多发性骨髓瘤基因表达谱分析

被引:2
作者
李颖新
刘全金
阮晓钢
机构
[1] 北京工业大学电子信息与控制工程学院
[2] 安庆师范学院物理系
[3] 北京工业大学电子信息与控制工程学院 北京
[4] 安徽 安庆
[5] 北京
关键词
神经网络; 决策树; 基因表达谱;
D O I
暂无
中图分类号
R733.3 [骨髓肿瘤];
学科分类号
100214 ;
摘要
为了依据肿瘤基因表达谱数据提取出其中蕴含的样本分类规则,以多发性骨髓瘤的基因表达谱为例,提出了一种在基因表达数据中提取分类特征规则的方法.该方法从统计学角度出发,以基因与样本类别问的相关系数作为衡量属性包含样本分类信息量的标准,并利用神经网络进行属性规约找出分类特征属性集,最后利用决策树进行知识提取,给出样本分类的产生式规则.实验结果表明,所提取出的3条规则对实验样本正确分类率达到100%.
引用
收藏
页码:286 / 289
页数:4
相关论文
共 34 条
[1]  
Multiclass cancer diagnosis using tumor gene expression signatures. Ramaswamy S, Tamayo P, Rifkin R, et al. Proceedings of the National Academy of Sciences of the United States of America . 2001
[2]  
Molecular classification of cutaneous malignant melanoma by gene expression profiling. Bittner M,Meltzer P,Chen Y,et al. Nature . 2000
[3]  
Molecular portraits of human breast tumours. Perou CM,Sorlie T,Eisen MB,et al. Nature . 2000
[4]  
Distinct types of diffuse large B-cell lymphoma identified by gene expression profiling. Aizadeh AA, Eisen MB, Davis RE, et al. Nature . 2000
[5]  
Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks. Khan J,Wei JS,Ringner M,et al. Nature Medicine . 2001
[6]  
Gene Expression Profile of Multiple Myeloma. Lambert Lab of Myeloma Genetics. http: //lambertlab.uams.edu/publicdata.htm . 2001
[7]  
Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring. Colub TR,Slonim DK,Tamayo P,et al. Science . 1999
[8]  
Genomics: Journey to the center of biology. Lander E S, Weinberg R A. Science . 2000
[9]  
V-region-specific alterations of serum IgM production in multiple myeloma of IgG class. SUNDBLAD A,COUTINHO A,BJORKHOLM M,et al. The Hematology Journal . 2000
[10]  
DNA MicroArrays in Clinical Oncology. Ramaswamy S, Golub T R. Journal of Clinical Oncology . 2002