Single-gene or polygene copy number detection system and method based on next generation sequencing technology

Abstract

The invention discloses a single-gene or polygene copy number detection system and method based on a next generation sequencing technology. The single-gene or polygene copy number detection system uses a machine learning algorithm based on a regularized linear regression model (LASSO) and shifting level models to infer copy number variation of single-gene or polygene exons, and includes successively connected sequence alignment module, repeat sequence removal module, calculation coverage depth module, standardized coverage depth module, regularized linear regression training module (LASSO linear regression training module), coverage depth prediction module, breakpoint detection and log2Ratio value correction module, and copy number state inference module. The single-gene or polygene copy number detection system and method based on a next generation sequencing technology utilize the machine learning method to train large-scale next-generation targeted capture sequencing data, and combine the shifting level models to reduce technical and biological errors caused by batch effects, thereby achieving better copy number detection accuracy and precision.

Description

technical field [0001] The present invention belongs to the field of biomedicine, in particular to a data analysis method related to copy number variation detection in the field of next-generation sequencing, and in particular to a single-gene or multi-gene copy number detection system based on next-generation sequencing technology; in addition, the present invention also It relates to a method for detecting the copy number of a single gene or multiple genes based on a next-generation sequencing technology. Background technique [0002] Copy number variation is responsible for the development of many genetic and rare diseases. For example, α-thalassemia, spinal muscular atrophy, Duchenne muscular dystrophy, etc., are all caused by abnormal copy number of exons on one or more genes. Therefore, the copy number detection of these genes plays a crucial role in the control of genetic diseases and the prevention of birth defects. Traditional detection methods such as qPCR (real-...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention: the present invention discloses a single-gene or multi-gene copy number detection system and method based on next-generation sequencing technology, which solves the problem of single-gene or multi-gene copy number variation detection in the field of next-generation sequencing technology. Strong secondary effects and low detection accuracy

Images