An accurate prediction method for disease-causing genetic variants

Abstract

The invention discloses an accurate prediction method of pathogenic genetic variation, which divides known pathogenic variation into two categories: database variation and training set positive variation, database variation obtains part of the evidence in ACMG guidelines, and simulates the patient's condition by random extraction method The positive genetic variation data in the training set and the corresponding phenotype data are used to calculate the features related to the guideline, and the phenotype-related features are calculated using the ERIC-based calculation method, combined with the existing features related to the judgment of pathogenicity, using machine learning algorithms, Realize the prediction of mutation pathogenicity by comprehensively considering genotype data and phenotype data; this method solves the problem of incomplete clinical phenotype data, noise and inaccurate description in actual scenarios, which lead to the inability to accurately predict the pathogenicity of mutations question.

Description

technical field [0001] The invention relates to a prediction method, in particular to an accurate prediction method of pathogenic genetic variation. Background technique [0002] Rare disease genetic prediction refers to the process of finding causative genetic variants from a patient's genome that can explain the patient's clinical phenotype. Accurate and rapid genetic prediction is related to the later treatment, care and even life of patients. However, it is very difficult to accurately predict the pathogenic genetic variation. In actual scenarios, a series of problems such as incomplete clinical phenotype data, noise and inaccurate description make it impossible to accurately predict the pathogenicity of the variation. Contents of the invention [0003] Aiming at the above-mentioned deficiencies in the prior art, the present invention provides an accurate prediction method of pathogenic genetic variation, which solves the problem of incomplete clinical phenotype data,...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the above-mentioned deficiencies in the prior art, the present invention provides an accurate prediction method of pathogenic genetic variation, which solves the problem of incomplete clinical phenotype data, noise and inaccurate description in actual scenarios, which lead to the inability to carry out mutation-causing disease. The problem of accurate prediction of sex

Images