位置:成果数据库 > 期刊 > 期刊详情页
Community Detection in Disease-Gene Network Based on Principal Component Analysis
  • 期刊名称:Tsinghua Science and Technology
  • 时间:2013.10.10
  • 页码:454-461
  • 分类:TP11[自动化与计算机技术—控制科学与工程;自动化与计算机技术—控制理论与控制工程] O212.4[理学—概率论与数理统计;理学—数学]
  • 作者机构:[1]Department of Computer Science, Information Science and Technology College, Yangzhou University, Yangzhou 225127, China.
  • 相关基金:Acknowledgements This research was supported in part by the Natural Science Foundation of Education Department of Jiangsu Province (No. 12KJB520019), the National Science Foundation of Jiangsu Province (No. BK20130452), Science and Technology Innovation Foundation of Yangzhou University (No. 2012CXJ026), the National Natural Science Foundation of China (Nos. 61070047, 61070133, and 61003180) and the National Key Basic Research and Development (973) Program of China (No. 2012CB316003).
  • 相关项目:蚁群优化算法的搜索偏离性研究
中文摘要:

The identification of communities is imperative in the understanding of network structures and functions.Using community detection algorithms in biological networks, the community structure of biological networks can be determined, which is helpful in analyzing the topological structures and predicting the behaviors of biological networks. In this paper, we analyze the diseasome network using a new method called disease-gene network detecting algorithm based on principal component analysis, which can be used to investigate the connection between nodes within the same group. Experimental results on real-world networks have demonstrated that our algorithm is more efficient in detecting community structures when compared with other well-known results.

英文摘要:

The identification of communities is imperative in the understanding of network structures and functions.Using community detection algorithms in biological networks, the community structure of biological networks can be determined, which is helpful in analyzing the topological structures and predicting the behaviors of biological networks. In this paper, we analyze the diseasome network using a new method called disease-gene network detecting algorithm based on principal component analysis, which can be used to investigate the connection between nodes within the same group. Experimental results on real-world networks have demonstrated that our algorithm is more efficient in detecting community structures when compared with other well-known results.

同期刊论文项目
期刊论文 62 会议论文 11 获奖 6
期刊论文 37 会议论文 11
同项目期刊论文