KATZMDA: Prediction of miRNA-Disease Associations Based on KATZ Model
KATZMDA: Prediction of miRNA-Disease Associations Based on KATZ Model
复制标题
KATZMDA：基于 KATZ 模型预测 miRNA 与疾病的关联
DOI：
10.1109/access.2017.2754409
复制
发表时间：
2018-01-01
期刊：
影响因子：
3.9
通讯作者：
Dong, Xiao
中科院分区：
文献类型：
--
作者：
Qu, Yu;Zhang, Huaxiang;Dong, Xiao
miRNAs是一类存在于植物、动物和各种病毒中的非编码RNA分子。它们已被证明在多种生物和生理过程中发挥重要作用。特别是越来越多的研究表明，miRNAs与许多疾病有着密切的关系，因此探索miRNAs与疾病的关系对疾病研究具有重要意义。虽然传统的实验方法可以获得miRNAs与疾病之间的关联，但所获得的数据量远远不足以让我们全面了解它们之间的关联。此外，传统的实验通常耗时且昂贵。因此，有必要提出有效的计算方法来预测miRNA与疾病的关联。在本文中，我们开发了一种新的计算方法的基础上KATZ模型预测miRNA-疾病协会（KATZMDA）通过集成多个数据源。为了评估KATZMDA的性能，我们使用了四种经典的方法（WBSMDA，HGIMDA，RKNNMDA，MCMDA）与我们的方法进行了比较。实验结果表明，我们的方法可以作为一种有效的工具来识别疾病相关的miRNA。此外，三种常见疾病的案例研究进一步验证了我们的方法的实用性。
MiRNAs are a kind of non-coding RNA molecules found in plants, animals, and various viruses. They have been proved to play an important role in multiple biological as well as physiological processes. Specifically, a growing number of studies have shown that miRNAs have close relationships with many diseases, and thus the exploration of the relationships between miRNAs and diseases is of great significance in disease research. Although traditional experimental methods can obtain the associations between miRNAs and diseases, the amount of data obtained is far from enough for us to fully understand the associations between them. Besides, traditional experiments are generally time-consuming and expensive. Therefore, it is necessary to propose efficient computational methods to predict miRNA-disease associations. In this paper, we develop a novel computational method based on KATZ model to predict MiRNA-Disease Associations (KATZMDA) by integrating multiple data sources. To evaluate the performance of KATZMDA, four classical methods are used to compare with our methods (WBSMDA, HGIMDA, RKNNMDA, MCMDA). The experimental results demonstrate that our method can be used as an effective tool to identify disease-related miRNAs. In addition, case studies of three common diseases further verify the utility of our method.