Local Lipschitz support surface-based dual-layer differential evolution protein structure prediction method

Abstract

The invention discloses a local Lipschitz support surface-based dual-layer differential evolution protein structure prediction method. The method comprises the steps of firstly, selecting an optimal conformation in a current population according to an energy value, calculating distances from other conformations to the optimal conformation, and ranking all the conformations according to the distances; secondly, selecting part of the conformations closest to the optimal conformation to establish a Lipschitz lower bound support surface, calculating an energy lower bound estimation value of each selected conformation, and calculating an average error of an actual energy value and the lower bound estimation values; and finally, dividing an algorithm into two layers according to the average error, randomly selecting the conformation to perform fragment assembling to generate a new conformation by the first layer, and performing fragment assembling according to the optimal conformation to generate a new conformation by the second layer, so as to guide the algorithm to be quickly and reliably converged to a region with the lowest energy. The method is high in prediction precision and relatively low in calculation cost.

Description

technical field [0001] The invention relates to the field of biological informatics, intelligent optimization and computer application, and in particular to a method for predicting protein structure of double-layer differential evolution based on local Lipschitz support surface. Background technique [0002] The smooth implementation of the Human Genome Project marks the completion of the sequencing of the 3 billion base pairs of human genome DNA. For more than a decade, the Human Genome Project has continuously deepened human understanding of ourselves and diseases, and has had a profound impact on biology, medicine, mathematics and computer science. However, so far, the blueprint drawn by former US President Clinton at the time: "revolutionizing the way we diagnose, prevent and treat the vast majority of diseases" has not yet emerged. In fact, the gene map only depicts the amino acid sequence of the protein (ie, the primary structure of the protein), and the protein can o...

AI Technical Summary

Problems solved by technology

X-ray crystallography is the most effective method for determining protein structure, and the accuracy it can achieve is unmatched by other methods. The main disadvantages are that protein crystals are difficult to cultivate and the period of crystal structure determination is long; multidimensional nuclear magnetic resonance (NMR) method can Directly determine the conformation of proteins in solution, but due to the large amount of samples required and high purity requirements, currently only small molecular proteins can be determined

In general, there are two main problems in the structure experimental determination method: on the one hand, for the main target membrane protein of modern drug design, it is extremely difficult to obtain its structure through experimental methods; on the other hand, the determination process is time-consuming, costly and laborious, for example, Determining a protein using NMR usually costs $150,000 and half a year

Then, as the length of the sequence increases, the energy model surface of the protein becomes more and more complex, which makes the population algorithm easy to fall into local optimum, and cannot accurately search for the lowest energy conformation, thus reducing the prediction accuracy

Moreover, the current simple evolutionary algorithm does not properly apply the effective technology of fragment assembly, resulting in an extremely large search space and high computational cost.

[0006] Therefore, the existing protein structure prediction method based on population algorithm has defects in prediction accuracy and calculation cost, and needs to be improved.

Images