基于转录组数据不平衡数据的乳腺癌分类预测模型  

Breast Cancer Classification Prediction Model Based on Unbalanced Transcriptome Data

作　　者：刘梓剑 LIU Zi-jian(College of Computer Science,Sichuan University,Chengdu 610065)

机构地区：[1]四川大学计算机学院,成都610065

出　　处：《现代计算机》2020年第10期81-84,共4页Modern Computer

摘　　要：乳腺癌是癌症中较为常见的一种,拥有很高的死亡率。乳腺癌早期的诊断对于治疗有着至关重要的意义,现代医学对于乳腺癌的通常使用医学影像,病理分析等方法进行初期的诊断。随着新一代的测序技术的发展,基因与转录组数据的获得越来越容易。基因转录组数据结合机器学习算法的运用,可以快速、准确地检测出癌症患病风险。提出一种基于基因转录组的特征选择与分类预测的算法,所提出的算法在The Cancer Genome Atlas(TCGA)中的乳腺癌数据集中进行验证,实验结果能够精确地预测分类信息。Breast cancer is the most common form of cancer and has a high mortality rate.Early diagnosis of breast cancer is of vital significance for treatment.Modern medicine usually USES medical imaging,pathological analysis and other methods for early diagnosis of breast cancer.With the development of a new generation of sequencing technology,gene and transcriptome data are more and more easily obtained.Gene transcriptome data combined with machine learning algorithms can quickly and accurately detect cancer risk.Presents an algorithm for fea ture selection and classification prediction based on gene transcriptome.The proposed algorithm was validated in The Cancer Genome At las(TCGA)breast Cancer dataset,and the experimental results could accurately predict The classification information.

关 键 词：癌症分类 癌症基因组图谱(TCGA) 深度森林 

分 类 号：R737.9[医药卫生—肿瘤] TP18[医药卫生—临床医学]