Protein structure prediction method based on ISFS (Improved Stochastic Fractal Search) algorithm

Abstract

The invention relates to the field of protein structure prediction, and designs a protein structure prediction method based on an ISFS (Improved Stochastic Fractal Search) algorithm. According to themethod, the SFS algorithm is introduced into protein structure prediction, and a diffusing process an an updating process in the protein structure prediction are improved. In the diffusing process, Levy flight is utilized to replace Gaussian distribution so as to reinforce the global searching ability; and in the updating process, feedback information is introduced, so that search jumps out of thelocal optimum. Compared to SFS, the disclosed method has high performance in the aspect of solving a problem of various nonlinear functions (e.g., a protein structure prediction problem). According to data obtained by experiments and comparison results of other methods, the method can more comprehensively search a corresponding protein minimum free energy value so as to obtain a more stable protein structure.

Description

technical field [0001] The invention relates to a random fractal search algorithm, in particular to a protein structure prediction method for improving the random fractal search algorithm by utilizing Levy flight to realize population diffusion and introducing feedback regulation to make the search jump out of local search. Background technique [0002] Protein is the material basis of all living things and the most important part of living things. With the development of life science and the successful completion of the human genome, life science has entered the post-gene era, and on this basis, bioinformatics has emerged as the times require. Therefore, obtaining the protein structure on the basis of known genes has become a new research topic. Protein structure prediction is one of the most important tasks in protein research, and it is also of great significance for revealing the secrets of life. [0003] However, the current main physical techniques for obtaining prot...

AI Technical Summary

Problems solved by technology

[0003] However, the current main physical techniques for obtaining protein structures (such as X-ray diffraction and nuclear magnetic resonance (NMR)) require strict laboratory requirements and consume a lot of research cost and time, which leads to the developmental structure database of proteins lagging far behind protein sequences. database development

Images