A Novel Method for Predicting Essential Proteins by Integrating Multidimensional Biological Attribute Information and Topological Properties

Abstract

Background: Essential proteins are indispensable to the maintenance of life activities and play essential roles in the areas of synthetic biology. Identification of essential proteins by computational methods has become a hot topic in recent years because of its efficiency. Objective: Identification of essential proteins is of important significance and practical use in the areas of synthetic biology, drug targets, and human disease genes. Method: In this paper, a method called EOP(Edge clustering coefficient -Orthologous-Protein) is proposed to infer potential essential proteins by combining Multidimensional Biological Attribute Information of proteins with Topological Properties of the protein-protein interaction network. Results: The simulation results on the yeast protein interaction network show that the number of essential proteins identified by this method is more than the number identified by the other 12 methods(DC, IC, EC, SC, BC, CC, NC, LAC, PEC, CoEWC, POEM, DWE). Especially compared with DC（Degree Centrality）, the SN(sensitivity) is 9% higher, when the candidate protein is 1%, the recognition rate is 34% higher, when the candidate protein is 5%, 10%, 15%, 20%, 25% the recognition rate is 36%, 22%, 15%, 11%, 8% higher respectively. Conclusion: Experimental results show that our method can achieve satisfactory prediction results, which may provide references for future research.

Computational prediction of allergenic proteins based on multi-feature fusion

“…For building a machine learning classifier for protein sequences, it is necessary to convert biological sequence information into feature vector information that can be processed by computers (Lu et al, 2022;Wang et al, 2023b;Dao et al, 2023;Le, 2023;Zhu et al, 2023). Therefore, it is very imortant to select appropriate feature extraction methods.…”