上海科技大学知识管理系统

本发明涉及的是一种肿瘤基因组拷贝数变异特征模式识别方法及其应用，属于基因诊断技术领域。本发明对肿瘤基因组拷贝数变异的特征进行了系统的分类，具体提取了8类肿瘤基因组拷贝数变异特征的80个数值，利用非负矩阵分解算法抽取肿瘤样本的拷贝数变异特征模式，然后依据拷贝数变异特征模式对肿瘤进行分型，从而能够实现对肿瘤临床预后的精准预测。

The invention relates to a tumor genome copy number variation characteristic pattern recognition method and application thereof, and belongs to the technical field of gene diagnosis. To the method, 8 values of 80 types of tumor genome copy number variation characteristics are extracted, the copy number variation characteristic mode of tumor samples is extracted by a non-negative matrix decomposition algorithm, and the tumor is typed according to the copy number variation characteristic mode, so that accurate prediction of tumor clinical prognosis can be realized.