【摘要】 现有关键蛋白质识别算法对生物信息考虑不全面、识别准确率亦有待提高,针对此问题,提出一种高效关键蛋白质识别算法PDWS。首先,结合由亚细胞定位信息获取到的蛋白质位置和蛋白质相互作用网络边聚类系数构建加权网络;其次,依据蛋白质所处亚细胞位置,提出亚细胞定位区室子网参与度指标;最后,融合亚细胞定位区室子网参与度和蛋白质复合物子网参与度指标,多维度度量蛋白质关键性。在DIP和Krogan两个标准数据集上的实验结果表明,PDWS算法性能优于PeC、PCSD等已有算法,可识别出更多特定结构的关键蛋白质,且识别精度分别达到0.76与0.73。更多还原

【Abstract】 Existing essential protein recognition algorithms don’t consider biological information comprehensively,and the recognition accuracy rate needs to be improved. To solve this problem,this paper proposed an efficient essential protein identification algorithm named PDWS. First,it combined the protein position obtained from the subcellular localization information and the edge clustering coefficient of the protein interaction network to construct a weighted network. Second,based on the analysis of the subcellular location of the protein,it proposed a subcellular location compartment subnetwork participation index. Finally,integrating subcellular localization compartment subnetwork participation index and protein complex subnetwork participation index,it multi-dimensionally measured the criticality of protein. The experimental results on the two standard datasets of DIP and Krogan show that PDWS can identify more specific structured essential proteins with recognition accuracies reaching0. 76 and 0. 73 respectively,which shows PDWS outperforms Pe C,PCSD and other existing algorithms.更多还原