Razaghi-Moghadam Zahra, Abdollahi Razieh, Goliaei Sama, Ebrahimi Morteza
Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran; School of Biological Sciences, Institute for Research in Foundation Sciences (IPM), Tehran, Iran.
Faculty of New Sciences and Technologies, University of Tehran, Tehran, Iran.
J Biomed Inform. 2016 Dec;64:139-146. doi: 10.1016/j.jbi.2016.10.003. Epub 2016 Oct 8.
In the past few years, many researches have been conducted on identifying and prioritizing disease-related genes with the goal of achieving significant improvements in treatment and drug discovery. Both experimental and computational approaches have been exploited in recent studies to explore disease-susceptible genes. The experimental methods for identification of these genes are usually time-consuming and expensive. As a result, a substantial number of these studies have shown interest in utilizing computational techniques, commonly known as gene prioritization methods. From a conceptual point of view, these methods combine various sources of information about a particular disease of interest and then use it to discover and prioritize candidate disease genes. In this paper, we propose a gene prioritization method (HybridRanker), which exploits network topological features, as well as several biomedical data sources to identify candidate disease genes. In this approach, the genes are characterized using both local and global features of a protein-protein interaction (PPI) network. Furthermore, to obtain improved results for a particular disease of interest, HybridRanker incorporates data from diseases with similar symptoms and also from its comorbid diseases. We applied this new approach to identify and prioritize candidate disease genes of colorectal cancer (CRC) and the efficiency of HybridRanker was confirmed by leave-one-out cross-validation test. Moreover, in comparison with several well-known prioritization methods, HybridRanker shows higher performance in terms of different criteria.
在过去几年中，为了在治疗和药物研发方面取得显著进展，人们开展了许多关于识别与疾病相关基因并确定其优先级的研究。近期的研究中，实验方法和计算方法都被用于探索疾病易感基因。识别这些基因的实验方法通常既耗时又昂贵。因此，大量此类研究对利用计算技术（通常称为基因优先级排序方法）表现出兴趣。从概念上讲，这些方法整合了关于特定目标疾病的各种信息源，然后利用这些信息来发现候选疾病基因并确定其优先级。在本文中，我们提出了一种基因优先级排序方法（HybridRanker），该方法利用网络拓扑特征以及多个生物医学数据源来识别候选疾病基因。在这种方法中，基因通过蛋白质 - 蛋白质相互作用（PPI）网络的局部和全局特征来表征。此外，为了针对特定目标疾病获得更好的结果，HybridRanker纳入了来自具有相似症状疾病及其共病的数据。我们应用这种新方法来识别和确定结直肠癌（CRC）候选疾病基因的优先级，留一法交叉验证测试证实了HybridRanker的有效性。此外，与几种知名的优先级排序方法相比，HybridRanker在不同标准下表现出更高的性能。
