PPI网络的改进马尔科夫聚类算法

蛋白质相互作用(PPI)网络是生物信息学的一个新的研究领域。近年来马尔科夫(MCL)聚类算法在未知蛋白质的功能模块预测方面发挥了重要作用,但是聚类质量不高,为此提出了一种基于突变因子和惩罚因子及重新定义解释聚类结果的MCL聚类算法。该算法采用惩罚因子,惩罚质量较大的吸引子；采用突变因子在算法后期断绝初始转移概率对转移概率的束缚。算法在PPI网络数据集上进行了测试,结果表明该算法不但可以抑制小类的产生,而且聚类结果的质量在Avg.F方面相对于基本MCL算法提高了13.1%。

Improved MCL Clustering Algorithm in PPI Networks

Protein-protein interaction (PPI) network is a new research field in the bioinformatics.Recently MCL clustering algorithm has played an important role in the field of predicting the function of unknown proteins.However,the quality of the clustering result is low.An improved MCL clustering algorithm was proposed in this paper,in which the penalty and mutation factors are introduced.New structured regulation operation takes place of expansion operation in the basic MCL algorithm.Experiments were performed on PPI data.And the results show that the new algorithm can not only minimize the number of small clusters,but also improve F-measure and Avg.F value compared with the basic MCL algorithm.