重要意义，并且在分类器模型中联合使用单个生物标志物在预测几种类型癌症的转移方面显示出极大的改善。然而，这是很少报道的CAD。因此，本研究的目的是筛选一个最佳的CAD肝转移的分类器模型，并探讨应用该分类器模型时的基因转移机制。从Moffitt癌症中心（MCC）数据集GSE 131418中筛选原发性CAD样品和CAD伴转移样品之间的差异表达基因。采用MCC数据集GSE 131418，比较LR、RF、SVM、GBDT、NN和CatBoost等6种算法对CAD合并肝转移样本的分类性能。此外，GSE 131418和GSE 81558的联盟数据集被用作内部和外部验证集，以筛选最优方法。随后，进行了应用最佳方法时特征基因的功能分析和药物靶向网络构建。筛选出最优的CatBoost模型，其最高准确率为99%，曲线下面积为1，该模型由33个特征基因组成。功能分析表明，特征基因与“类固醇代谢过程”和“脂蛋白颗粒受体结合”（如APOB和APOC 3）密切相关。此外，特征基因在“补体和凝血级联”途径（例如FGA、F2和F9）中显著富集。在药物-靶标相互作用网络中，F2和F9被预测为甲萘醌的靶标。使用33个特征基因构建的CatBoost模型显示出识别CAD与肝转移的最佳分类性能。APOB、APOC 3、FGA、F2、F9和NKX 2 - 3是CAD伴肝转移分类的潜在生物标志物。甲萘醌可能通过在F2和F9位点发挥作用，成为一种很有前途的CAD细胞抗转移药物。由33个特征基因构建的CatBoost模型对于识别CAD肝转移显示出最佳的分类性能。
Early diagnosis of liver metastasis is of great importance for enhancing the survival of colorectal adenocarcinoma (CAD) patients, and the combined use of a single biomarker in a classier model has shown great improvement in predicting the metastasis of several types of cancers. However, it is little reported for CAD. This study therefore aimed to screen an optimal classier model of CAD with liver metastasis and explore the metastatic mechanisms of genes when applying this classier model. The differentially expressed genes between primary CAD samples and CAD with metastasis samples were screened from the Moffitt Cancer Center (MCC) dataset GSE131418. The classification performances of six selected algorithms, namely, LR, RF, SVM, GBDT, NN, and CatBoost, for classification of CAD with liver metastasis samples were compared using the MCC dataset GSE131418 by detecting their classification test accuracy. In addition, the consortium datasets of GSE131418 and GSE81558 were used as internal and external validation sets to screen the optimal method. Subsequently, functional analyses and a drug‐targeted network construction of the feature genes when applying the optimal method were conducted. The optimal CatBoost model with the highest accuracy of 99%, and an area under the curve of 1, was screened, which consisted of 33 feature genes. A functional analysis showed that the feature genes were closely associated with a “steroid metabolic process” and “lipoprotein particle receptor binding” (eg APOB and APOC3). In addition, the feature genes were significantly enriched in the “complement and coagulation cascade” pathways (eg FGA, F2, and F9). In a drug‐target interaction network, F2 and F9 were predicted as targets of menadione. The CatBoost model constructed using 33 feature genes showed the optimal classification performance for identifying CAD with liver metastasis. APOB, APOC3, FGA, F2, F9, and NKX2‐3 were potential biomarkers for classification of CAD with liver metastasis. Menadione might be a promising anti‐metastatic drug of CAD cells through functioning its role at sites of F2 and F9. CatBoost model constructed by 33 feature genes showed the optimal classification performance for identifying CAD liver metastasis.
登录
查看更多内容
影响因子：
14.9
作者：
The Gene Ontology Consortium
通讯作者：
The Gene Ontology Consortium
影响因子：
4.8
作者：
Freedman, SJ;Blostein, MD;Furie, B
通讯作者：
Furie, B
影响因子：
16.2
作者：
Feng, Rui-Mei;Zong, Yi-Nan;Xu, Rui-Hua
通讯作者：
Xu, Rui-Hua
影响因子：
7.1
作者：
Chandler, Paulette D.;Song, Yiqing;Wang, Lu
通讯作者：
Wang, Lu
影响因子：
3.9
作者：
Chinnaraj M;Planer W;Pozzi N
通讯作者：
Pozzi N