Copy number variation prediction method and device, computer equipment and storage medium

Abstract

The invention relates to a copy number variation prediction method and device, computer equipment and a storage medium. The method comprises the following steps: receiving gene sequence files corresponding to an input sample to be detected and a contrast sample; analyzing the gene sequence files to obtain single nucleotide polymorphism sites; calculating model input parameters corresponding to theobtained single nucleotide polymorphism sites according to a preset input parameter calculation logic; inputting the model input parameters into a site copy number variation identification model to obtain a copy number state and a segmentation point location corresponding to each single nucleotide polymorphism site; and inputting the copy number state and the segmentation point location corresponding to each single nucleotide polymorphism site into a chromosome copy number variation identification model to obtain copy number variation states corresponding to the sample to be detected and percentage corresponding to each copy number variation state, wherein the chromosome copy number variation identification model is obtained according to a long-term and short-term memory network trainingmodel. The method can improve prediction accuracy.

Description

technical field [0001] The present application relates to the field of biotechnology, in particular to a copy number variation prediction method, device, computer equipment and storage medium. Background technique [0002] With the development of biotechnology, there has been a technology to detect whether there is abnormal chromosome copy number in a sample. Copy Number Variation (CNV) is caused by genome rearrangement, generally referring to a genome with a length of more than 1kb The copy number increase or decrease of large fragments is mainly manifested as submicroscopic level deletions and duplications. CNV is an important part of genome structural variation (Structural Variation, SV). The mutation rate of CNV loci is much higher than that of SNP (Single Nucleotide Polymorphism), which is one of the important pathogenic factors of tumor diseases. [0003] However, the traditional technical solution is to use the genome sequencing data of a sample to be tested, and th...

AI Technical Summary

Problems solved by technology

[0003] However, the traditional technical solution is to use the genome sequencing data of a sample to be tested, and through data analysis methods, to determine whether there is an abnormal chromosome copy number in the sample, such as predicting through the Maldives sequence, but because the Maldives sequence is continuous Limited and single mode, which will cause inaccurate detection

Images