采用基于Gene Ontology的聚类方法研究白血病的遗传异质性

采用基因表达谱可以研究基因功能模块与疾病异质性之间的关系.根据两套白血病基因表达谱数据,将富集高变异基因的Gene Ontology基因功能模块作为特征功能模块,将疾病样本聚为两类.通过对比原始多类标签,采用聚类评估指标来分析两类化聚类结果的效果,并探讨特征功能模块与疾病异质性之间的关系.实验结果显示:在两套不同的白血病基因表达谱数据中得到的特征功能模块类似,它们对白血病亚型有较强的分型能力.

Using Gene Ontology-based clustering method to study the genetic heterogeneity of leukemia

Gene expression profile data can be used to study the relationship between gene functional modules and disease genetic heterngeneity. Based on two leukemia datasets, the functional modules enriched with genes of high variations in expression level across disease samples were selected and used for the following clustering analysis, grouping the samples into two types. The clustering ability of every feature functional module was analyzed using clustering validation index, and the relationship between functional modules and disease heterogeneity was analyzed. The results showed that the feature functional modules selected from two different data sets were consistent and they were relevant to leukemia sub-typing.