Inference method of stepwise regression gene regulatory network

Abstract

The invention discloses an inference method of a stepwise regression gene regulatory network. The method comprises the following steps of: A, reading a gene expression data matrix and a gene perturbation data matrix; B, confirming whether the gene expression data matrix and the gene perturbation data matrix are standardized data or not; C, respectively carrying out data normalization on the gene expression data matrix and the gene perturbation data matrix to form the standardized data; D, analyzing the standardized data and calculating all inter-gene correlation coefficient matrixes; and E, visualizing the inter-gene correlation coefficient matrixes into a network to obtain a gene regulatory network chart. The method can select optimal regression subsets to solve the problem of high-dimension small-sample experimental data, gradually select the most influential regulator for a target gene, accord with the true condition of the gene regulatory network, and be superior to similar methods in calculation precision and calculation efficiency along with the enlargement of the gene regulatory network scale and the network sparsity.

Description

technical field [0001] The invention relates to the field of computers, and relates to an inference method of stepwise regression gene regulation network. Background technique [0002] Inferring gene regulatory networks from large-scale gene expression measurement datasets is computationally and experimentally challenging. The main reason is that, even without considering the specific biochemical reaction dynamics (such as the dynamic change of the gene regulatory network), there are quite a lot of possibilities for the network structure composed of a certain number of genes. Therefore, the biggest challenge for gene network prediction or algorithm construction is that the data dimension is too large, the experimental samples are limited, and there are many possibilities for the related network structure. [0003] Successfully constructing gene regulatory networks from gene expression data often requires complex calculations, or costly and time-consuming upfront experimenta...

AI Technical Summary

Problems solved by technology

Through such an assumption, the data dimension is reduced, and the gene regulatory coefficient matrix is ​​converted into a sparse matrix, which is indeed in line with the theory that the biological network is a sparse network, but at the same time, it also causes defects in the selection of regulators for each gene from quantity to quality :

[0006] 2. From the perspectiv

Images