The mount of available biological data is growing at a tremendous pace. However, stil) a lot of biological information such as some information about protein-protein interaction( PPI) is undiscovered. Those unknown protein information to the study of biological process is essential. Therefore, in recent years, mining and researching unknown biological information has already attracted many people' s attention. However, revealing hidden and unknown links of biological network takes the high experimental and time costs. Thus, this paper proposed a new method based on the similarity between proteins to predict implicit or previously unknown links in the weighted PPI networks, and the weight of network could be obtained by combining the topology of PPI network and the inherent information of proteins. It used the MIPS database to evaluate the experimental results show that the algorithm is excellent accuracy performance.%当前可用的生物数据在不断地迅速增长,仍有很多生物信息如蛋白质交互信息(protein-protein interaction,PPI)还未被发现,而这些潜在的或未知的信息对生物过程的研究是至关重要的.近年来,对未知生物信息的挖掘和研究吸引了很多人的关注.通过实验检测方法来发现这些信息是非常耗时耗力的,所以链接预测成为一种新的挖掘这些信息的指导方法.基于蛋白质交互网络并融合了基因表达数据信息,从拓扑和基因表达两个方面的信息来构建PPI权值网络,提出了一种在权值网络中基于相似度比较的链接预测的新方法来预测PPI网络中未知的交互信息.使用MIPS数据库评估了实验结果,表明了该算法有很好的准确率和良好的性能.
展开▼
