Tumor key gene identification method based on multi-objective particle swarm algorithm of preference grid and Levi flight

Abstract

The invention discloses a tumor key gene identification method based on a multi-objective particle swarm algorithm of a preference grid and Levi flight. The method comprises the steps that a classification information index is used to filter an original gene expression profile data set to acquire a primary gene pool; the GCS value of the gene category sensitivity information of each gene in the initial gene pool is calculated, and then particles are encoded by the GCS value; the classification accuracy of gene subsets on an extreme learning machine ELM and the size of the gene subsets are targeted to build a multi-objective optimization model; and the final gene subset is searched through the established multi-objective model, and then the key genes of a tumor are identified. In terms of the multi-objective optimization model, the method provided by the invention can quickly and efficiently identify a small number of key gene subsets with good classification performance in the primarygene pool through the multi-objective model.

Description

technical field [0001] The invention belongs to the application field of computer analysis technology of tumor gene expression spectrum data, and in particular relates to a tumor key gene identification method based on preference grid and Levy flight multi-objective particle swarm optimization. Background technique [0002] Since the 1980s, microarray technology has been widely used in disease diagnosis. It helps medical staff and researchers access the expression levels of thousands of genes simultaneously, ultimately generating microarray data. Classification and prediction of the diagnostic class of a sample by gene expression profiling, which has been successfully applied to the classification of cancer. However, complex gene expression profile data still faces many challenges when developing an effective classifier: First, gene expression profile data has a high dimensionality, and there are complex and unknown relationships between each dimension and genes. Second, t...

AI Technical Summary

Problems solved by technology

Third, the sample size of gene expression profiling datasets is small, which leads to higher computational complexity and more prediction errors

From this perspective, these methods waste computational cost in searching for solutions that do not require

Images