基于复合物信息和亚细胞定位信息的关键蛋白质识别

Identification of Essential Proteins Based on Protein Complexes Informationand Subcellular Locallization Information

针对蛋白质相互作用(protein-protein interaction,PPI)网络中存在大量噪声,以及现有关键蛋白识别方法的挖掘效率和预测准确率不高等问题,提出一种基于复合物信息和亚细胞定位信息(united protein complexes and subcellular locallizations,PCSL)来识别关键蛋白质。首先,整合PPI网络的拓扑属性、生物属性和空间属性构建加权网络,以降低PPI网络中噪声的影响,达到提升PPI网络的可靠性的目的;其次,根据复合物信息和空间信息,设计一种衡量蛋白质关键性的度量,从多维角度强化关键蛋白质在PPI中的重要程度;最后,利用基于PPI网络拓扑特性的寻优算法,设计一种新的试探策略,提升挖掘关键蛋白质的效率。PCSL方法应用在DIP(database of interacting protein)数据集上进行验证。实验结果表明,与其他10种关键蛋白质识别方法相比较,该方法具有较好的识别性能,能够识别更多的关键蛋白质。

Due to the noise in protein-protein interaction(PPI)network,the poor efficiency of detecting process,as well as the poor identification accuracy of essential proteins,a method was proposed.Protein complexes and subcellular locallizations(PCSL)were united.The model was based on protein complex information and subcellular locallizations to identify essential proteins.Firstly,this topological data,biological data and subcellular locallization data were integrated to construct weighted network to reduce the noise(the false positive and the false negative)impact in the original PPI network.Secondly,according to the complex property and space property of essential proteins,a measure was designed to measure the essentiality of proteins from weighted network,which emphasized the importance of the essential proteins from multi-dimension angle.Finally,based on optimal algorithm for essential proteins,a new probe strategy was designed to improve the efficiency of detecting essential proteins from weighted network.The PCSL method was applied to the DIP(database of interacting protein)dataset for predicting essential proteins.Compared with other ten methods of predicting essential proteins,the experimental results show that this method can identify more essential proteins and have better performance on predicting essential proteins.