Gene expression full-spectrum inference method based on generative adversarial network

Abstract

The invention discloses a gene expression data inference method based on a generative adversarial network. The method comprises the steps that gene expression data is preprocessed, wherein high-dimensional small-sample gene expression data of different platforms is processed to obtain gene expression data with a large sample quantity, a unified scale and the same format; (2) a gene generation model and a gene discrimination model are designed based on the generative adversarial network; and (3) an objective function and a training strategy of the network are designed, wherein sub-package cyclic training is performed on the preprocessed gene expression data, and an optimal generation model is obtained through continuous adjustment and optimization of the network. The method has good practicability and precision, and gene generation model and gene discrimination model construction and generative adversarial network training are adopted to realize gene expression data inference.

Description

technical field [0001] The invention belongs to the technical field of biological information, and in particular relates to a gene expression full-spectrum inference method based on a generative confrontation network. Background technique [0002] Today, the study of global gene expression profiling has been widely used in the fields of disease discovery, genetic perturbation, and complex disease classification. [0003] Gene expression profiling can describe the complete set of genes and their abundance expressed in tissues and cells under specific circumstances, and it reflects tissue or cell-specific phenotypes and expression patterns at the mRNA level. Through the bioinformatics search, query, comparison and analysis of gene expression profiles, relevant information such as gene transcription, gene regulation, signal transduction pathways, nucleic acid and protein structure and function and their interrelationships can be obtained. The full spectrum of gene expression i...

AI Technical Summary

Problems solved by technology

Due to the extensive non-linear correlations between gene expression profiles, the computational model is limited in its inference accuracy

Images