A feature ensemble technology to identify molecular mechanisms for distinction between multiple subtypes of lymphoma  

作　　者：Yueying Yang Haiyun Wang Xia Li Xue Xiao Su Fei Chuanxing Li Hongzhi Wang Shaoqi Rao Yadong Wang 

机构地区：[1]College of Bioinformatics Science and Technology, Bio-pharmaceutical Key Laboratory of Heilongjiang Province and State Harbin Medical University, Harbin 150081, China [2]College of Life Science and Technology, Tongii University, Shanghai 200092, China [3]The Biomedical Engineering Institute, Capital Medical University, Beijing 100054, China [4]Department of Computer Science, Harbin Institute of Technology, Harbin 150080, China [5]Department of Molecular Cardiology, Cleveland Clinic Foundation, Cleveland, OH 44195, USA

出　　处：《Progress in Natural Science:Materials International》2008年第12期1491-1500,共10页自然科学进展·国际材料（英文版）

基　　金：supported in part by the National High Tech Development Project of China (Grant No.2007AA02Z329);the National Natural Science Foundation of China (Grant Nos.30571034,30570424 and 20060213024);the grant for Outstanding Overseas Scientist,Department of Education,Heilongjiang Province (Grant No.1055HG009);Natural Science Foundation of Heilongjiang Province (Grant Nos.ZJG0501,GB03C602-4 and F2004-02);Health Department of Heilongjiang Province Key Project (2005-39)

摘　　要：Due to complexities and genetic heterogeneities of biological phenotypes, robust computational approaches are desirable to achieve high generalization performance with multiple classifiers, perturbations of the data structures, and biological interpretations. The purpose of this study is to extend our developed ensemble decision approach to distinguish multiple heterogeneous phenotypes and to elucidate the underlying molecular bridges that intertwine the subtypes. Our work identifies the significant molecular mechanisms （disease-relevant genes and functions） that underpin the complex molecular mechanisms for distinction between multiple phenotypes. Feature genes and hierarchical gene cores identified by our method have achieved high accuracy in the classification of multiple phenotypes. The results show that the proposed analysis strategy is feasible and powerful in the classification of biological subtypes and in the explanation of the molecular connections between clinical phenotypes. Biological interpretations with Gene Ontology revealed concerted genetic pathways for some lymphoma subtypes.由于复杂性和生物显型的基因异质，柔韧的计算途径是合乎需要的与多重分类器，数据结构的不安，和生物解释完成高归纳性能。这研究的目的是扩大我们的发达整体决定途径区分多重异构的显型并且阐明缠绕子类型的内在的分子的桥。我们的工作识别支撑的重要分子的机制(疾病相关的基因和功能) 为在多重显型之间的区别的复杂分子的机制。特征基因和我们的方法识别的层次基因核心在多重显型的分类完成了高精确性。结果证明建议分析策略在生物子类型的分类并且在在临床的显型之间的分子的连接的解释可行、强大。有基因本体论的生物解释为一些淋巴瘤子类型揭示了一致基因小径。

关 键 词：Ensemble decision approach Molecular mechanisms LYMPHOMA MICROARRAY 

分 类 号：R733.4[医药卫生—肿瘤]