Method for identifying key protein by adopting improved flower pollination algorithm

Abstract

The invention discloses a method for identifying a key protein by adopting an improved flower pollination algorithm. A protein-protein interaction network is converted into an undirected graph, previous Q proteins having the largest choice degree serve as pollen individuals, the PeC centrality is measured, compound information is determined, subcellular localization information is determined, pollen significance is evaluated, a pollen position is updated, and an identified key protein is output. The topological attributes of the protein network are considered and the biological characteristicsof the protein network are fused during evaluation of the pollen significance, and the key protein can be accurately identified. A simulation experiment result shows that the index properties such asaccuracy, specificity and sensitivity are more excellent. Compared with other key protein identifying methods, the key protein identifying process is achieved by combining with the topological attributes and biological characteristics of the protein network, and the key protein identifying accuracy is improved.

Description

【Technical field】 [0001] The invention belongs to the field of biological information, and relates to a method for identifying key proteins in protein interaction networks, in particular to a method for identifying key proteins by adopting an improved flower pollination algorithm. 【Background technique】 [0002] Key proteins are essential proteins in the life activities of cells, and the absence of key proteins will lead to the loss of the function of the relevant protein complex and cause the organism to fail to survive. Since key proteins play an important role in life activities, the prediction and identification of key proteins has become an important research task. Identifying key proteins is of great significance for the study of cell growth regulation. In addition, in the field of biomedicine, the identification of key proteins is of great significance for the discovery of disease-causing genes and the identification of drug targets, and has important application valu...

AI Technical Summary

Problems solved by technology

[0008] Although the identification of key proteins has attracted more and more attention, the accuracy of current identification methods combined with network information is still low, and most methods use a small number of parameters or features to analyze key proteins in isolation or piecemeal, leading to critical The accuracy of protein identification is low

[0009] Combining the shortcomings of the above-mentioned key protein identification methods, most of the methods only consider the topological characteristics of the network and the false positives of protein interaction network data, while ignoring the intrinsic biological significance of key proteins. Although some methods increase biological data, However, the consideration is not comprehensive enough, resulting in unsatisfactory identification results of key proteins

Images