Method for identifying key protein using artificial bee colony optimization algorithm of foraging mechanism

Abstract

The invention discloses a method for identifying key protein using an artificial bee colony optimization algorithm of a foraging mechanism. The method comprises: converting a protein-protein interaction network to an undirected graph, obtaining ribonucleic acid genetic expression values corresponding to protein, preprocessing edges and nodes of the protein-protein interaction network, establishing a dynamic protein-protein interaction network, selecting known key protein as a honey source, honey bees searching neighbourhood of the honey source, following bees searching neighbourhood of the honey bees, updating the honey sources, investigating bees searching new honey sources in a global manner, updating the honey sources, and generating the key protein. The method can accurately identify the key protein. Results of simulation experiments show that sensitiveness, specificity, positive predictive values, negative predictive values and other performance indexes are relatively excellent. Compared with other key protein identification method, the identification process of key protein realized by combining optimizing characteristics of artificial bee colony with characteristics of the protein-protein interaction network improves identification accuracy rate of the key protein.

Description

[0001] 【Technical field】 [0002] The invention belongs to the field of biological information, and relates to a method for identifying key proteins in a dynamic protein interaction network, in particular to a method for identifying key proteins using an artificial bee colony optimization algorithm using a foraging mechanism. [0003] 【Background technique】 [0004] Key proteins are proteins necessary for the survival and reproduction of organisms, and the absence of key proteins will result in the loss of the function of the 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 work. In biology, the identification of key proteins mainly relies on biological experimental methods, such as single gene selection and conditional gene knockout. Although the results obtained through these experimental techniques are clear and effective...

AI Technical Summary

Problems solved by technology

[0010] Based on the defects of the above key protein identification methods, the main reason is that the dynamics of the protein interaction network is not considered, only the local features are considered and the globality of the network and the false positive of the protein interaction network data are ignored, and the accuracy of key protein identification is low.

Images