【摘要】 肿瘤亚型的准确判别对肿瘤的治疗具有重要意义。该文依据肿瘤的基因表达谱,研究了利用支持向量机进行肿瘤亚型识别的方法。该方法以基因蕴含的样本分类信息量为依据首先排除噪声基因,然后采用支持向量机作为分类器进行肿瘤亚型的识别。文章以急性白血病的基因表达谱数据为例,进行亚型识别并同已有的研究成果进行了对比。实验结果表明了该方法的可行性和有效性。更多还原

【Abstract】 Accurate prediction of different tumor subtypes has great value in providing better treatment.A method based on support vector machine is proposed using gene expression profiles.The ’noisy-genes’ which do not contribute to clas-sification is firstly removed in term of a measure defined in the paper,and then based on the expression values of in-formative genes,a support vector machine is used as the classifier to classify different tumor subtypes.This process has been applied to the human acute leukemia dataset as a test case.The effectiveness and feasibility of the method is proved by the results that all the samples can be correctly classified without any error.更多还原