A Differential Evolution-Based Method for Predicting the Structure of Protein Dimers

Abstract

A protein dipolymer structure predicting method based on differential evolution includes the steps of firstly, predicting structural information of two chains of protein dipolymers through an I-TASSERsever so as to improve the prediction precision of the space structure of each single chain of protein; secondly, converting the existing protein dipolymer structure predicting problem into the optimal individual search optimizing problem through the design of population individuals so as to reduce the calculation price; thirdly, searching for the optimal individual through a differential evolution algorithm so as to improve the prediction precision of the protein dipolymer structure. The protein dipolymer structure predicting method based on differential evolution is low in calculation priceand high in search efficiency.

Description

technical field [0001] The invention relates to the fields of bioinformatics, intelligent optimization and computer application, in particular to a method for predicting protein dimer structure based on differential evolution. Background technique [0002] Protein is ubiquitous and indispensable in life activities, and it undertakes a variety of biological functions in organisms, such as the catalysis of enzyme proteins, the transport of membrane proteins, and the immune function of antibody proteins. In order to complete these complex biological functions, proteins often need to interact with other proteins to form high-molecular complexes combined with non-covalent bonds. Among them, the polymer complex composed of two protein molecules is called protein dimer. Studying the spatial structure of protein dimers is not only crucial for understanding the biological functions of protein dimers and understanding the principles and mechanisms of protein-protein interactions, but...

AI Technical Summary

Problems solved by technology

Among them, Z-DOCK takes an average of 11.5 minutes to predict the spatial structure of a protein dimer, which cannot meet the actual needs for the prediction method directly starting from the single-chain structure of the protein; the spatial structure of the protein dimer predicted by ClusPro The root mean square deviation from the experimentally determined spatial structure is in There should be a large gap between the actual distance

[0004] In summary, the existing methods for predicting the spatial structure of protein dimers are still far from the requirements of practical applications in terms of calculation cost and prediction accuracy, and urgently need to be improved.

Images