Genetic variation pathogenicity prediction method and device, storage medium and computer equipment

Abstract

According to the heritable variation pathogenicity prediction method and device, the storage medium and the computer equipment, firstly, the feature data corresponding to the to-be-predicted gene variation site is determined, then the feature data is predicted through the heritable variation pathogenicity prediction model, and the heritable variation pathogenicity prediction result is obtained; the hereditary variation pathogenicity prediction model is obtained by integrating a plurality of target prediction sub-models designed according to different pathogenicity grade classifications, and when each target prediction sub-model is trained, feature data of training gene variation sites classified according to the corresponding pathogenicity grade is used as a training sample; according to the genetic variation pathogenicity prediction model, the pathogenicity grade classification of the variation site of the training gene is used as a sample tag for training, and meanwhile, a training sample contains all mutation types, so that the genetic variation pathogenicity prediction model is suitable for all mutation types; and an accurate genetic variation pathogenicity prediction result can be obtained according to the input feature data of the gene variation site.

Description

technical field [0001] The present application relates to the technical field of gene detection, in particular to a method, device, storage medium and computer equipment for predicting the pathogenicity of genetic variation. Background technique [0002] With the gradual maturity of high-throughput sequencing technology and the decreasing cost, sequencing has become an important means of clinical research and diagnosis. After years of accumulation of clinical applications, major public genome databases have collected a large number of variant sites, and accurate interpretation of these variant sites is the key to the realization of human precision medicine. [0003] In 2015, the American Society of Medical Genetics and Genomics (ACMG) released the classification and interpretation standards of gene variation sites, and divided the gene variation sites into five categories: pathogenic, likely pathogenic, unclear clinical significance, possible Benign and benign, to assess th...

AI Technical Summary

Problems solved by technology

[0004] The purpose of this application is to at least solve one of the above-mentioned technical defects, especially the technical defect that it is impossible to predict all mutation types in the prior art, so that the prediction accuracy is not high

Images