基于胃癌基因组学的机器学习识别特征性甲基化位点  

Identification of characteristic methylation sites in gastric cancer using genomics-based machine learning

作　　者：王晓江[1] 刘伟 陈宝珍[1] 何银珠[1] 陈燕坪[2] 陈刚[2] Wang Xiaojiang;Liu Wei;Chen Baozhen;He Yinzhu;Chen Yanping;Chen Gang(Department of Molecular Pathology,Fujian Cancer Hospital,Fuzhou 350014,China;Department of Pathology,Fujian Cancer Hospital,Fuzhou 350014,China)

机构地区：[1]福建省肿瘤医院分子病理室,福州350014 [2]福建省肿瘤医院病理科,福州350014

出　　处：《中华病理学杂志》2021年第4期363-368,共6页Chinese Journal of Pathology

基　　金：福建省科技厅计划资助项目(2018Y2003,2019L3018,2019YZ016006);福建医科大学启航课题(2017XQ1212)。

摘　　要：目的基于基因组学的数据,通过机器学习,构建胃癌相关甲基化预测模型。方法下载TCGA(The Cancer Genome Atlas)数据库中胃癌基因突变数据、基因表达数据和甲基化芯片数据,进行特征选择,构建支持向量机(径向基核函数)、随机森林和误差反向传播(error back propagation,BP)神经网络模型,并在新的数据集中进行模型的验证。结果在3个模型中BP神经网络的检验效能最高(F1 值=0.89,Kappa=0.66,受试者工作特征曲线下面积=0.93)。结论 BP神经网络能够充分利用分子检测的基因组数据进行机器学习,可以用于胃癌相关甲基化预测。Objective To construct a prediction model of gastric cancer related methylation using machine learning algorithms based on genomic data.Methods The gene mutation data,gene expression data and methylation chip data of gastric cancer were downloaded from The Caner Genome Atlas database,feature selection was conducted,and support vector machine(radial basis function),random forest and error back propagation(BP)neural network models were constructed;the model was verified in the new data set.Results Among the three machine learning models,BP neural network had the highest test efficiency(F1 score=0.89,Kappa=0.66,area under curve=0.93).Conclusion Machine learning algorithms,particularly BP neural network,can be used to take advantages of the genomic data for discovering molecular markers,and to help identify characteristic methylation sites of gastric cancer.

关 键 词：胃肿瘤 人工智能 DNA甲基化 神经网络(计算机) 

分 类 号：R735.2[医药卫生—肿瘤]