决策树分类器在分析基因微阵列数据中的应用  

Application of decision tree classifier to analysis of gene microarray data

作　　者：项婧[1] 任劼[1] 

机构地区：[1]华北计算技术研究所,北京100083

出　　处：《计算机工程与设计》2006年第15期2905-2908,共4页Computer Engineering and Design

摘　　要：近年来,需要深入研究癌症细胞的基因表达技术正在不断增多。机器学习算法已经被广泛用于当今世界的许多领域,但是却很少应用于生物信息领域。系统研究了决策树的生成、修剪的原理和算法以及其它与决策树相关的问题;并且根据CAMDA2000(criticalassessmentofmicroarraydataanalysis)提供的急性淋巴白血病(ALL)和急性骨髓白血病(AML)数据集,设计并实现了一个基于ID3算法的决策树分类器,并利用后剪枝算法简化决策树。最后通过实验验证算法的有效性,实验结果表明利用该决策树分类器对白血病微阵列实验数据进行判别分析,分类准确率很高,证明了决策树算法在医学数据挖掘领域有着广泛的应用前景。In the last years, there has been a large growth in gene expression profiling technologies, which are expected to provide insight into cancer related cellular processes. Machine Learning algorithms, which are extensively applied in many areas of the real world, are not still popular in the bioinformatics community. The principle and algorithm of the foundation, pruning of the decision tree classifier and also other relative aspects of the decision tree are studied. A decision tree classifier is designed and actualized based on the data provided with CAMDA2000 （critical assessment ofmieroarray data analysis）, then the decision tree is pruned. The results of the classify show that the decision tree classifier has high correctness of classify, therefore manifest the decision tree algorithm have a extensive applied prospect in the field of medicinal data mining.

关 键 词：机器学习 决策树 剪枝算法 微阵列数据分析 数据挖掘 知识发现 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]