基于动态图的PPI网络构建和复合物挖掘算法研究

Research on PPI Network Construction and Complex Mining Algorithm Based on Dynamic Graph

动态蛋白质网络的构建和复合物挖掘问题是目前研究的热点.针对现有的算法在解决前述问题上的不足,文中考虑了蛋白质的活性周期和连接强度,首先提出了一种基于动态图的蛋白质网络构建算法.然后基于密度聚类设计了一种在动态蛋白质网络上挖掘复合物的算法(PCMA).整个挖掘过程包含三个步骤:基于DBSCAN(Density-Based Spatial Clustering of Applications with Noise)算法的蛋白质复合物生成;基于合并增益的蛋白质复合物合并和基于归属度的复合物调整.在多个公开的生物数据集上进行了实验,实验结果表明,所提算法在查全率、查准率和F-measure方面的性能都要优于现有的算法,且对输入参数不敏感.在保证蛋白质复合物挖掘准确性的前提下,算法的时间复杂度处于一个合理的范围之内.

Dynamic protein network construction and complex mining problem is a hot topic.In view of the shortcomings of existing algorithms in solving the above problems,a protein network construction algorithm based on dynamic graph is firstly proposed by considering the active period and the connection strength of proteins in this paper.Then,a protein complex mining algorithm(PCMA)on dynamic protein network is designed based on the density clustering.The whole mining process consists of three steps:the generation of protein complex based on DBSCAN(density-based spatial clustering of applications with noise)algorithm;the combination of protein complex based on the combination gain and the adjustment of protein complex based on the degree of membership.Experiments are carried out on several open biological datasets.The experimental results show that the performance of the proposed algorithm is better than that of the existing algorithms in terms of recall,precision and F-measure,and it is not sensitive to the input parameters.On the premise of ensuring the accuracy of protein complex mining,the time complexity of the proposed algorithm is in a reasonable range.