Method and system for obtaining polygene risk score based on deep learning model

Abstract

The embodiment of the invention discloses a method and a system for obtaining a polygene risk score based on a deep learning model. The method comprises the following steps: preprocessing original SNPsample data; creating deep learning models of the relationship between SNP data and disease risk scores, wherein the deep learning models at least comprise a deep neural network model, a convolutional neural network model and a residual neural network model; optimizing the deep learning model; and scoring the SNP data to be scored based on the optimized deep learning model. According to the method, the corresponding deep learning model is trained by using a large number of SNP loci, so that the complex nonlinear relationship between the SNP loci and the hereditary diseases is fitted so as toconveniently, objectively and accurately provide the PRS score for a user.

Description

technical field [0001] The present invention relates to the technical field of gene detection and analysis, in particular to a method and system for obtaining a polygenic risk score based on a deep learning model. Background technique [0002] Single nucleotide polymorphisms (single nucleotide polymorphisms, SNPs) are the most common genetic variation in the human genome, and are of great significance to the study of genetic diseases. The traditional genome-wide association studies (GWAS) method can find out the most significant SNP loci that affect the disease, but in fact the occurrence of some diseases is due to the joint action of multiple SNP loci. The emergence of polygenic risk scores (Polygenic RiskScores, PRS) has brought a new method for the study of genetic diseases. PRS can estimate the genetic predisposition at the individual level and evaluate the predictive ability of genetic data in the clinical environment. It is also very useful. It may play an important r...

AI Technical Summary

Problems solved by technology

The existing polygenic risk score method is to calculate the risk score of the disease by linearly weighting the SNPs screened by GWAS. However, most of the SNPs screened by GWAS have only a small impact on the disease, and are usually really rel...

Images