Gene regulation and control network reconstruction method based on gene expression data

Abstract

The invention provides a gene regulation and control network reconstruction method based on gene expression data, and relates to the technical field of gene regulation and control network reconstruction in bioinformatics. The method comprises the following steps that: obtaining gene expression quantity data required for reconstruction; carrying out normalization processing on the data; carrying out predictive modeling on a target gene expression quantity; predicting the target gene expression quantity; analyzing a regulation and control relationship between an input feature gene and a target gene; and reconstructing the gene regulation and control network. By use of the gene regulation and control network reconstruction method based on the gene expression data, high-accuracy gene regulation and control network modeling is realized according to gene expression data, and an Elman neural network optimized by a differential evolution algorithm predicts the gene expression quantity so as tohave the advantages of high operation speed and high accuracy. In addition, simulation data can be used for solving the problem of an insufficient data quantity is solved, the gene regulation and control network which is finally established exhibits good accuracy, has a wide applicable range, can be suitable for different pieces of gene expression data and exhibits good transportability.

Description

technical field [0001] The invention belongs to the technical field of gene regulation network reconstruction in bioinformatics, and in particular relates to a gene regulation network reconstruction method based on gene expression data. Background technique [0002] Gene regulatory networks exist widely in prokaryotes and eukaryotes, and are networks that describe gene-gene interactions. Gene regulatory network reconstruction can simulate the synergistic relationship between genes and discover the mechanism of genes' influence on biological life cycle and life activities, which is an important research direction in the field of bioinformatics. Accurate gene regulatory network models can help people understand the dynamic structure of gene regulatory networks, which is of great significance for revealing life processes. [0003] There are many complex factors in the process of gene expression, such as random behavior, gene replication, and feedback loops, etc., which lead to...

AI Technical Summary

Problems solved by technology

[0003] There are many complex factors in the process of gene expression, such as random behavior, gene replication, and feedback loops, etc., which lead to complex characteristics of gene regulatory networks such as nonlinearity and randomness; at the same time, the limited number of samples of gene expression data leads to time aggregation bias, data Significant noise exists, increasing the complexity of gene regulatory network reconstruction

Among the gene regulatory network reconstruction methods widely used at present, the linear gene regulatory network reconstruction methods, such as Boolean network and linear combination model, can describe the gene regulatory network simply, but it is difficult to accurately reflect the nonlinear relationship between genes; Linear gene regulatory network reconstruction methods, such as Bayesian networks, dynamic Bayesian networks, models based on differential equations, etc., have high accuracy of the model, but there are problems of high computational complexity and poor generalization

Images