【工具】MNMO从基于多组学数据的多层网络中发现驱动基因-CSDN博客

本文链接：https://blog.csdn.net/H20230717/article/details/147711906

在这里插入图片描述

文章目录

介绍

癌症作为一个公共卫生问题，是由“癌症驱动基因”中的基因组变异所引发的。驱动基因的识别对于关键生物标志物的发现以及个性化治疗的发展至关重要。
我们提出了一种预测方法 MNMO：一种基于多组学数据的多层网络模型。MNMO 首先构建了一个由 miRNA（微小 RNA）和三种具有不同特征的基因组成的动态调整的四层网络。然后，设计并计算了三种分数，即控制能力、突变分数和网络分数，通过调和平均值生成综合基因分数。我们在三种真实癌症数据上进行了实验，以比较 MNMO 方法与其他六种最先进的方法的识别性能。结果表明，在大多数情况下，MNMO 方法的识别性能最佳。MNMO 方法优先选择的基因不仅比其他方法识别的基因与基准基因有更好的匹配度，而且都与癌症的发展和进展有关。此外，MNMO 方法的一些扩展版本在某些特定数据集的大多数评估指标上都能进一步取得更好的性能。这些方法可能更有利于识别组织特异性基因，这一点已通过多项实验得到验证。

Cancer as a public health problem is driven by genomic variations in “cancer driver” genes. The identification of driver genes is critical for the discovery of key biomarkers and the development of personalized therapy.

We propose a prediction method MNMO: a multi-layer network model based on multi-omics data. MNMO firstly constructs a dynamically adjusted four-layer network composed of miRNAs and three kinds of genes with different features. Then three kinds of scores, i.e. control capacity, mutation score, and network score, are devised and calculated by harmonic mean to produce the integrated gene score. Experiments were performed on three kinds of real cancer data to compare the identification performance of method MNMO with that of six state-of-the-art ones. The results indicate that method MNMO presents the best identification performance under most circumstances. The genes prioritized by method MNMO not only have a better match to the benchmark ones than those identified by the other methods, but also are all associated with the development and progression of cancers. In addition, some extended versions of method MNMO can further achieve better performance on most evaluation metrics for some specific datasets. They may be more conducive to identifying tissue-specific genes, which has been verified through a number of experiments.